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 +1,128 @@
|
||||
import { beforeEach, describe, expect, it, vi } from 'vitest';
|
||||
import { handleAgentRubric } from '../../src/assertions/agentRubric';
|
||||
import { matchesAgentRubric } from '../../src/matchers/agent';
|
||||
|
||||
import type { AssertionParams, GradingResult } from '../../src/types/index';
|
||||
|
||||
vi.mock('../../src/matchers/agent');
|
||||
|
||||
describe('handleAgentRubric', () => {
|
||||
const params: AssertionParams = {
|
||||
assertion: {
|
||||
type: 'agent-rubric',
|
||||
value: 'Verify the claimed change',
|
||||
},
|
||||
baseType: 'agent-rubric',
|
||||
assertionValueContext: {
|
||||
prompt: 'test prompt',
|
||||
vars: {},
|
||||
test: { vars: {} },
|
||||
logProbs: undefined,
|
||||
provider: undefined,
|
||||
providerResponse: undefined,
|
||||
},
|
||||
inverse: false,
|
||||
output: 'Implemented',
|
||||
outputString: 'Implemented',
|
||||
renderedValue: 'Verify the claimed change',
|
||||
test: {
|
||||
vars: {},
|
||||
options: {},
|
||||
},
|
||||
providerResponse: {
|
||||
output: 'Implemented',
|
||||
},
|
||||
};
|
||||
|
||||
const mockMatchesAgentRubric = vi.mocked(matchesAgentRubric);
|
||||
|
||||
beforeEach(() => {
|
||||
vi.resetAllMocks();
|
||||
});
|
||||
|
||||
it('passes rubric inputs to the agent matcher', async () => {
|
||||
const result: GradingResult = {
|
||||
pass: true,
|
||||
score: 1,
|
||||
reason: 'verified',
|
||||
};
|
||||
mockMatchesAgentRubric.mockResolvedValue(result);
|
||||
|
||||
await expect(handleAgentRubric(params)).resolves.toEqual(result);
|
||||
expect(mockMatchesAgentRubric).toHaveBeenCalledWith(
|
||||
'Verify the claimed change',
|
||||
'Implemented',
|
||||
{},
|
||||
{},
|
||||
params.assertion,
|
||||
undefined,
|
||||
);
|
||||
});
|
||||
|
||||
it('uses a structured rubric prompt when no assertion value is rendered', async () => {
|
||||
const rubricPrompt = [{ role: 'system', content: 'Inspect the artifact' }];
|
||||
const structuredParams: AssertionParams = {
|
||||
...params,
|
||||
assertion: {
|
||||
...params.assertion,
|
||||
value: undefined,
|
||||
},
|
||||
renderedValue: undefined,
|
||||
test: {
|
||||
vars: {},
|
||||
options: { rubricPrompt },
|
||||
},
|
||||
};
|
||||
mockMatchesAgentRubric.mockResolvedValue({
|
||||
pass: true,
|
||||
score: 1,
|
||||
reason: 'verified',
|
||||
});
|
||||
|
||||
await expect(handleAgentRubric(structuredParams)).resolves.toEqual({
|
||||
pass: true,
|
||||
score: 1,
|
||||
reason: 'verified',
|
||||
});
|
||||
|
||||
const serializedPrompt = JSON.stringify(rubricPrompt);
|
||||
expect(structuredParams.test.options?.rubricPrompt).toBe(serializedPrompt);
|
||||
expect(structuredParams.assertion.value).toBe(serializedPrompt);
|
||||
expect(mockMatchesAgentRubric).toHaveBeenCalledWith(
|
||||
'',
|
||||
'Implemented',
|
||||
{ rubricPrompt: serializedPrompt },
|
||||
{},
|
||||
structuredParams.assertion,
|
||||
undefined,
|
||||
);
|
||||
});
|
||||
|
||||
it('inverts successful verdicts and scores', async () => {
|
||||
mockMatchesAgentRubric.mockResolvedValue({
|
||||
pass: true,
|
||||
score: 0.8,
|
||||
reason: 'verified',
|
||||
});
|
||||
|
||||
const result = await handleAgentRubric({ ...params, inverse: true });
|
||||
|
||||
expect(result.pass).toBe(false);
|
||||
expect(result.score).toBeCloseTo(0.2);
|
||||
});
|
||||
|
||||
it('does not invert grader transport or parse failures', async () => {
|
||||
const failure: GradingResult = {
|
||||
pass: false,
|
||||
score: 0,
|
||||
reason: 'No output',
|
||||
metadata: { graderError: true },
|
||||
};
|
||||
mockMatchesAgentRubric.mockResolvedValue(failure);
|
||||
|
||||
await expect(handleAgentRubric({ ...params, inverse: true })).resolves.toEqual({
|
||||
...failure,
|
||||
assertion: params.assertion,
|
||||
});
|
||||
});
|
||||
});
|
||||
Reference in New Issue
Block a user