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
65 lines
1.9 KiB
TypeScript
65 lines
1.9 KiB
TypeScript
import { describe, expect, it, vi } from 'vitest';
|
|
import { runCompareAssertion } from '../../src/assertions/index';
|
|
import { createMockProvider, createProviderResponse } from '../factories/provider';
|
|
|
|
import type {
|
|
ApiProvider,
|
|
Assertion,
|
|
AtomicTestCase,
|
|
CallApiContextParams,
|
|
} from '../../src/types/index';
|
|
|
|
describe('select-best context propagation', () => {
|
|
it('should pass context with originalProvider to grading provider', async () => {
|
|
let capturedContext: CallApiContextParams | undefined;
|
|
|
|
// Create a grading provider that captures the context
|
|
const gradingProvider = createMockProvider({
|
|
id: 'test-grading-provider',
|
|
callApi: vi.fn<ApiProvider['callApi']>().mockImplementation(async (_prompt, context) => {
|
|
capturedContext = context;
|
|
return {
|
|
output: '0', // Select first option
|
|
tokenUsage: {},
|
|
};
|
|
}),
|
|
});
|
|
|
|
const originalProvider = createMockProvider({
|
|
id: 'original-provider',
|
|
response: createProviderResponse({ output: '', tokenUsage: {} }),
|
|
});
|
|
|
|
const test: AtomicTestCase = {
|
|
vars: { foo: 'bar' },
|
|
options: {
|
|
provider: gradingProvider,
|
|
},
|
|
};
|
|
|
|
const assertion: Assertion = {
|
|
type: 'select-best',
|
|
value: 'Pick the best output',
|
|
};
|
|
|
|
const outputs = ['Output 1', 'Output 2'];
|
|
|
|
const contextToPass: CallApiContextParams = {
|
|
originalProvider,
|
|
prompt: { raw: 'test prompt', label: 'test' },
|
|
vars: { foo: 'bar' },
|
|
};
|
|
|
|
// Call runCompareAssertion with context
|
|
await runCompareAssertion(test, assertion, outputs, contextToPass);
|
|
|
|
// Verify the grading provider was called
|
|
expect(gradingProvider.callApi).toHaveBeenCalled();
|
|
|
|
// Verify it received the context with originalProvider
|
|
expect(capturedContext).toBeDefined();
|
|
expect(capturedContext?.originalProvider).toBeDefined();
|
|
expect(capturedContext?.originalProvider?.id()).toBe('original-provider');
|
|
});
|
|
});
|