Step 13 - completed

This commit is contained in:
2026-03-03 15:14:04 +01:00
parent d0b303e745
commit 480e7ac5bd
8 changed files with 762 additions and 32 deletions

View File

@@ -1,48 +1,30 @@
"""Tests for the storage layer: encryption, BlobStore, and VectorStore."""
"""Tests for the storage layer: encryption, BlobStore, VectorStore, and storage routes."""
from __future__ import annotations
import base64
import hashlib
import os
from unittest.mock import MagicMock, patch
import boto3
import pytest
from botocore.exceptions import ClientError
from moto import mock_aws
from app.storage.encryption import reject_if_tampered, verify_checksum
from app.storage.blob_store import BlobStore
from app.storage.vector_store import VectorStore, _blob_to_vector
from app.schemas import VectorItem, VectorSearchResult
from tests.conftest import auth_header, S3_TEST_BUCKET
# ── Helpers ───────────────────────────────────────────────────────────
_BLOB = b"encrypted-payload-opaque-to-server"
_CHECKSUM = hashlib.sha256(_BLOB).hexdigest()
_BUCKET = "test-bucket"
_BUCKET = S3_TEST_BUCKET
_REGION = "us-east-1"
@pytest.fixture
def s3_bucket():
"""Create a mocked S3 bucket and expose its name."""
with mock_aws():
os.environ.setdefault("AWS_ACCESS_KEY_ID", "testing")
os.environ.setdefault("AWS_SECRET_ACCESS_KEY", "testing")
os.environ.setdefault("AWS_DEFAULT_REGION", _REGION)
client = boto3.client("s3", region_name=_REGION)
client.create_bucket(Bucket=_BUCKET)
with patch("app.storage.blob_store.settings") as mock_settings:
mock_settings.S3_BUCKET = _BUCKET
mock_settings.S3_REGION = _REGION
mock_settings.AWS_ACCESS_KEY_ID = "testing"
mock_settings.AWS_SECRET_ACCESS_KEY = "testing"
yield _BUCKET
def _pinecone_mock():
"""Return a mock Pinecone index with realistic return shapes."""
mock_index = MagicMock()
@@ -383,3 +365,198 @@ class TestVectorStoreQdrant:
await store.delete("u1", ["v1"])
call_kwargs = mock_client.delete.call_args[1]
assert call_kwargs["collection_name"] == "adiuva_vectors"
# ── TestStorageRoutes (integration) ───────────────────────────────────
class TestStorageRoutes:
"""Integration tests for POST/GET/PUT/DELETE /api/v1/storage/records.
Pydantic v2 converts JSON string → bytes via ``str.encode('utf-8')``.
So "hello" in JSON becomes ``b"hello"`` on the server. We use plain
ASCII strings as blob values and compute checksums accordingly.
"""
_BLOB_STR = "encrypted-payload-opaque-to-server"
_BLOB_BYTES = _BLOB_STR.encode()
_BLOB_CHECKSUM = hashlib.sha256(_BLOB_BYTES).hexdigest()
@classmethod
def _create_payload(cls, blob_str: str | None = None) -> dict:
blob_str = blob_str or cls._BLOB_STR
checksum = hashlib.sha256(blob_str.encode()).hexdigest()
return {
"table": "tasks",
"blob": blob_str,
"checksum": checksum,
}
def _create_record(self, client, tier="power", blob_str=None):
payload = self._create_payload(blob_str)
return client.post(
"/api/v1/storage/records",
json=payload,
headers=auth_header(tier),
)
# ── Create ────────────────────────────────────────────────────────
def test_create_record(self, client, s3_bucket) -> None:
resp = self._create_record(client)
assert resp.status_code == 201
data = resp.json()
assert "id" in data
assert "created_at" in data
def test_create_record_bad_checksum(self, client, s3_bucket) -> None:
payload = {
"table": "tasks",
"blob": self._BLOB_STR,
"checksum": "0" * 64,
}
resp = client.post(
"/api/v1/storage/records",
json=payload,
headers=auth_header("power"),
)
assert resp.status_code == 400
def test_create_record_free_tier_blocked(self, client, s3_bucket) -> None:
"""Free tier has cloud_storage_gb=0 → 402."""
resp = self._create_record(client, tier="free")
assert resp.status_code == 402
def test_create_record_pro_tier_allowed(self, client, s3_bucket) -> None:
"""Pro tier has cloud_storage_gb=5 → succeeds for small blob."""
resp = self._create_record(client, tier="pro")
assert resp.status_code == 201
# ── List ──────────────────────────────────────────────────────────
def test_list_records(self, client, s3_bucket) -> None:
self._create_record(client)
self._create_record(client, blob_str="second-blob")
resp = client.get(
"/api/v1/storage/records",
headers=auth_header("power"),
)
assert resp.status_code == 200
data = resp.json()
assert len(data) == 2
# Each entry has metadata, no blob bytes
for item in data:
assert "id" in item
assert "table" in item
assert "checksum" in item
assert "blob" not in item
def test_list_records_filter_by_table(self, client, s3_bucket) -> None:
self._create_record(client)
# Create in a different table
note_blob = "note-blob"
payload = {
"table": "notes",
"blob": note_blob,
"checksum": hashlib.sha256(note_blob.encode()).hexdigest(),
}
client.post(
"/api/v1/storage/records",
json=payload,
headers=auth_header("power"),
)
resp = client.get(
"/api/v1/storage/records?table=notes",
headers=auth_header("power"),
)
assert resp.status_code == 200
data = resp.json()
assert len(data) == 1
assert data[0]["table"] == "notes"
def test_list_records_isolated_per_user(self, client, s3_bucket) -> None:
"""One user's records should not appear in another user's list."""
self._create_record(client, tier="power")
resp = client.get(
"/api/v1/storage/records",
headers=auth_header("team"),
)
assert resp.json() == []
# ── Download ──────────────────────────────────────────────────────
def test_download_record(self, client, s3_bucket) -> None:
create_resp = self._create_record(client)
record_id = create_resp.json()["id"]
resp = client.get(
f"/api/v1/storage/records/{record_id}",
headers=auth_header("power"),
)
assert resp.status_code == 200
assert resp.content == self._BLOB_BYTES
assert resp.headers["X-Checksum"] == self._BLOB_CHECKSUM
def test_download_record_not_found(self, client, s3_bucket) -> None:
resp = client.get(
"/api/v1/storage/records/nonexistent-id",
headers=auth_header("power"),
)
assert resp.status_code == 404
# ── Update ────────────────────────────────────────────────────────
def test_update_record(self, client, s3_bucket) -> None:
create_resp = self._create_record(client)
record_id = create_resp.json()["id"]
new_blob_str = "updated-encrypted-payload"
new_checksum = hashlib.sha256(new_blob_str.encode()).hexdigest()
resp = client.put(
f"/api/v1/storage/records/{record_id}",
json={"blob": new_blob_str, "checksum": new_checksum},
headers=auth_header("power"),
)
assert resp.status_code == 200
assert resp.json() == {"ok": True}
# Verify download returns the updated blob
dl = client.get(
f"/api/v1/storage/records/{record_id}",
headers=auth_header("power"),
)
assert dl.content == new_blob_str.encode()
def test_update_record_bad_checksum(self, client, s3_bucket) -> None:
create_resp = self._create_record(client)
record_id = create_resp.json()["id"]
resp = client.put(
f"/api/v1/storage/records/{record_id}",
json={"blob": "some-data", "checksum": "0" * 64},
headers=auth_header("power"),
)
assert resp.status_code == 400
# ── Delete ────────────────────────────────────────────────────────
def test_delete_record(self, client, s3_bucket) -> None:
create_resp = self._create_record(client)
record_id = create_resp.json()["id"]
resp = client.delete(
f"/api/v1/storage/records/{record_id}",
headers=auth_header("power"),
)
assert resp.status_code == 200
assert resp.json() == {"ok": True}
# Subsequent GET should return 404
dl = client.get(
f"/api/v1/storage/records/{record_id}",
headers=auth_header("power"),
)
assert dl.status_code == 404
def test_delete_record_not_found(self, client, s3_bucket) -> None:
resp = client.delete(
"/api/v1/storage/records/nonexistent",
headers=auth_header("power"),
)
assert resp.status_code == 404