chore: import upstream snapshot with attribution
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
CI / Shell Format Check (push) Has been cancelled
CI / Check Ruby (3.4) (push) Has been cancelled
CI / CI Config (push) Has been cancelled
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Has been cancelled
CI / Build on Node ${{ matrix.node }} (push) Has been cancelled
CI / Style Check (push) Has been cancelled
CI / Generate Assets (push) Has been cancelled
CI / Check Python (3.14) (push) Has been cancelled
CI / Check Python (3.9) (push) Has been cancelled
CI / Build Docs (push) Has been cancelled
CI / Code Scan Action (push) Has been cancelled
CI / Site tests (push) Has been cancelled
CI / webui tests (push) Has been cancelled
CI / Run Integration Tests (push) Has been cancelled
CI / Run Smoke Tests (push) Has been cancelled
CI / Go Tests (push) Has been cancelled
CI / Share Test (push) Has been cancelled
CI / Redteam (Production API) (push) Has been cancelled
CI / Redteam (Staging API) (push) Has been cancelled
CI / GitHub Actions Lint (push) Has been cancelled
CI / Check Ruby (3.0) (push) Has been cancelled
release-please / release-please (push) Has been cancelled
release-please / build (push) Has been cancelled
release-please / publish-npm (push) Has been cancelled
release-please / publish-npm-backfill (push) Has been cancelled
release-please / docker (push) Has been cancelled
release-please / publish-code-scan-action (push) Has been cancelled
release-please / attest-code-scan-action (push) Has been cancelled
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Has been cancelled
Test and Publish Multi-arch Docker Image / test (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-arm64 platform:linux/arm64 runner:ubuntu-24.04-arm]) (push) Has been cancelled
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Has been cancelled
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Has been cancelled
Validate Renovate Config / Validate Renovate Configuration (push) Has been cancelled
This commit is contained in:
@@ -0,0 +1,129 @@
|
||||
import { afterEach, beforeAll, beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
import { getDb } from '../../src/database/index';
|
||||
import { updateSignalFile } from '../../src/database/signal';
|
||||
import { datasetsTable, evalsTable, promptsTable, tagsTable } from '../../src/database/tables';
|
||||
import { runDbMigrations } from '../../src/migrate';
|
||||
import {
|
||||
clearStandaloneEvalCache,
|
||||
getStandaloneEvals,
|
||||
writeResultsToDatabase,
|
||||
} from '../../src/util/database';
|
||||
import {
|
||||
getCachedStandaloneEvals,
|
||||
getStandaloneEvalCacheKey,
|
||||
} from '../../src/util/standaloneEvalCache';
|
||||
import { createEvaluateSummaryV2 } from '../factories/eval';
|
||||
|
||||
vi.mock('../../src/database/signal', async () => {
|
||||
const actual = await vi.importActual('../../src/database/signal');
|
||||
return {
|
||||
...actual,
|
||||
updateSignalFile: vi.fn(),
|
||||
};
|
||||
});
|
||||
|
||||
function expectWrittenHistoryCached() {
|
||||
expect(getCachedStandaloneEvals(getStandaloneEvalCacheKey())).toBeDefined();
|
||||
}
|
||||
|
||||
describe('writeResultsToDatabase', () => {
|
||||
beforeAll(async () => {
|
||||
await runDbMigrations();
|
||||
});
|
||||
|
||||
afterEach(() => {
|
||||
vi.resetAllMocks();
|
||||
});
|
||||
|
||||
beforeEach(async () => {
|
||||
const db = await getDb();
|
||||
await db.run('DROP TRIGGER IF EXISTS fail_evals_to_tags_insert');
|
||||
await db.run('DELETE FROM evals_to_datasets');
|
||||
await db.run('DELETE FROM evals_to_prompts');
|
||||
await db.run('DELETE FROM evals_to_tags');
|
||||
await db.run('DELETE FROM evals');
|
||||
await db.run('DELETE FROM datasets');
|
||||
await db.run('DELETE FROM prompts');
|
||||
await db.run('DELETE FROM tags');
|
||||
clearStandaloneEvalCache();
|
||||
});
|
||||
|
||||
it('rolls back related rows when a dependent insert fails', async () => {
|
||||
const db = await getDb();
|
||||
await db.run(`
|
||||
CREATE TRIGGER fail_evals_to_tags_insert
|
||||
BEFORE INSERT ON evals_to_tags
|
||||
BEGIN
|
||||
SELECT RAISE(ABORT, 'forced tag failure');
|
||||
END;
|
||||
`);
|
||||
|
||||
await expect(
|
||||
writeResultsToDatabase(
|
||||
createEvaluateSummaryV2(),
|
||||
{
|
||||
tags: { suite: 'regression' },
|
||||
tests: [],
|
||||
},
|
||||
new Date('2024-01-01T00:00:00.000Z'),
|
||||
),
|
||||
).rejects.toThrow();
|
||||
|
||||
await expect(db.select().from(evalsTable).all()).resolves.toHaveLength(0);
|
||||
await expect(db.select().from(promptsTable).all()).resolves.toHaveLength(0);
|
||||
await expect(db.select().from(datasetsTable).all()).resolves.toHaveLength(0);
|
||||
await expect(db.select().from(tagsTable).all()).resolves.toHaveLength(0);
|
||||
});
|
||||
|
||||
it('keeps cached history when a later write rolls back', async () => {
|
||||
const firstEvalId = await writeResultsToDatabase(createEvaluateSummaryV2(), {}, new Date());
|
||||
const beforeIds = (await getStandaloneEvals()).map((row) => row.evalId);
|
||||
expect(beforeIds).toContain(firstEvalId);
|
||||
expectWrittenHistoryCached();
|
||||
const secondDate = new Date(Date.now() + 1000);
|
||||
|
||||
const db = await getDb();
|
||||
await db.run(`
|
||||
CREATE TRIGGER fail_evals_to_tags_insert
|
||||
BEFORE INSERT ON evals_to_tags
|
||||
BEGIN
|
||||
SELECT RAISE(ABORT, 'forced tag failure');
|
||||
END;
|
||||
`);
|
||||
|
||||
await expect(
|
||||
writeResultsToDatabase(
|
||||
createEvaluateSummaryV2(),
|
||||
{
|
||||
tags: { suite: 'regression' },
|
||||
tests: [],
|
||||
},
|
||||
secondDate,
|
||||
),
|
||||
).rejects.toThrow();
|
||||
|
||||
const cachedIds = getCachedStandaloneEvals(getStandaloneEvalCacheKey())?.map(
|
||||
(row) => row.evalId,
|
||||
);
|
||||
expect(cachedIds).toContain(firstEvalId);
|
||||
});
|
||||
|
||||
it('includes newly persisted evals after history has been cached', async () => {
|
||||
const firstDate = new Date();
|
||||
const firstEvalId = await writeResultsToDatabase(createEvaluateSummaryV2(), {}, firstDate);
|
||||
const beforeIds = (await getStandaloneEvals()).map((row) => row.evalId);
|
||||
expect(beforeIds).toContain(firstEvalId);
|
||||
expectWrittenHistoryCached();
|
||||
|
||||
const secondEvalId = await writeResultsToDatabase(
|
||||
createEvaluateSummaryV2(),
|
||||
{},
|
||||
new Date(firstDate.getTime() + 1000),
|
||||
);
|
||||
|
||||
const afterIds = (await getStandaloneEvals()).map((row) => row.evalId);
|
||||
expect(afterIds).toContain(firstEvalId);
|
||||
expect(afterIds).toContain(secondEvalId);
|
||||
expect(updateSignalFile).toHaveBeenCalledWith(secondEvalId);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user