timmy
860c84f0fe
Quality gates / quality (pull_request) Failing after 9m42s
Promote the ingest script into an auditable corpus pipeline. Each sample now records consent (version + timestamp), source kind and raw-input digest, both hashes, the derivation pipeline, review status, split, and lifecycle state, with the caller's path never written down. Withdrawal is a new `--revoke <contribution-id> --reason` operation: it deletes the derived image and any raw pre-derivation copy, then appends a tombstone that addresses each removed artifact by contribution id and digest while dropping labels, subject key, and paths. History is append-only, so the original sample record survives the withdrawal it documents. Illegal moves are refused instead of silently applied: revoked -> active, revoking an unknown or already-revoked contribution, an unknown state, a duplicate contribution id, and a second label set for the same derived image. The duplicate guard runs before any byte is written, so a refused ingest cannot strand an image in the active dataset. Tests written first and watched fail (tests/corpus-manifest.test.py): provenance, tombstone + byte removal, active-record filtering, and the transition guards. The transition helper itself passed on first write and is reported as a hold-out check rather than a RED cycle. Wired into the quality workflow and check:syntax; contract documented in docs/CORPUS-MANIFEST.md. No browser surface changed, so record_release_demo.mjs is untouched and claims nothing new: the nearest honest visible effect is the withdrawn-receipt tombstone already recorded for #24.
57 lines
2.6 KiB
JavaScript
57 lines
2.6 KiB
JavaScript
import test from 'node:test';
|
|
import assert from 'node:assert/strict';
|
|
import { mkdtemp, readFile, rm, stat } from 'node:fs/promises';
|
|
import { spawnSync } from 'node:child_process';
|
|
import { tmpdir } from 'node:os';
|
|
import { join } from 'node:path';
|
|
|
|
test('training ingest strips metadata, derives a pseudonymous split, and writes reviewable labels', async () => {
|
|
const out = await mkdtemp(join(tmpdir(), 'timmy-ingest-'));
|
|
try {
|
|
const run = spawnSync('python3', [
|
|
'scripts/ingest_training_photo.py',
|
|
'--input', 'tests/fixtures/synthetic-type4.jpg',
|
|
'--output-dir', out,
|
|
'--subject-id', 'subject-123',
|
|
'--consent-version', 'research-v1',
|
|
'--contribution-id', '6f1d0c9e-2c4a-4f3b-9d1e-8a7b6c5d4e3f',
|
|
'--bristol-type', '4',
|
|
'--color', 'brown',
|
|
'--quality', 'good',
|
|
'--reviewer', 'user-confirmed',
|
|
], { encoding: 'utf8', env: { ...process.env, TIMMY_DATASET_SALT: 'test-only-salt' } });
|
|
assert.equal(run.status, 0, run.stderr);
|
|
const record = JSON.parse(run.stdout);
|
|
assert.match(record.imageId, /^[a-f0-9]{64}$/);
|
|
assert.ok(['train', 'validation', 'test'].includes(record.split));
|
|
assert.equal(record.subjectKey.length, 16);
|
|
assert.equal(record.consentVersion, 'research-v1');
|
|
assert.deepEqual(record.labels, { bristolType: 4, color: 'brown', quality: 'good' });
|
|
assert.equal(record.review.status, 'user-confirmed');
|
|
assert.equal('inputPath' in record, false);
|
|
const derived = join(out, record.relativePath);
|
|
assert.ok((await stat(derived)).size > 100);
|
|
const manifest = (await readFile(join(out, 'manifest.jsonl'), 'utf8')).trim().split('\n').map(JSON.parse);
|
|
assert.deepEqual(manifest, [record]);
|
|
const exif = spawnSync('python3', ['-c', "from PIL import Image;import sys;print(len(Image.open(sys.argv[1]).getexif()))", derived], { encoding: 'utf8' });
|
|
assert.equal(exif.stdout.trim(), '0');
|
|
} finally {
|
|
await rm(out, { recursive: true, force: true });
|
|
}
|
|
});
|
|
|
|
test('training ingest rejects records without explicit consent or human review', () => {
|
|
const run = spawnSync('python3', [
|
|
'scripts/ingest_training_photo.py',
|
|
'--input', 'tests/fixtures/synthetic-type4.jpg',
|
|
'--output-dir', '/tmp/should-not-exist-timmy',
|
|
'--subject-id', 'subject-123',
|
|
'--contribution-id', '6f1d0c9e-2c4a-4f3b-9d1e-8a7b6c5d4e3f',
|
|
'--bristol-type', '4',
|
|
'--color', 'brown',
|
|
'--quality', 'good',
|
|
], { encoding: 'utf8', env: { ...process.env, TIMMY_DATASET_SALT: 'test-only-salt' } });
|
|
assert.notEqual(run.status, 0);
|
|
assert.match(run.stderr, /consent/i);
|
|
});
|