US07-02: Harden API Authorization and Path Boundaries

This commit is contained in:
2026-08-16 23:06:41 +02:00
parent d143fee4d2
commit b2b996b37e
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

View File

@@ -129,7 +129,10 @@ class ThumbnailService:
raise ThumbnailUnavailable(f"asset {asset_id} has no readable file")
source = str(source)
if source == asset.current_path:
self._validate_path(source) # archive roots lie outside the library
# Render the *resolved* path the check approved: revalidating and then
# reopening the original name would let a symlink swapped in between
# the two steps decide which bytes are served (US07-02).
source = str(self._validate_path(source)) # archive roots lie outside
# Rendering happens outside the DB session (no transaction held during I/O).
try:
@@ -195,20 +198,16 @@ class ThumbnailService:
session.commit()
# ── path safety ──────────────────────────────────────────────────────────
def _validate_path(self, current_path: str) -> None:
path = Path(current_path)
if path_policy.is_excluded(path):
raise PathNotAllowed(f"excluded path: {current_path}")
roots = self._config.library_roots
if not roots:
return
for root in roots:
try:
path_policy.resolve_within(Path(root), path)
return
except path_policy.PathPolicyError:
continue
raise PathNotAllowed(f"path outside configured roots: {current_path}")
def _validate_path(self, current_path: str) -> Path:
"""The resolved path to read, or ``PathNotAllowed``.
The message names no path: a refusal is returned to the browser, and where
the library lives is not the caller's business (US07-02).
"""
try:
return path_policy.resolve_in_roots(self._config.library_roots, current_path)
except path_policy.PathPolicyError as error:
raise PathNotAllowed(str(error)) from None
# ── cache key + rendering ──────────────────────────────────────────────────
@staticmethod