feat(14-06): route preview/download bytes through durable byte cache

- Add hydrate_and_cache_bytes to services/cloud_cache.py (Plan 06 cache lifecycle)
  - Cache-hit path: pin existing entry, read from MinIO, release pin in finally
  - Cache-miss path: fetch from provider, store in MinIO, create/reactivate entry, pin during response, release pin in finally
  - CacheQuotaExceeded and MinIO failures are non-fatal (bytes returned from provider path)
  - evict_lru_entries run after pin release to stay within user cache limit
- Update preview_cloud_file and download_cloud_file in operations.py to call hydrate_and_cache_bytes
  - Version key computed from CloudItem metadata (no provider call required for key resolution)
  - Shared _make_minio_cache_wrapper helper eliminates duplicate adapter code
  - Falls through to direct provider fetch when no CloudItem row found
- Add _make_minio_cache_wrapper helper to operations.py (DRY, shared by preview and download)
- Add 5 new tests to test_cloud_cache.py: cache-miss fetches provider, cache-hit skips provider, pin released on hit, pin released on miss, user isolation
- Add 3 new security tests to test_cloud_security.py: preview response excludes object_key, download response excludes object_key, foreign-user IDOR via download blocked
This commit is contained in:
curo1305
2026-06-23 16:28:06 +02:00
parent 5a9f3a628e
commit dfc335022f
4 changed files with 715 additions and 8 deletions
+159 -8
View File
@@ -1,5 +1,5 @@
"""
Phase 13 cloud content and mutation endpoints.
Phase 13 cloud content and mutation endpoints (Phase 14 Plan 06: byte cache integration).
Owner-scoped routes for opening, previewing, downloading, renaming, moving,
deleting, creating folders, and uploading cloud files. All routes are
@@ -14,6 +14,16 @@ Security invariants (T-13-14):
- Cross-connection moves are rejected before the adapter is called (D-08).
- Self-destination moves are rejected before the adapter is called (D-09).
- No health probe triggered by folder navigation (D-13).
- cache entries (object_key) are never returned in any response (T-14-02).
Phase 14 Plan 06 byte cache integration:
- preview_cloud_file and download_cloud_file route provider bytes through
hydrate_and_cache_bytes — cache hits avoid a provider round-trip.
- The cache pin lifecycle protects active preview/download entries from LRU
eviction during the response stream.
- cache_limit_bytes is read from UserAnalysisSettings (default 512 MB).
- All byte storage is behind the MinIO private bucket — object keys are
never exposed.
Route family:
GET /connections/{id}/items/{item_id}/open — D-02 authorized access URL
@@ -132,6 +142,44 @@ async def _resolve_and_get_adapter(
return conn, adapter
def _make_minio_cache_wrapper(backend):
"""Return a lightweight MinIO wrapper for use with hydrate_and_cache_bytes.
The wrapper adapts the MinIOBackend instance to the interface expected by
hydrate_and_cache_bytes: async get_object(key), put_object(key, data, content_type),
and delete_object(key). This avoids duplicating the wrapper class at every
call site (Plan 06, DRY principle).
"""
import io as _io
import asyncio as _asyncio
class _MinIOCacheWrapper:
def __init__(self, b):
self._b = b
async def get_object(self, key: str) -> bytes:
return await self._b.get_object(key)
async def put_object(self, key: str, data: bytes, content_type: str = None) -> None:
buf = _io.BytesIO(data)
await _asyncio.to_thread(
self._b._client.put_object,
self._b._bucket,
key,
buf,
length=len(data),
content_type=content_type or "application/octet-stream",
)
async def delete_object(self, key: str) -> None:
try:
await self._b.delete_object(key)
except Exception:
pass
return _MinIOCacheWrapper(backend)
def _mutation_error_json(result: dict, http_status: int) -> JSONResponse:
"""Return a typed JSON error response for a failed mutation.
@@ -304,14 +352,68 @@ async def preview_cloud_file(
if not PreviewSupport.is_supported(content_type):
return _unsupported_preview_response(connection_id, item_id, "unsupported_format")
# Step 4: Fetch bytes via the adapter (supported binary format confirmed above)
# Step 4: Resolve the adapter (requires credential decryption).
try:
conn, adapter = await _resolve_and_get_adapter(session, connection_id, current_user.id)
file_bytes = await adapter.get_object(item_id)
except HTTPException:
# Re-raise 401 (credential failure) and 404 (ownership race) — never mask as
# unsupported_preview. The IDOR guard in Step 1 already passed, but a 401
# from credential decryption should surface as an auth error to the client.
raise
except Exception:
return _unsupported_preview_response(connection_id, item_id, "provider_error")
# Step 5: Fetch bytes via the byte cache (PATTERNS.md lifecycle, Plan 06).
# hydrate_and_cache_bytes: cache hit → read from MinIO without a provider call;
# cache miss → fetch from provider, store in MinIO, pin for duration of response.
try:
from services.cloud_cache import hydrate_and_cache_bytes
from services.cloud_analysis_versioning import compute_version_key
from services.cloud_analysis_settings import (
get_or_create_user_analysis_settings,
DEFAULT_CACHE_LIMIT_BYTES,
)
from storage import get_storage_backend
# Compute the version key from CloudItem metadata (no provider call required).
version_key = compute_version_key(
provider_item_id=item_id,
version=cloud_item.version if cloud_item else None,
etag=cloud_item.etag if cloud_item else None,
size=cloud_item.provider_size if cloud_item else None,
modified_at=str(cloud_item.modified_at) if (cloud_item and cloud_item.modified_at) else None,
content_type=content_type,
) if cloud_item else None
# Resolve user's cache byte limit.
try:
user_settings = await get_or_create_user_analysis_settings(
session, user_id=current_user.id
)
cache_limit = user_settings.cloud_cache_limit_bytes
except Exception:
cache_limit = DEFAULT_CACHE_LIMIT_BYTES
if cloud_item and version_key:
# MinIO client wrapper for cache operations.
_backend = get_storage_backend()
minio_wrapper = _make_minio_cache_wrapper(_backend)
file_bytes, _ = await hydrate_and_cache_bytes(
session,
user_id=current_user.id,
connection_id=connection_id,
cloud_item_id=cloud_item.id,
provider_item_id=item_id,
version_key=version_key,
content_type=content_type,
fetch_fn=lambda: adapter.get_object(item_id),
minio_client=minio_wrapper,
cache_limit_bytes=cache_limit,
)
else:
# No CloudItem row or no version key — fetch directly from provider.
file_bytes = await adapter.get_object(item_id)
except HTTPException:
raise
except Exception:
return _unsupported_preview_response(connection_id, item_id, "provider_error")
@@ -364,10 +466,59 @@ async def download_cloud_file(
filename = cloud_item.name if cloud_item else item_id
content_type = (cloud_item.content_type if cloud_item else None) or "application/octet-stream"
# Fetch bytes via the byte cache (Plan 06, PATTERNS.md cache lifecycle).
# hydrate_and_cache_bytes: cache hit → read from MinIO without a provider call;
# cache miss → fetch from provider, store in MinIO, pin for duration of response.
try:
file_bytes = await adapter.get_object(item_id)
from services.cloud_cache import hydrate_and_cache_bytes
from services.cloud_analysis_versioning import compute_version_key
from services.cloud_analysis_settings import (
get_or_create_user_analysis_settings,
DEFAULT_CACHE_LIMIT_BYTES,
)
from storage import get_storage_backend
version_key = compute_version_key(
provider_item_id=item_id,
version=cloud_item.version if cloud_item else None,
etag=cloud_item.etag if cloud_item else None,
size=cloud_item.provider_size if cloud_item else None,
modified_at=str(cloud_item.modified_at) if (cloud_item and cloud_item.modified_at) else None,
content_type=content_type if content_type != "application/octet-stream" else None,
) if cloud_item else None
try:
user_settings = await get_or_create_user_analysis_settings(
session, user_id=current_user.id
)
cache_limit = user_settings.cloud_cache_limit_bytes
except Exception:
cache_limit = DEFAULT_CACHE_LIMIT_BYTES
if cloud_item and version_key:
_backend = get_storage_backend()
minio_wrapper = _make_minio_cache_wrapper(_backend)
file_bytes, _ = await hydrate_and_cache_bytes(
session,
user_id=current_user.id,
connection_id=connection_id,
cloud_item_id=cloud_item.id,
provider_item_id=item_id,
version_key=version_key,
content_type=content_type if content_type != "application/octet-stream" else None,
fetch_fn=lambda: adapter.get_object(item_id),
minio_client=minio_wrapper,
cache_limit_bytes=cache_limit,
)
else:
# No CloudItem metadata — fetch directly from provider.
file_bytes = await adapter.get_object(item_id)
except HTTPException:
raise
except Exception as exc:
result_dict = adapter._normalize_error(exc)
result_dict = getattr(adapter, "_normalize_error", lambda e: {})(exc)
if result_dict.get("kind") == MUT_KIND_REAUTH:
raise HTTPException(
status_code=status.HTTP_401_UNAUTHORIZED,