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 +1,174 @@
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
import { matchesLlmRubric } from '../../../src/matchers/llmGrading';
|
||||
import { RbacGrader, RbacPlugin } from '../../../src/redteam/plugins/rbac';
|
||||
import {
|
||||
createMockProvider,
|
||||
createProviderResponse,
|
||||
type MockApiProvider,
|
||||
} from '../../factories/provider';
|
||||
|
||||
import type { AtomicTestCase } from '../../../src/types/index';
|
||||
|
||||
vi.mock('../../../src/util/fetch/index.ts');
|
||||
vi.mock('../../../src/matchers/llmGrading', async (importOriginal) => {
|
||||
return {
|
||||
...(await importOriginal()),
|
||||
matchesLlmRubric: vi.fn(),
|
||||
};
|
||||
});
|
||||
|
||||
describe('RbacPlugin', () => {
|
||||
let mockProvider: MockApiProvider;
|
||||
|
||||
beforeEach(() => {
|
||||
mockProvider = createMockProvider();
|
||||
});
|
||||
|
||||
it('should generate assertions with correct plugin ID', () => {
|
||||
const plugin = new RbacPlugin(mockProvider, 'test purpose', 'test_var');
|
||||
const assertions = (plugin as any).getAssertions('test prompt');
|
||||
|
||||
expect(assertions).toHaveLength(1);
|
||||
expect(assertions[0]).toEqual({
|
||||
type: plugin.id,
|
||||
metric: 'RbacEnforcement',
|
||||
});
|
||||
});
|
||||
|
||||
it('should generate test cases with correct format', async () => {
|
||||
const plugin = new RbacPlugin(mockProvider, 'test purpose', 'test_var');
|
||||
|
||||
const mockResponse = {
|
||||
output: 'Prompt: Test prompt 1\nPrompt: Test prompt 2',
|
||||
};
|
||||
|
||||
vi.mocked(mockProvider.callApi).mockResolvedValue(mockResponse);
|
||||
|
||||
const testCases = await plugin.generateTests(2);
|
||||
|
||||
expect(testCases).toEqual(
|
||||
expect.arrayContaining([
|
||||
expect.objectContaining({
|
||||
vars: {
|
||||
test_var: 'Test prompt 1',
|
||||
},
|
||||
assert: [
|
||||
{
|
||||
type: 'promptfoo:redteam:rbac',
|
||||
metric: 'RbacEnforcement',
|
||||
},
|
||||
],
|
||||
}),
|
||||
expect.objectContaining({
|
||||
vars: {
|
||||
test_var: 'Test prompt 2',
|
||||
},
|
||||
assert: [
|
||||
{
|
||||
type: 'promptfoo:redteam:rbac',
|
||||
metric: 'RbacEnforcement',
|
||||
},
|
||||
],
|
||||
}),
|
||||
]),
|
||||
);
|
||||
});
|
||||
|
||||
it('should handle empty response', async () => {
|
||||
const plugin = new RbacPlugin(mockProvider, 'test purpose', 'test_var');
|
||||
|
||||
const mockResponse = {
|
||||
output: '',
|
||||
};
|
||||
|
||||
vi.mocked(mockProvider.callApi).mockResolvedValue(mockResponse);
|
||||
|
||||
const testCases = await plugin.generateTests(2);
|
||||
expect(testCases).toHaveLength(0);
|
||||
});
|
||||
});
|
||||
|
||||
describe('RbacGrader', () => {
|
||||
const grader = new RbacGrader();
|
||||
|
||||
it('should have correct plugin ID', () => {
|
||||
expect(grader.id).toBe('promptfoo:redteam:rbac');
|
||||
});
|
||||
|
||||
it('should render rubric with variables', () => {
|
||||
const vars = {
|
||||
purpose: 'test purpose',
|
||||
prompt: 'test prompt',
|
||||
entities: ['entity1', 'entity2'],
|
||||
};
|
||||
|
||||
const rendered = grader.renderRubric(vars);
|
||||
|
||||
expect(rendered).toContain('test purpose');
|
||||
expect(rendered).toContain('test prompt');
|
||||
expect(rendered).toContain('entity1');
|
||||
expect(rendered).toContain('entity2');
|
||||
});
|
||||
|
||||
it('should get result with default grader', async () => {
|
||||
// Mock the matchesLlmRubric function to return a passing grade
|
||||
vi.mocked(matchesLlmRubric).mockResolvedValue({
|
||||
pass: true,
|
||||
score: 1,
|
||||
reason: 'test reason',
|
||||
});
|
||||
|
||||
const mockProvider = createMockProvider({
|
||||
id: 'test',
|
||||
response: createProviderResponse({
|
||||
output: JSON.stringify({
|
||||
reason: 'test reason',
|
||||
score: 1,
|
||||
pass: true,
|
||||
}),
|
||||
}),
|
||||
});
|
||||
|
||||
const testCase: AtomicTestCase = {
|
||||
vars: {},
|
||||
assert: [],
|
||||
description: 'test case',
|
||||
metadata: {
|
||||
purpose: 'test purpose',
|
||||
},
|
||||
};
|
||||
|
||||
const result = await grader.getResult(
|
||||
'test prompt',
|
||||
'test output',
|
||||
testCase,
|
||||
mockProvider,
|
||||
undefined,
|
||||
);
|
||||
|
||||
expect(result).toEqual(
|
||||
expect.objectContaining({
|
||||
grade: expect.anything(),
|
||||
rubric: expect.anything(),
|
||||
}),
|
||||
);
|
||||
});
|
||||
|
||||
it('should get suggestions for test case', () => {
|
||||
const testCase: AtomicTestCase = {
|
||||
vars: {},
|
||||
assert: [],
|
||||
description: 'test case',
|
||||
metadata: {
|
||||
purpose: 'test purpose',
|
||||
},
|
||||
};
|
||||
|
||||
const suggestions = grader.getSuggestions({
|
||||
test: testCase,
|
||||
rawPrompt: 'test prompt',
|
||||
});
|
||||
|
||||
expect(Array.isArray(suggestions)).toBe(true);
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user