Files
wehub-resource-sync 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
chore: import upstream snapshot with attribution
2026-07-13 13:24:08 +08:00

127 lines
3.2 KiB
TypeScript

import { beforeEach, describe, expect, it, vi } from 'vitest';
import { handleModelGradedClosedQa } from '../../src/assertions/modelGradedClosedQa';
import { matchesClosedQa } from '../../src/matchers/llmGrading';
import type { AssertionParams } from '../../src/types/index';
vi.mock('../../src/matchers/llmGrading');
describe('handleModelGradedClosedQa', () => {
beforeEach(() => {
vi.mocked(matchesClosedQa).mockResolvedValue({
pass: true,
score: 1,
reason: 'test reason',
});
});
it('should validate string value', async () => {
const params: AssertionParams = {
assertion: { type: 'model-graded-closedqa' },
baseType: 'model-graded-closedqa',
assertionValueContext: {
prompt: 'test prompt',
vars: {},
test: { vars: {} },
logProbs: undefined,
provider: undefined,
providerResponse: undefined,
},
inverse: false,
output: 'test output',
outputString: 'test output',
prompt: 'test prompt',
providerResponse: {},
renderedValue: {},
test: {
options: {},
vars: {},
},
};
await expect(handleModelGradedClosedQa(params)).rejects.toThrow(
'model-graded-closedqa assertion type must have a string value',
);
});
it('should validate prompt exists', async () => {
const params: AssertionParams = {
assertion: { type: 'model-graded-closedqa' },
baseType: 'model-graded-closedqa',
assertionValueContext: {
prompt: undefined,
vars: {},
test: { vars: {} },
logProbs: undefined,
provider: undefined,
providerResponse: undefined,
},
inverse: false,
output: 'test output',
outputString: 'test output',
prompt: undefined,
providerResponse: {},
renderedValue: 'test value',
test: {
options: {},
vars: {},
},
};
await expect(handleModelGradedClosedQa(params)).rejects.toThrow(
'model-graded-closedqa assertion type must have a prompt',
);
});
it('should call matchesClosedQa with correct parameters', async () => {
const params: AssertionParams = {
assertion: { type: 'model-graded-closedqa' },
baseType: 'model-graded-closedqa',
assertionValueContext: {
prompt: 'test prompt',
vars: { var: 'value' },
test: { vars: { var: 'value' } },
logProbs: undefined,
provider: undefined,
providerResponse: undefined,
},
inverse: false,
output: 'test output',
outputString: 'test output',
prompt: 'test prompt',
providerResponse: {},
renderedValue: 'test value',
test: {
options: {
rubricPrompt: 'test rubric',
},
vars: {
var: 'value',
},
},
};
const result = await handleModelGradedClosedQa(params);
expect(matchesClosedQa).toHaveBeenCalledWith(
'test prompt',
'test value',
'test output',
{
rubricPrompt: 'test rubric',
},
{
var: 'value',
},
undefined,
);
expect(result).toEqual({
assertion: { type: 'model-graded-closedqa' },
pass: true,
score: 1,
reason: 'test reason',
});
});
});