Kemal Yaylali
11fb6b3d73
An end-to-end audit found the repo could not build, test or run as shipped. This fixes every finding, then adds a Cloud Run track so the demo costs about £1/month idle instead of ~£150. CI (red on its first run) - api: setuptools could not build the package (flat layout with app/ and alembic/) - web: missing @types/node; `vitest run` exited 1 with no test files - pipeline: the stub run needed a gitignored VCF, and no process had a stub block - ruff pinned, mypy configured, DB tests on real Postgres (pgserver locally, service in CI) ML serving (scores were meaningless) - the registered model now carries its own feature engineering and returns predict_proba, so serving sends raw columns and cannot drift from training - resolve by registry alias (stages are deprecated in MLflow 3) and record the real version; re-scoring upserts instead of failing on the unique constraint - ClinVar labels parsed from VEP's lowercase terms Pipeline - exact ref/alt recovered from a CHROM_POS_REF_ALT VCF ID; loading is idempotent - job status reaches running/failed/succeeded, so the UI stops polling dead jobs - DATABASE_URL travels in the environment or a Nextflow secret, never on a command line - VEP cache and plugins staged as inputs; the gcp profile runs tasks on Google Batch Deployment - the API serves /api (matching the ingress); the web app reads its API URL at runtime - migrations run in an init container under a Postgres advisory lock - terraform: custom VPC shared with Batch, private Cloud SQL, API enablement, Workload Identity bindings, Secret Manager, deletion protection - serverless track, now the default: Cloud Run services scaling to zero, a Cloud Run job for the Nextflow driver, and Neon or Cloud SQL behind one DATABASE_URL secret. GKE and Argo remain, behind -var deploy_kubernetes=true. See docs/cloud.md. Correctness and security - 409 on duplicate sample names, 422 on bad paging, natural chromosome ordering, wider VEP text columns, enum dropped on downgrade, the sample's assembly actually used - vcf_uri restricted to gs:// objects or files under the data root, blocking option injection - CORS restricted to configured origins; `make down` no longer deletes volumes Data - docs/data.md records the peer-reviewed, openly licensed sources (GIAB HG002, ClinVar, gnomAD) with citations and an honest evaluation plan; `make data` fetches a chr22 slice Verified: api 50 tests, ml 18, loader 16, web 12; ruff, mypy, svelte-check, terraform validate and both kustomize overlays clean.
84 lines
2.4 KiB
Python
84 lines
2.4 KiB
Python
"""Test bootstrap.
|
|
|
|
CI provides DATABASE_URL (a Postgres service container). Locally, when it is unset, a throwaway
|
|
Postgres is started with `pgserver` so `pytest` needs no Docker. Set REQUIRE_DB=1 to turn a missing
|
|
database into a failure instead of a skip (CI does this).
|
|
|
|
DATABASE_URL must be settled before anything imports `app`, because `app.config.settings` and the
|
|
engine in `app.db` are created at import time.
|
|
"""
|
|
import os
|
|
import tempfile
|
|
from collections.abc import AsyncIterator, Iterator
|
|
from pathlib import Path
|
|
from typing import TYPE_CHECKING
|
|
|
|
import pytest
|
|
from httpx import ASGITransport, AsyncClient
|
|
|
|
if TYPE_CHECKING:
|
|
from alembic.config import Config
|
|
|
|
API_DIR = Path(__file__).resolve().parents[1]
|
|
_pg_server = None # keeps the pgserver handle alive for the whole session
|
|
|
|
|
|
def _resolve_database_url() -> str | None:
|
|
global _pg_server
|
|
if url := os.environ.get("DATABASE_URL"):
|
|
return url
|
|
try:
|
|
import pgserver
|
|
except ImportError:
|
|
return None
|
|
_pg_server = pgserver.get_server(tempfile.mkdtemp(prefix="rarelens-pg-"), cleanup_mode="delete")
|
|
socket_dir = _pg_server.get_uri().split("host=", 1)[1]
|
|
return f"postgresql+asyncpg://postgres@/postgres?host={socket_dir}"
|
|
|
|
|
|
DATABASE_URL = _resolve_database_url()
|
|
if DATABASE_URL:
|
|
os.environ["DATABASE_URL"] = DATABASE_URL
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def alembic_cfg() -> "Config":
|
|
if not DATABASE_URL:
|
|
if os.environ.get("REQUIRE_DB"):
|
|
pytest.fail("REQUIRE_DB is set but no database is available")
|
|
pytest.skip("no DATABASE_URL and pgserver is not installed")
|
|
from alembic.config import Config
|
|
|
|
cfg = Config(str(API_DIR / "alembic.ini"))
|
|
cfg.set_main_option("script_location", str(API_DIR / "alembic"))
|
|
return cfg
|
|
|
|
|
|
@pytest.fixture(scope="session")
|
|
def migrated_db(alembic_cfg: "Config") -> Iterator[None]:
|
|
from alembic import command
|
|
|
|
command.upgrade(alembic_cfg, "head")
|
|
yield
|
|
|
|
|
|
@pytest.fixture
|
|
async def db(migrated_db: None) -> AsyncIterator[None]:
|
|
from sqlalchemy import text
|
|
|
|
from app.db import engine
|
|
|
|
async with engine.begin() as conn:
|
|
await conn.execute(
|
|
text("TRUNCATE samples, jobs, variants, predictions RESTART IDENTITY CASCADE")
|
|
)
|
|
yield
|
|
|
|
|
|
@pytest.fixture
|
|
async def client() -> AsyncIterator[AsyncClient]:
|
|
from app.main import app
|
|
|
|
async with AsyncClient(transport=ASGITransport(app=app), base_url="http://test") as c:
|
|
yield c
|