generated from coulomb/repo-seed
WP-0001-T012: data plane SPI and in-process implementation
src/artifactstore/dataplane/: - spi.py: DataPlane Protocol with the five operations ingest_stream, serve_object, verify_object, delete_object, backend_health (ADR-0004). Dataclasses: IngestHints (size_hint, primary_algorithm, backend_id overrides), IngestResult (primary_digest + sha256_digest + size_bytes + StorageReceipt), VerifyResult (verified bool, mismatch reason, actual digests + size). - inproc.py: InProcessDataPlane wraps one StorageBackend. ingest_stream is two-pass against a tempfile (drain stream while dual-hashing into BLAKE3+SHA-256, then forward the tempfile to backend.put under the primary content address); fsync+cleanup on exception. serve_object passes byte ranges through; verify_object re-reads bytes via backend.get, re-digests with the stored algorithm, and reports mismatches. delete and health are thin pass-throughs. tests/unit/test_dataplane_inproc.py (11 cases): - ingest_stream computes correct dual digests, returns receipt, stores bytes at the content-addressed path. - empty-input ingest returns the BLAKE3/SHA-256 of empty. - serve_object round-trips ingested bytes; supports byte_range. - verify_object verifies intact bytes; detects on-disk corruption. - delete_object passes through (True then False). - backend_health passes through. - IngestHints override of primary_algorithm (sha256-as-primary path). - Missing-object serve raises ObjectNotFoundError. - Architectural test (ADR-0004 invariant): no control-plane module (api / registry / retention / audit) imports artifactstore.storage.backends.* or artifactstore.dataplane.inproc directly. Enforced via AST scan of every .py file in those packages. Gates: ruff clean, mypy --strict clean on 44 files, 70 tests pass. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
93
src/artifactstore/dataplane/spi.py
Normal file
93
src/artifactstore/dataplane/spi.py
Normal file
@@ -0,0 +1,93 @@
|
||||
"""Data plane SPI (ADR-0004).
|
||||
|
||||
The control plane (``registry`` / ``api`` / ``retention`` / ``audit``)
|
||||
interacts with bytes exclusively through this surface. v1 ships an
|
||||
in-process implementation backed by a :class:`StorageBackend`; a future
|
||||
Rust daemon will satisfy the same protocol over a Unix socket.
|
||||
|
||||
The SPI uses CBOR-serialisable input and output types so the in-process
|
||||
implementation and a future RPC implementation share representations.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
from collections.abc import AsyncIterator
|
||||
from dataclasses import dataclass
|
||||
from typing import Protocol, runtime_checkable
|
||||
|
||||
from artifactstore.identity import ContentAddress, Digest
|
||||
from artifactstore.storage.spi import BackendStatus, DeletionResult, StorageReceipt
|
||||
|
||||
__all__ = [
|
||||
"DataPlane",
|
||||
"IngestHints",
|
||||
"IngestResult",
|
||||
"VerifyResult",
|
||||
]
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class IngestHints:
|
||||
"""Optional hints attached to an ingest call.
|
||||
|
||||
``size_hint`` lets backends pre-allocate or pick an upload strategy.
|
||||
``primary_algorithm`` overrides the default primary hash (BLAKE3).
|
||||
``backend_id`` lets the data plane select among configured backends
|
||||
(ignored when only one backend is configured).
|
||||
"""
|
||||
|
||||
size_hint: int | None = None
|
||||
primary_algorithm: str | None = None
|
||||
backend_id: str | None = None
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class IngestResult:
|
||||
"""Return value of :meth:`DataPlane.ingest_stream`."""
|
||||
|
||||
primary_digest: Digest
|
||||
sha256_digest: Digest
|
||||
size_bytes: int
|
||||
receipt: StorageReceipt
|
||||
|
||||
|
||||
@dataclass(frozen=True, slots=True)
|
||||
class VerifyResult:
|
||||
"""Return value of :meth:`DataPlane.verify_object`.
|
||||
|
||||
``verified`` is ``True`` when the bytes currently held at
|
||||
``content_address`` re-digest to the expected primary digest. ``mismatch``
|
||||
is populated with a short explanation when verification fails.
|
||||
"""
|
||||
|
||||
content_address: ContentAddress
|
||||
verified: bool
|
||||
actual_primary_digest: Digest
|
||||
actual_sha256_digest: Digest
|
||||
actual_size_bytes: int
|
||||
mismatch: str | None = None
|
||||
|
||||
|
||||
@runtime_checkable
|
||||
class DataPlane(Protocol):
|
||||
"""Byte-handling surface used by the control plane."""
|
||||
|
||||
async def ingest_stream(
|
||||
self,
|
||||
stream: AsyncIterator[bytes],
|
||||
*,
|
||||
hints: IngestHints | None = None,
|
||||
) -> IngestResult: ...
|
||||
|
||||
async def serve_object(
|
||||
self,
|
||||
content_address: ContentAddress,
|
||||
*,
|
||||
byte_range: tuple[int, int] | None = None,
|
||||
) -> AsyncIterator[bytes]: ...
|
||||
|
||||
async def verify_object(self, content_address: ContentAddress) -> VerifyResult: ...
|
||||
|
||||
async def delete_object(self, content_address: ContentAddress) -> DeletionResult: ...
|
||||
|
||||
async def backend_health(self) -> BackendStatus: ...
|
||||
Reference in New Issue
Block a user