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.
55 lines
1.9 KiB
TypeScript
55 lines
1.9 KiB
TypeScript
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
|
|
import { poll } from './poll';
|
|
|
|
beforeEach(() => vi.useFakeTimers());
|
|
afterEach(() => vi.useRealTimers());
|
|
|
|
describe('poll', () => {
|
|
it('fetches until done, then stops', async () => {
|
|
const values = ['queued', 'running', 'succeeded', 'never'];
|
|
const fetch = vi.fn(async () => values.shift()!);
|
|
const seen: string[] = [];
|
|
poll(fetch, { intervalMs: 1000, done: (v) => v === 'succeeded', onValue: (v) => seen.push(v), onError: () => {} });
|
|
|
|
await vi.advanceTimersByTimeAsync(5000);
|
|
expect(seen).toEqual(['queued', 'running', 'succeeded']);
|
|
expect(fetch).toHaveBeenCalledTimes(3);
|
|
});
|
|
|
|
it('never has two requests in flight when the API is slower than the interval', async () => {
|
|
let inFlight = 0;
|
|
let maxInFlight = 0;
|
|
const fetch = async () => {
|
|
inFlight++;
|
|
maxInFlight = Math.max(maxInFlight, inFlight);
|
|
await new Promise((r) => setTimeout(r, 2500));
|
|
inFlight--;
|
|
return 'running';
|
|
};
|
|
poll(fetch, { intervalMs: 1000, done: () => false, onValue: () => {}, onError: () => {} });
|
|
|
|
await vi.advanceTimersByTimeAsync(10_000);
|
|
expect(maxInFlight).toBe(1);
|
|
});
|
|
|
|
it('reports an error once and stops', async () => {
|
|
const fetch = vi.fn(async () => { throw new Error('502'); });
|
|
const onError = vi.fn();
|
|
poll(fetch, { intervalMs: 1000, done: () => false, onValue: () => {}, onError });
|
|
|
|
await vi.advanceTimersByTimeAsync(5000);
|
|
expect(onError).toHaveBeenCalledOnce();
|
|
expect(fetch).toHaveBeenCalledOnce();
|
|
});
|
|
|
|
it('stop() cancels future fetches, e.g. when the page unmounts', async () => {
|
|
const fetch = vi.fn(async () => 'running');
|
|
const stop = poll(fetch, { intervalMs: 1000, done: () => false, onValue: () => {}, onError: () => {} });
|
|
|
|
await vi.advanceTimersByTimeAsync(1500);
|
|
stop();
|
|
await vi.advanceTimersByTimeAsync(10_000);
|
|
expect(fetch).toHaveBeenCalledTimes(1);
|
|
});
|
|
});
|