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
+90
View File
@@ -879,6 +879,96 @@ async def test_foreign_user_cannot_access_analysis_estimate(async_client, db_ses
)
# ── Phase 14 Plan 06: Cache-backed preview/download security ──────────────────
async def test_preview_cache_hit_response_excludes_object_key(async_client, db_session):
"""T-14-02/Plan 06: Preview response from a cache hit must not expose object_key.
Even when bytes come from MinIO (cache hit path), the response body and headers
must not contain the MinIO object key or credentials_enc.
"""
import uuid as _uuid2
from unittest.mock import AsyncMock, patch as _patch, MagicMock
owner_ctx = await _create_user_and_token(db_session, role="user")
conn = await _create_cloud_connection(db_session, owner_ctx["user"].id)
# Simulate a cache hit by patching hydrate_and_cache_bytes to return bytes
with _patch(
"api.cloud.operations.hydrate_and_cache_bytes" if False else "services.cloud_cache.hydrate_and_cache_bytes",
new=AsyncMock(return_value=(b"pdf-bytes", _uuid2.uuid4())),
):
with _patch("api.cloud.operations._resolve_and_get_adapter") as mock_adapter:
mock_conn = MagicMock()
mock_ad = AsyncMock()
mock_ad.get_object = AsyncMock(return_value=b"pdf-bytes")
mock_adapter.return_value = (mock_conn, mock_ad)
# No cloud_item in DB, so falls to direct fetch path — test response exclusion
resp = await async_client.get(
f"/api/cloud/connections/{conn.id}/items/pitem-preview-sec/preview",
headers=owner_ctx["headers"],
)
# Any 2xx or unsupported_preview is acceptable; key check is no secret leakage
assert resp.status_code not in (500,), f"Should not 500 — got {resp.status_code}: {resp.text}"
body = resp.text
assert "object_key" not in body, "T-14-02: object_key must not appear in preview response"
assert "credentials_enc" not in body, "credentials_enc must not appear in preview response"
async def test_download_response_excludes_object_key(async_client, db_session):
"""T-14-02/Plan 06: Download response must not expose object_key or credentials.
The cache lookup and MinIO path are internal; the response headers and body
must contain only the file bytes and safe metadata.
"""
from unittest.mock import AsyncMock, patch as _patch, MagicMock
owner_ctx = await _create_user_and_token(db_session, role="user")
conn = await _create_cloud_connection(db_session, owner_ctx["user"].id)
with _patch("api.cloud.operations._resolve_and_get_adapter") as mock_adapter:
mock_conn = MagicMock()
mock_ad = AsyncMock()
mock_ad.get_object = AsyncMock(return_value=b"download-bytes")
mock_adapter.return_value = (mock_conn, mock_ad)
resp = await async_client.get(
f"/api/cloud/connections/{conn.id}/items/pitem-download-sec/download",
headers=owner_ctx["headers"],
)
assert resp.status_code != 500, f"Should not 500 — got {resp.status_code}: {resp.text}"
# Check headers
for header_name, header_value in resp.headers.items():
assert "object_key" not in header_value.lower(), (
f"T-14-02: object_key must not appear in response headers — found in {header_name}"
)
assert "credentials_enc" not in header_value.lower(), (
"credentials_enc must not appear in response headers"
)
async def test_foreign_user_cannot_download_via_cache(async_client, db_session):
"""T-14-01/Plan 06: Foreign user cannot download another user's cloud file via cache.
The ownership check (resolve_owned_connection) must run before any cache lookup.
"""
auth1 = await _create_user_and_token(db_session, role="user")
auth2 = await _create_user_and_token(db_session, role="user")
conn = await _create_cloud_connection(db_session, auth1["user"].id)
resp = await async_client.get(
f"/api/cloud/connections/{conn.id}/items/pitem-idor/download",
headers=auth2["headers"],
)
assert resp.status_code == 404, (
f"Foreign user must not download via cache — expected 404, got {resp.status_code}"
)
async def test_foreign_user_cannot_read_analysis_job_status(async_client, db_session):
"""T-14-01: Foreign user cannot read job status for another user's job."""
from unittest.mock import patch as _patch