0d3cb498a3
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
103 lines
3.3 KiB
TypeScript
103 lines
3.3 KiB
TypeScript
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
|
import logger from '../../../src/logger';
|
|
import { DoNotAnswerPlugin, fetchDataset } from '../../../src/redteam/plugins/donotanswer';
|
|
import { fetchWithTimeout } from '../../../src/util/fetch/index';
|
|
|
|
vi.mock('fs');
|
|
vi.mock('../../../src/util/fetch/index');
|
|
vi.mock('../../../src/logger');
|
|
|
|
describe('DoNotAnswerPlugin', () => {
|
|
let plugin: DoNotAnswerPlugin;
|
|
|
|
beforeEach(() => {
|
|
vi.resetAllMocks();
|
|
plugin = new DoNotAnswerPlugin({} as any, 'test', 'input');
|
|
});
|
|
|
|
describe('fetchDataset', () => {
|
|
it('should fetch and parse dataset correctly', async () => {
|
|
const mockData = `id,risk_area,types_of_harm,specific_harms,question
|
|
1,test_area,test_harm,specific,test_question`;
|
|
|
|
vi.mocked(fetchWithTimeout).mockResolvedValue({
|
|
ok: true,
|
|
text: () => Promise.resolve(mockData),
|
|
} as Response);
|
|
|
|
const result = await fetchDataset(1);
|
|
expect(result).toHaveLength(1);
|
|
expect(result[0]).toMatchObject({
|
|
vars: {
|
|
risk_area: 'test_area',
|
|
types_of_harm: 'test_harm',
|
|
specific_harms: 'specific',
|
|
question: 'test_question',
|
|
},
|
|
});
|
|
});
|
|
|
|
it('should handle fetch errors gracefully', async () => {
|
|
vi.mocked(fetchWithTimeout).mockRejectedValue(new Error('Fetch failed'));
|
|
const result = await fetchDataset(1);
|
|
expect(result).toEqual([]);
|
|
expect(logger.error).toHaveBeenCalledWith(expect.stringContaining('Error fetching dataset'));
|
|
});
|
|
});
|
|
|
|
describe('DoNotAnswerPlugin class', () => {
|
|
it('should have correct plugin ID', () => {
|
|
expect(plugin.id).toBe('promptfoo:redteam:donotanswer');
|
|
});
|
|
|
|
it('should set canGenerateRemote to false', () => {
|
|
expect(DoNotAnswerPlugin.canGenerateRemote).toBe(false);
|
|
});
|
|
|
|
it('should throw error for getTemplate', async () => {
|
|
await expect(plugin.getTemplate()).rejects.toThrow('Not implemented');
|
|
});
|
|
|
|
it('should return correct assertions', () => {
|
|
const prompt = 'test prompt';
|
|
const assertions = plugin.getAssertions(prompt);
|
|
expect(assertions).toHaveLength(1);
|
|
expect(assertions[0]).toMatchObject({
|
|
metric: 'DoNotAnswer',
|
|
type: 'llm-rubric',
|
|
});
|
|
});
|
|
|
|
it('should generate tests correctly', async () => {
|
|
const mockData = `id,risk_area,types_of_harm,specific_harms,question
|
|
1,test_area,test_harm,specific,test_question`;
|
|
|
|
vi.mocked(fetchWithTimeout).mockResolvedValue({
|
|
ok: true,
|
|
text: () => Promise.resolve(mockData),
|
|
} as Response);
|
|
|
|
const tests = await plugin.generateTests(1);
|
|
expect(tests).toHaveLength(1);
|
|
expect(tests[0]).toMatchObject({
|
|
vars: {
|
|
input: 'test_question',
|
|
},
|
|
metadata: {
|
|
risk_area: 'test_area',
|
|
types_of_harm: 'test_harm',
|
|
specific_harms: 'specific',
|
|
pluginId: 'donotanswer',
|
|
},
|
|
});
|
|
});
|
|
|
|
it('should handle fetch errors gracefully in generateTests', async () => {
|
|
vi.mocked(fetchWithTimeout).mockRejectedValue(new Error('Fetch failed'));
|
|
const tests = await plugin.generateTests(1);
|
|
expect(tests).toEqual([]);
|
|
expect(logger.error).toHaveBeenCalledWith(expect.stringContaining('Error fetching dataset'));
|
|
});
|
|
});
|
|
});
|