feat: checkpoint distributed gguf runtime stories

2026-07-15 23:42:58 +03:00
parent eaf00f6add
commit 1fe31ef38d
60 changed files with 8478 additions and 105 deletions
--- a/.scratch/distributed-gguf-runtime/evidence/DGR-006/results.json
+++ b/.scratch/distributed-gguf-runtime/evidence/DGR-006/results.json
@@ -0,0 +1,161 @@
+{
+  "story": "DGR-006",
+  "date": "2026-07-15",
+  "evidence_kind": "synthetic-unit (pure-numpy dense-Llama parity + boundary contract)",
+  "targeted_tests": {
+    "file": "tests/test_boundary_adapter.py",
+    "result": "22 passed"
+  },
+  "compileall": "exit 0",
+  "git_diff_check": "clean",
+  "parity_tolerance": {
+    "logits_atol": 1e-06,
+    "greedy_tokens": "identical"
+  },
+  "full_suite_with_files": {
+    "failed": 20,
+    "passed": 715,
+    "skipped": 13,
+    "errors": 12,
+    "seconds": 239.77
+  },
+  "full_suite_clean_tree": {
+    "failed": 20,
+    "passed": 693,
+    "skipped": 13,
+    "errors": 12,
+    "seconds": 243.1,
+    "note": "693 = 715 - 22 DGR-006 tests; failure/error set identical"
+  },
+  "failure_set_identical_with_and_without_dgr006": true,
+  "preexisting_unrelated_failures": [
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_capability_and_health_round_trip"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_checksum_algorithms_verify"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_cross_language_roundtrip_python_and_cpp"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_defaults_are_stable_for_backward_compatibility"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_fragment_and_reassemble_round_trip_with_checksums"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_message_header_carries_every_required_field"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_named_tensor_bundle_describes_shape_dtype_byteorder_and_fragments"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_reassemble_detects_fragment_corruption"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_service_descriptor_exposes_all_operations"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_session_response_carries_structured_status_and_results"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_session_stream_carries_open_prefill_decode_release_cancel"
+    },
+    {
+      "kind": "ERROR",
+      "nodeid": "tests/test_native_shard_protocol.py::test_unknown_fields_are_preserved_for_forward_compatibility"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_activation_compression.py::test_compressible_body_uses_zstd_when_it_clears_savings_policy"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_activation_compression.py::test_incompressible_body_stays_raw_after_measured_trial"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_activation_compression.py::test_malformed_zstd_and_legacy_raw_bodies_are_handled_explicitly"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_activation_compression.py::test_threshold_requires_both_byte_and_ratio_savings"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_dynamic_routing.py::test_admin_can_replace_a_served_model_and_release_it"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_gossip_and_relay.py::test_activation_compression_round_trips_and_skips_small_bodies"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_manual_route_benchmark.py::test_benchmark_records_one_and_two_node_routes"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_manual_route_benchmark.py::test_clients_without_route_are_unaffected"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_manual_route_benchmark.py::test_invalid_route_shape_is_400"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_manual_route_benchmark.py::test_pinned_route_uses_named_node"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_manual_route_benchmark.py::test_unknown_route_node_is_400"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_node_doctor.py::test_cli_doctor_flags_select_what_is_validated"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_openai_gateway.py::test_langchain_chat_openai"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_toploc_calibration_dispatch.py::test_calibration_run_dispatches_only_solo_capable_nodes"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_toploc_calibration_dispatch.py::test_calibration_run_node_without_commitment_endpoint_is_skipped_not_failed"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_toploc_calibration_dispatch.py::test_calibration_run_persists_corpus_and_results_endpoint_reports_it"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_tracker_capability_admission.py::test_an_enforcing_tracker_never_routes_a_node_whose_proof_does_not_cover_it[invalid]"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_tracker_control_plane.py::test_tracker_startup_does_not_import_or_load_model_backends"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_tracker_routing.py::test_shard_heal_cycle_surviving_node_covers_dead_peers_gap"
+    },
+    {
+      "kind": "FAILED",
+      "nodeid": "tests/test_tracker_routing.py::test_torch_node_applies_tracker_load_shard_directive"
+    }
+  ]
+}