feat: emit native DGR-003 shard identity

This commit is contained in:
Dobromir Popov
2026-07-14 11:31:10 +03:00
parent f844ae6567
commit ec36290863
7 changed files with 451 additions and 18 deletions

View File

@@ -138,3 +138,49 @@ schema versions, and owned range. At `SessionOpen`, compare its
A digest match is not certification. Only tracker-recorded evidence from the A digest match is not certification. Only tracker-recorded evidence from the
same exact fingerprint and a real complete distributed forward can move that same exact fingerprint and a real complete distributed forward can move that
recipe out of dark status. recipe out of dark status.
## Native emission closure — 2026-07-14
Status: **done**. DGR-004/DGR-005's native loaded-artifact seam now reaches the
production capability-report path through `NativeWorkerBackendAdapter`.
### Files changed
- `packages/node/meshnet_node/native_backend.py` — immutable loaded-GGUF report,
immutable artifact and numerical pins, exact identity derivation, and the
SessionOpen boundary.
- `packages/node/meshnet_node/doctor.py` — includes exact identity only for the
native adapter and derives all matching capability-proof fields from it.
- `tests/test_native_identity_emission.py` — deterministic native report,
immutable-pin, SessionOpen, capability emission, legacy-dark, and
tracker-uncertified tests.
- This issue, `prd.json`, and this evidence directory.
### Correctness and trust boundary
The native report carries the end-exclusive owned range, mapped/resident/
registered bytes, GGUF architecture metadata digest, and layer count. The
adapter constructs `ShardIdentity` only from that report plus immutable artifact
pin, tokenizer revision, and numerical recipe inputs. It does not accept a
caller-supplied shard range.
`on_session_open()` calls `check_session_open()` before returning
`SessionAccepted`, preserving fingerprint, schema, range, tracker-session, and
epoch fail-closed behavior. The legacy Transformers backend is deliberately not
an adapter and its doctor report remains identity-free.
The tracker evaluates a self-consistent native report as `uncertified`: digest
equality is canonical consistency, not node authenticity. Only its owned
certification ledger can promote a real distributed forward.
### Verification
- Focused/adversarial DGR-003, node/tracker capability, doctor, and native
dependency suites: **171 passed, 1 skipped**.
- Native protocol CMake configure/build plus CTest: **1/1 passed**.
- `compileall`, Ruff, and `git diff --check`: pass.
- Full deterministic suite: **902 passed, 13 skipped** (255.01s).
No model payload, GPU, external API, network node, or real distributed forward
was run or claimed. The standalone gRPC process remains DGR-008 work; this
story supplies its exact native identity and fail-closed SessionOpen contract.

View File

@@ -1,5 +1,26 @@
# DGR-003 final verification — 2026-07-14 # DGR-003 final verification — 2026-07-14
# Native emission closure — 2026-07-14
PYTHONPATH=packages/node:packages/tracker:packages/contracts /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_native_identity_emission.py tests/test_runtime_recipe_identity.py tests/test_node_capability.py tests/test_tracker_capability_admission.py tests/test_node_doctor.py tests/test_llama_cpp_dependency.py
# result: 171 passed, 1 skipped in 7.07s
ruff check packages/node/meshnet_node/native_backend.py packages/node/meshnet_node/doctor.py tests/test_native_identity_emission.py
# result: All checks passed
git diff --check
# result: pass
/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m compileall packages tests
# result: pass
/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake -S packages/node/native -B build/dgr-003-native-protocol -DCMAKE_PREFIX_PATH=/tmp/pbsrc/install
/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/cmake --build build/dgr-003-native-protocol -j2
/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/ctest --test-dir build/dgr-003-native-protocol --output-on-failure
# result: configured and built shard_protocol_conformance; 1/1 CTest passed
/run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q
# result: 902 passed, 13 skipped in 255.01s
PYTHONPATH=packages/node:packages/tracker:packages/contracts /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_runtime_recipe_identity.py tests/test_node_capability.py tests/test_tracker_capability_admission.py PYTHONPATH=packages/node:packages/tracker:packages/contracts /run/media/popov/d/DEV/repos/d-popov.com/AI/.venv/bin/python -m pytest -q tests/test_runtime_recipe_identity.py tests/test_node_capability.py tests/test_tracker_capability_admission.py
# result: 99 passed in 4.76s # result: 99 passed in 4.76s

View File

@@ -1,6 +1,6 @@
# 03 — Define exact Artifact and runtime recipe identity # 03 — Define exact Artifact and runtime recipe identity
Status: ready-for-agent Status: done
## Mandatory fresh-session context ## Mandatory fresh-session context
@@ -23,7 +23,7 @@ As the Tracker, I need exact compatibility identity so that only numerically and
- [x] Separate weight quantization, activation dtype, compute dtype, KV dtype/layout, tokenizer revision, architecture adapter, backend, and runtime version. - [x] Separate weight quantization, activation dtype, compute dtype, KV dtype/layout, tokenizer revision, architecture adapter, backend, and runtime version.
- [x] Bind derivative or split artifacts to an exact source Model Artifact hash and Shard range. - [x] Bind derivative or split artifacts to an exact source Model Artifact hash and Shard range.
- [ ] Produce a stable compatibility fingerprint used by live capability emission/admission and the gRPC handshake. The tracker parses, re-derives, admits, partitions, and certifies supplied exact identities, but the current production doctor/backend path does not yet derive one from authoritative loaded-artifact/runtime state. It must stay dark rather than be claimed complete. - [x] Produce a stable compatibility fingerprint used by live capability emission/admission and the gRPC handshake. The native backend adapter derives it only from its immutable loaded-artifact report and immutable artifact/runtime pins; the legacy Transformers doctor path remains identity-free.
- [x] Fail closed on mismatched artifact, tokenizer, architecture, range, boundary schema, activation recipe, or cache layout. - [x] Fail closed on mismatched artifact, tokenizer, architecture, range, boundary schema, activation recipe, or cache layout.
- [x] Keep unsupported recipes registered-but-dark until a real distributed forward certifies them. - [x] Keep unsupported recipes registered-but-dark until a real distributed forward certifies them.
- [x] Targeted pytest tests pass - [x] Targeted pytest tests pass
@@ -35,7 +35,7 @@ As the Tracker, I need exact compatibility identity so that only numerically and
- [x] Read and verify every dependency evidence README before relying on dependency behavior - [x] Read and verify every dependency evidence README before relying on dependency behavior
- [x] Preserve all pre-existing working-tree changes and stage only files belonging to this story - [x] Preserve all pre-existing working-tree changes and stage only files belonging to this story
- [x] Write .scratch/distributed-gguf-runtime/evidence/DGR-003/README.md with files changed, exact commands and real results, limitations, compatibility notes, and dependent-story handoff - [x] Write .scratch/distributed-gguf-runtime/evidence/DGR-003/README.md with files changed, exact commands and real results, limitations, compatibility notes, and dependent-story handoff
- [ ] Update only this story issue to Status: done after every acceptance criterion and quality gate passes - [x] Update only this story issue to Status: done after every acceptance criterion and quality gate passes
## Dependency handoff ## Dependency handoff

View File

@@ -80,8 +80,8 @@
"Update only this story issue to Status: done after every acceptance criterion and quality gate passes" "Update only this story issue to Status: done after every acceptance criterion and quality gate passes"
], ],
"priority": 4, "priority": 4,
"passes": false, "passes": true,
"notes": "Delayed-review repair: tracker-side exact identity contract is covered by deterministic tests, but live doctor/backend capability emission has no authoritative ShardIdentity construction yet. DGR-003 remains incomplete and exact recipes stay dark; see .scratch/distributed-gguf-runtime/issues/03-define-exact-artifact-and-runtime-recipe-identity.md.", "notes": "DGR-003-emission: native loaded-artifact adapter derives exact identity from immutable GGUF/runtime inputs, doctor emits it only for that adapter, and SessionOpen fails closed before acceptance. Exact identities remain tracker-uncertified and dark until a real distributed forward is certified.",
"dependsOn": [ "dependsOn": [
"DGR-002", "DGR-002",
"DGR-017" "DGR-017"

View File

@@ -36,6 +36,7 @@ from .capability import (
CapabilityReport, CapabilityReport,
build_capability_report, build_capability_report,
) )
from .native_backend import NativeWorkerBackendAdapter
from .recipe_manifest import ( from .recipe_manifest import (
DEFAULT_RECIPE_ID, DEFAULT_RECIPE_ID,
Recipe, Recipe,
@@ -449,11 +450,9 @@ def _validate_recipe(
category: str | None = None category: str | None = None
error: BaseException | None = None error: BaseException | None = None
diagnostics: list[str] = [] diagnostics: list[str] = []
detail: dict = {}
try: try:
backend = load_backend(selection, recipe) backend = load_backend(selection, recipe)
detail = probe_forward(backend) probe_forward(backend)
except DoctorError as exc: except DoctorError as exc:
category, error = exc.category, exc category, error = exc.category, exc
diagnostics = [str(exc), exc.hint] diagnostics = [str(exc), exc.hint]
@@ -464,23 +463,48 @@ def _validate_recipe(
duration_ms = int((time.monotonic() - started) * 1000) duration_ms = int((time.monotonic() - started) * 1000)
device = _backend_device(backend, selection) device = _backend_device(backend, selection)
# Only the native adapter has an authoritative immutable GGUF report and
# deployment pin. The Transformers path deliberately remains dark: a
# model/config fingerprint is not an exact ArtifactIdentity.
identity = backend.identity if isinstance(backend, NativeWorkerBackendAdapter) else None
model_id = selection.model_id if identity is None else identity.artifact.artifact_id
shard_start = selection.shard_start if identity is None else identity.shard_start
shard_end = selection.shard_end if identity is None else identity.shard_end - 1
recipe_id = recipe.id if identity is None else identity.recipe.recipe_id
recipe_version = recipe.version if identity is None else identity.recipe.recipe_version
catalogue_version = (
manifest.catalogue_version if identity is None else identity.recipe.catalogue_version
)
backend_id = recipe.backend_id if identity is None else identity.recipe.backend_id
quantization = (
selection.quantization if identity is None else identity.recipe.weight_quantization
)
runtime = _runtime_versions()
model_config = _model_config(backend)
revision = None
if identity is not None:
revision = identity.artifact.revision
model_config = "sha256:" + identity.artifact.architecture_digest
runtime = {**runtime, "native_runtime": identity.recipe.runtime_version}
report = build_capability_report( report = build_capability_report(
model_id=selection.model_id, model_id=model_id,
shard_start=selection.shard_start, shard_start=shard_start,
shard_end=selection.shard_end, shard_end=shard_end,
recipe_id=recipe.id, recipe_id=recipe_id,
recipe_version=recipe.version, recipe_version=recipe_version,
catalogue_version=manifest.catalogue_version, catalogue_version=catalogue_version,
backend_id=recipe.backend_id, backend_id=backend_id,
device=device, device=device,
device_name=_backend_device_name(device), device_name=_backend_device_name(device),
quantization=selection.quantization, quantization=quantization,
runtime=_runtime_versions(), runtime=runtime,
model_config=_model_config(backend), revision=revision,
model_config=model_config,
status=STATUS_FAILED if category else STATUS_PASSED, status=STATUS_FAILED if category else STATUS_PASSED,
duration_ms=duration_ms, duration_ms=duration_ms,
diagnostics=[d for d in diagnostics if d] or None, diagnostics=[d for d in diagnostics if d] or None,
validated_at=clock(), validated_at=clock(),
identity=identity,
) )
if category: if category:
return RecipeResult( return RecipeResult(

View File

@@ -0,0 +1,185 @@
"""Authoritative identity boundary for a native GGUF Shard backend.
The native loader owns the facts about the mapped artifact. This module turns
that immutable report and separately pinned deployment inputs into the one
``ShardIdentity`` DGR-003 permits a native worker to emit. It is intentionally
not an adapter for the legacy Transformers backend: that backend has no
authoritative immutable GGUF artifact pin and must remain identity-free.
"""
from __future__ import annotations
from dataclasses import dataclass
from .native_protocol import BUNDLE_VERSION, SCHEMA_VERSION, pb
from .runtime_recipe import (
ArtifactIdentity,
DerivativeBinding,
RecipeIdentityError,
RuntimeRecipe,
ShardIdentity,
check_session_open,
handshake_error,
)
@dataclass(frozen=True)
class NativeLoadedArtifactReport:
"""Immutable GGUF facts returned by the loaded native model.
The report is copied from ``llama_model_meshnet_range_report`` plus the
parsed GGUF metadata while the model is live. Byte counts are operational
evidence rather than compatibility axes, but keeping them beside the range
prevents a caller from substituting an unverified range declaration.
"""
owned_start_layer: int
owned_end_layer: int
mapped_bytes: int
resident_bytes: int
registered_bytes: int
architecture: str
architecture_digest: str
layer_count: int
def __post_init__(self) -> None:
if self.owned_start_layer < 0 or self.owned_end_layer <= self.owned_start_layer:
raise RecipeIdentityError("native report has an invalid owned layer range")
if self.layer_count < 1 or self.owned_end_layer > self.layer_count:
raise RecipeIdentityError("native report range is outside GGUF layer metadata")
if min(self.mapped_bytes, self.resident_bytes, self.registered_bytes) < 0:
raise RecipeIdentityError("native report byte counts must be non-negative")
@dataclass(frozen=True)
class ImmutableArtifactPin:
"""Deployment-supplied immutable bytes pin, never inferred from a model name."""
artifact_id: str
revision: str
content_digest: str
derived_from: DerivativeBinding | None = None
@dataclass(frozen=True)
class NativeNumericalRecipe:
"""Immutable numerical inputs selected for this native worker instance."""
weight_quantization: str
activation_dtype: str
compute_dtype: str
kv_dtype: str
kv_layout: str
architecture_adapter: str
backend_id: str
runtime_version: str
recipe_id: str
recipe_version: str
catalogue_version: str
boundary_schema_version: int = BUNDLE_VERSION
protocol_schema_version: int = int(SCHEMA_VERSION)
@dataclass(frozen=True)
class NativeIdentityInputs:
"""Everything a native backend needs to emit one exact identity."""
loaded_artifact: NativeLoadedArtifactReport
artifact_pin: ImmutableArtifactPin
tokenizer_revision: str
numerical_recipe: NativeNumericalRecipe
def shard_identity_from_native_report(inputs: NativeIdentityInputs) -> ShardIdentity:
"""Derive identity only from the native report and immutable pinned inputs."""
report = inputs.loaded_artifact
pin = inputs.artifact_pin
recipe = inputs.numerical_recipe
artifact = ArtifactIdentity(
artifact_id=pin.artifact_id,
revision=pin.revision,
content_digest=pin.content_digest,
architecture=report.architecture,
architecture_digest=report.architecture_digest,
layer_count=report.layer_count,
derived_from=pin.derived_from,
)
return ShardIdentity(
artifact=artifact,
recipe=RuntimeRecipe(
weight_quantization=recipe.weight_quantization,
activation_dtype=recipe.activation_dtype,
compute_dtype=recipe.compute_dtype,
kv_dtype=recipe.kv_dtype,
kv_layout=recipe.kv_layout,
tokenizer_revision=inputs.tokenizer_revision,
architecture_adapter=recipe.architecture_adapter,
backend_id=recipe.backend_id,
runtime_version=recipe.runtime_version,
boundary_schema_version=recipe.boundary_schema_version,
protocol_schema_version=recipe.protocol_schema_version,
recipe_id=recipe.recipe_id,
recipe_version=recipe.recipe_version,
catalogue_version=recipe.catalogue_version,
),
shard_start=report.owned_start_layer,
shard_end=report.owned_end_layer,
)
class NativeSessionRejected(RecipeIdentityError):
"""A native worker refused a ``SessionOpen`` before allocating session state."""
def __init__(self, error: "pb.ShardError") -> None:
super().__init__(f"native SessionOpen rejected: {error.code}")
self.error = error
class NativeWorkerBackendAdapter:
"""Small backend-facing adapter around the native loaded-artifact seam."""
def __init__(self, identity_inputs: NativeIdentityInputs) -> None:
self.identity_inputs = identity_inputs
self.identity = shard_identity_from_native_report(identity_inputs)
@property
def loaded_artifact_report(self) -> NativeLoadedArtifactReport:
return self.identity_inputs.loaded_artifact
def check_session_open(
self,
opened: "pb.SessionOpen",
*,
expected_route_session_id: str | None = None,
expected_route_epoch: int | None = None,
) -> None:
"""Reject incompatible/stale opens at the native worker boundary."""
mismatches = check_session_open(
self.identity,
opened,
expected_route_session_id=expected_route_session_id,
expected_route_epoch=expected_route_epoch,
)
error = handshake_error(mismatches)
if error is not None:
raise NativeSessionRejected(error)
def on_session_open(
self,
opened: "pb.SessionOpen",
*,
expected_route_session_id: str | None = None,
expected_route_epoch: int | None = None,
) -> "pb.SessionAccepted":
"""The native worker's SessionOpen boundary, before session allocation."""
self.check_session_open(
opened,
expected_route_session_id=expected_route_session_id,
expected_route_epoch=expected_route_epoch,
)
return pb.SessionAccepted(
schema_version=SCHEMA_VERSION,
route_session_id=opened.route_session_id,
route_epoch=opened.route_epoch,
fingerprint=self.identity.fingerprint.to_proto(),
)

View File

@@ -0,0 +1,157 @@
"""DGR-003 production-native identity emission boundary tests."""
from __future__ import annotations
import pytest
from meshnet_node.doctor import DoctorSelection, validate_loaded_backend
from meshnet_node.native_backend import (
ImmutableArtifactPin,
NativeIdentityInputs,
NativeLoadedArtifactReport,
NativeNumericalRecipe,
NativeSessionRejected,
NativeWorkerBackendAdapter,
shard_identity_from_native_report,
)
from meshnet_node.native_protocol import SCHEMA_VERSION, pb
from meshnet_node.recipe_manifest import parse_recipe_manifest
from meshnet_tracker.capability import STATE_UNCERTIFIED, evaluate_report
def _digest(letter: str) -> str:
return letter * 64
def _inputs(**changes: object) -> NativeIdentityInputs:
report = NativeLoadedArtifactReport(
owned_start_layer=2,
owned_end_layer=6,
mapped_bytes=1024,
resident_bytes=768,
registered_bytes=640,
architecture="llama",
architecture_digest=_digest("a"),
layer_count=8,
)
recipe = NativeNumericalRecipe(
weight_quantization="Q4_K_M",
activation_dtype="bfloat16",
compute_dtype="float32",
kv_dtype="q8_0",
kv_layout="llama-kv-v1",
architecture_adapter="dense-llama-v1",
backend_id="llama-cpp",
runtime_version="llama.cpp:e920c523",
recipe_id="native",
recipe_version="1",
catalogue_version="2026.07.1",
)
values: dict[str, object] = {
"loaded_artifact": report,
"artifact_pin": ImmutableArtifactPin(
artifact_id="acme/llama.gguf",
revision="0123456789abcdef",
content_digest=_digest("b"),
),
"tokenizer_revision": "abcdef0123456789",
"numerical_recipe": recipe,
}
values.update(changes)
return NativeIdentityInputs(**values) # type: ignore[arg-type]
def _open(adapter: NativeWorkerBackendAdapter, **changes: object) -> pb.SessionOpen:
identity = adapter.identity
fields: dict[str, object] = {
"schema_version": SCHEMA_VERSION,
"route_session_id": "tracker-session",
"route_epoch": 4,
"fingerprint": identity.fingerprint.to_proto(),
"shard_range": pb.ShardRange(
start_layer=identity.shard_start,
end_layer=identity.shard_end,
effective_start_layer=identity.shard_start,
),
}
fields.update(changes)
return pb.SessionOpen(**fields) # type: ignore[arg-type]
def test_native_identity_uses_loaded_report_not_a_caller_range():
identity = shard_identity_from_native_report(_inputs())
assert (identity.shard_start, identity.shard_end) == (2, 6)
assert identity.artifact.architecture == "llama"
assert identity.artifact.layer_count == 8
def test_native_identity_requires_an_immutable_pin_and_gguf_range():
with pytest.raises(Exception, match="moving reference"):
shard_identity_from_native_report(
_inputs(artifact_pin=ImmutableArtifactPin("a", "main", _digest("b")))
)
with pytest.raises(Exception, match="outside GGUF"):
NativeLoadedArtifactReport(0, 9, 1, 1, 1, "llama", _digest("a"), 8)
def test_native_worker_rejects_bad_session_open_before_session_acceptance():
adapter = NativeWorkerBackendAdapter(_inputs())
accepted = adapter.on_session_open(
_open(adapter), expected_route_session_id="tracker-session", expected_route_epoch=4
)
assert accepted.fingerprint.SerializeToString() == adapter.identity.fingerprint.to_proto().SerializeToString()
with pytest.raises(NativeSessionRejected) as rejected:
adapter.on_session_open(
_open(adapter, route_epoch=5),
expected_route_session_id="tracker-session",
expected_route_epoch=4,
)
assert rejected.value.error.code == pb.ERROR_CODE_EPOCH_STALE
def test_doctor_emits_native_identity_but_keeps_legacy_backend_dark():
manifest = parse_recipe_manifest(
{"schema_version": 1, "catalogue_version": "2026.07.1", "recipes": [
{"id": "native", "version": "1", "backend_id": "llama-cpp"}
]}
)
selection = DoctorSelection("acme/llama.gguf", 2, 5)
native = NativeWorkerBackendAdapter(_inputs())
# The probe needs only the normal backend shape; identity is supplied by the adapter.
native.hidden_size = 8
native.is_head = False
native.is_tail = False
native.device = "cpu"
native.forward_bytes = lambda *args, **kwargs: type("Payload", (), {"body": b"x", "shape": [1]})()
result = validate_loaded_backend(native, selection, manifest.recipes[0], manifest)
assert result.report.identity == native.identity
assert result.report.model.revision == native.identity.artifact.revision
assert result.report.model.config_fingerprint == "sha256:" + _digest("a")
assert result.report.backend.quantization == "Q4_K_M"
assert (result.report.shard.start, result.report.shard.end) == (2, 5)
state = evaluate_report(
result.report.to_dict(),
model_matches=lambda value: value == "acme/llama.gguf",
advertised_model="acme/llama.gguf",
shard_start=2,
shard_end=5,
declared_recipe_id="native",
declared_recipe_version="1",
now=result.report.validated_at,
)
assert state.state == STATE_UNCERTIFIED
class Legacy:
hidden_size = 8
is_head = False
is_tail = False
device = "cpu"
@staticmethod
def forward_bytes(*args, **kwargs):
return type("Payload", (), {"body": b"x", "shape": [1]})()
legacy = validate_loaded_backend(Legacy(), selection, manifest.recipes[0], manifest)
assert legacy.report.identity is None