US07-02: Harden API Authorization and Path Boundaries (#84)

This commit was merged in pull request #84.
This commit is contained in:
2026-08-16 23:07:36 +02:00
parent d143fee4d2
commit d2e44b5657
21 changed files with 1134 additions and 34 deletions

View File

@@ -25,6 +25,7 @@ from typing import Protocol
from sqlalchemy import func, select
from sqlalchemy.orm import sessionmaker
from photo_pipeline import path_policy
from photo_pipeline.integrations import exiftool
from photo_pipeline.models import AnalysisResult, Asset, SafetyReview
from photo_pipeline.services import hashing
@@ -59,9 +60,16 @@ def _now() -> datetime:
class AnalysisService:
def __init__(self, session_factory: sessionmaker, *, provider: VisionProvider | None = None) -> None:
def __init__(
self,
session_factory: sessionmaker,
*,
provider: VisionProvider | None = None,
library_roots: tuple = (),
) -> None:
self._session_factory = session_factory
self._provider = provider
self._roots = tuple(library_roots)
def _sfw_asset_ids(self, session) -> set[str]:
"""Asset ids whose latest safety decision is ``sfw`` — the ONLY assets that
@@ -136,6 +144,18 @@ class AnalysisService:
if not path:
skipped += 1
continue
# Second gate, at the moment of use: the database says where the file
# was, the filesystem decides what that name means now. A link swapped
# under an asset after the scan would otherwise send bytes from outside
# the library — the one place that leaves this machine (US07-02).
try:
path = str(path_policy.resolve_in_roots(self._roots, path))
except path_policy.PathPolicyError as error:
self._store(
asset_id, status="error", result=None, error=str(error), tokens=0, raw=""
)
errors += 1
continue
try:
result = provider.analyze(path, album_hint=_album_hint(path))
except Exception as error: # provider/validation failure is per-asset