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 +1,117 @@
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
import { handleClassifier } from '../../src/assertions/classifier';
|
||||
import { matchesClassification } from '../../src/matchers/classification';
|
||||
import { createMockProvider, createProviderResponse } from '../factories/provider';
|
||||
|
||||
import type { AssertionParams, AtomicTestCase } from '../../src/types/index';
|
||||
|
||||
vi.mock('../../src/matchers/classification', () => ({
|
||||
matchesClassification: vi.fn(),
|
||||
}));
|
||||
|
||||
const mockedMatchesClassification = vi.mocked(matchesClassification);
|
||||
|
||||
const mockProvider = createMockProvider({
|
||||
id: 'mock',
|
||||
response: createProviderResponse({ output: 'mock' }),
|
||||
});
|
||||
|
||||
function createParams(overrides: Partial<AssertionParams> = {}): AssertionParams {
|
||||
return {
|
||||
assertion: {
|
||||
type: 'classifier',
|
||||
threshold: 0.7,
|
||||
value: 'safe',
|
||||
},
|
||||
baseType: 'classifier',
|
||||
renderedValue: 'safe',
|
||||
output: 'model output',
|
||||
outputString: 'model output',
|
||||
providerResponse: { output: 'model output' },
|
||||
test: {
|
||||
options: {
|
||||
provider: 'classification-provider',
|
||||
},
|
||||
} as AtomicTestCase,
|
||||
inverse: false,
|
||||
assertionValueContext: {
|
||||
vars: {},
|
||||
test: {} as AtomicTestCase,
|
||||
prompt: 'prompt',
|
||||
logProbs: undefined,
|
||||
provider: mockProvider,
|
||||
providerResponse: { output: 'model output' },
|
||||
},
|
||||
...overrides,
|
||||
};
|
||||
}
|
||||
|
||||
describe('handleClassifier', () => {
|
||||
beforeEach(() => {
|
||||
vi.resetAllMocks();
|
||||
mockedMatchesClassification.mockResolvedValue({
|
||||
pass: true,
|
||||
score: 0.9,
|
||||
reason: 'classification passed',
|
||||
});
|
||||
});
|
||||
|
||||
it('passes rendered values, thresholds, and test options to the classifier matcher', async () => {
|
||||
const params = createParams();
|
||||
|
||||
await expect(handleClassifier(params)).resolves.toEqual({
|
||||
assertion: params.assertion,
|
||||
pass: true,
|
||||
score: 0.9,
|
||||
reason: 'classification passed',
|
||||
});
|
||||
|
||||
expect(mockedMatchesClassification).toHaveBeenCalledWith(
|
||||
'safe',
|
||||
'model output',
|
||||
0.7,
|
||||
params.test.options,
|
||||
);
|
||||
});
|
||||
|
||||
it('uses the default threshold and inverts matcher results for inverse assertions', async () => {
|
||||
mockedMatchesClassification.mockResolvedValue({
|
||||
pass: false,
|
||||
score: 0.25,
|
||||
reason: 'classification failed',
|
||||
});
|
||||
const params = createParams({
|
||||
assertion: {
|
||||
type: 'not-classifier',
|
||||
value: undefined,
|
||||
},
|
||||
renderedValue: undefined,
|
||||
inverse: true,
|
||||
});
|
||||
|
||||
await expect(handleClassifier(params)).resolves.toEqual({
|
||||
assertion: params.assertion,
|
||||
pass: true,
|
||||
score: 0.75,
|
||||
reason: 'classification failed',
|
||||
});
|
||||
|
||||
expect(mockedMatchesClassification).toHaveBeenCalledWith(
|
||||
undefined,
|
||||
'model output',
|
||||
1,
|
||||
params.test.options,
|
||||
);
|
||||
});
|
||||
|
||||
it('rejects non-string classifier assertion values', async () => {
|
||||
const params = createParams({
|
||||
renderedValue: { label: 'safe' },
|
||||
});
|
||||
|
||||
await expect(handleClassifier(params)).rejects.toThrow(
|
||||
'"classifier" assertion type must have a string value or be undefined',
|
||||
);
|
||||
expect(mockedMatchesClassification).not.toHaveBeenCalled();
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user