Files
rarelens/api/tests/test_cloudrun.py
T
Kemal Yaylali 11fb6b3d73 fix: overhaul the platform skeleton, add a serverless deployment track
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.
2026-09-12 07:21:11 +01:00

98 lines
3.5 KiB
Python

"""The serverless track: the API starts a Cloud Run job instead of publishing to Pub/Sub."""
import uuid
from typing import Any
import pytest
from httpx import AsyncClient
from app.config import settings
from app.services import events
class FakeOperation:
def __init__(self, execution: str) -> None:
self.metadata = type("Meta", (), {"name": execution})()
class FakeJobsClient:
def __init__(self, result: Any = None) -> None:
self.result = result
self.requests: list[dict] = []
def run_job(self, request: dict) -> FakeOperation:
self.requests.append(request)
if isinstance(self.result, Exception):
raise self.result
return self.result
async def new_sample(client: AsyncClient) -> str:
r = await client.post(
"/api/samples",
json={"name": f"s-{uuid.uuid4()}", "vcf_uri": "gs://bucket/x.vcf.gz", "assembly": "GRCh37"},
)
assert r.status_code == 201, r.text
return r.json()["id"]
@pytest.fixture
def cloudrun(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setattr(settings, "pubsub_topic", None)
monkeypatch.setattr(settings, "cloudrun_job", "rarelens-nextflow")
monkeypatch.setattr(settings, "gcp_project", "my-proj")
monkeypatch.setattr(settings, "gcp_region", "europe-west2")
@pytest.mark.usefixtures("db", "cloudrun")
async def test_annotate_executes_the_job_with_pipeline_arguments(
client: AsyncClient, monkeypatch: pytest.MonkeyPatch
) -> None:
jobs = FakeJobsClient(FakeOperation("projects/p/locations/l/executions/rarelens-nextflow-abc12"))
monkeypatch.setattr(events, "_jobs_client", lambda: jobs)
sample_id = await new_sample(client)
r = await client.post(f"/api/samples/{sample_id}/annotate")
assert r.status_code == 202
job = r.json()
assert job["status"] == "running"
assert job["workflow_ref"] == "cloudrun:rarelens-nextflow-abc12"
[request] = jobs.requests
assert request["name"] == "projects/my-proj/locations/europe-west2/jobs/rarelens-nextflow"
[override] = request["overrides"]["container_overrides"]
args = override["args"]
assert args[:4] == ["run", "/pipeline/main.nf", "-profile", "gcp"]
assert args[args.index("--job_id") + 1] == job["id"]
assert args[args.index("--assembly") + 1] == "GRCh37"
assert args[args.index("--vcf") + 1] == "gs://bucket/x.vcf.gz"
@pytest.mark.usefixtures("db", "cloudrun")
async def test_a_failed_execution_call_marks_the_job_failed(
client: AsyncClient, monkeypatch: pytest.MonkeyPatch
) -> None:
monkeypatch.setattr(
events, "_jobs_client", lambda: FakeJobsClient(RuntimeError("403 permission denied"))
)
sample_id = await new_sample(client)
job = (await client.post(f"/api/samples/{sample_id}/annotate")).json()
assert job["status"] == "failed"
assert "403 permission denied" in job["log"]
@pytest.mark.usefixtures("db", "cloudrun")
async def test_cloud_run_job_takes_precedence_over_pubsub(
client: AsyncClient, monkeypatch: pytest.MonkeyPatch
) -> None:
monkeypatch.setattr(settings, "pubsub_topic", "vcf-uploaded")
jobs = FakeJobsClient(FakeOperation("projects/p/locations/l/executions/x-1"))
monkeypatch.setattr(events, "_jobs_client", lambda: jobs)
monkeypatch.setattr(
events, "_publisher", lambda: pytest.fail("Pub/Sub must not be used in the serverless track")
)
sample_id = await new_sample(client)
assert (await client.post(f"/api/samples/{sample_id}/annotate")).json()["status"] == "running"
assert len(jobs.requests) == 1