Files
wehub-resource-sync 0d3cb498a3
Deploy local.promptfoo.app / Deploy to Cloudflare Pages (push) Waiting to run
Test and Publish Multi-arch Docker Image / test (push) Waiting to run
Test and Publish Multi-arch Docker Image / build-docker-and-push-digests (map[digest-suffix:linux-amd64 platform:linux/amd64 runner:ubuntu-latest]) (push) Blocked by required conditions
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) Blocked by required conditions
Test and Publish Multi-arch Docker Image / merge-docker-digests (push) Blocked by required conditions
Test and Publish Multi-arch Docker Image / Attest Multi-arch Image (push) Blocked by required conditions
Validate Renovate Config / Validate Renovate Configuration (push) Waiting to run
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
chore: import upstream snapshot with attribution
2026-07-13 13:24:08 +08:00

131 lines
3.9 KiB
TypeScript

import './setup';
import { randomUUID } from 'crypto';
import { expect, it, vi } from 'vitest';
import { evaluate } from '../../src/evaluator';
import { runExtensionHook } from '../../src/evaluatorHelpers';
import Eval from '../../src/models/eval';
import { type TestSuite } from '../../src/types/index';
import { toPrompt } from './helpers';
import { describeEvaluator } from './lifecycle';
describeEvaluator('evaluator session metadata', () => {
it('should use sessionId from vars if not in response', async () => {
const mockApiProvider = {
id: () => 'test-provider',
callApi: vi.fn().mockResolvedValue({
output: 'Test output',
// No sessionId in response
}),
};
const mockExtension = 'file://test-extension.js';
let capturedContext: any;
const mockedRunExtensionHook = vi.mocked(runExtensionHook);
mockedRunExtensionHook.mockImplementation(async (_extensions, hookName, context) => {
if (hookName === 'afterEach') {
capturedContext = context;
}
return context;
});
const testSuite: TestSuite = {
providers: [mockApiProvider],
prompts: [toPrompt('Test prompt')],
tests: [
{
vars: { var1: 'value1', sessionId: 'vars-session-456' },
},
],
extensions: [mockExtension],
};
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
await evaluate(testSuite, evalRecord, {});
expect(capturedContext).toBeDefined();
expect(capturedContext.result.metadata.sessionId).toBe('vars-session-456');
});
it('should prioritize response sessionId over vars sessionId', async () => {
const mockApiProvider = {
id: () => 'test-provider',
callApi: vi.fn().mockResolvedValue({
output: 'Test output',
sessionId: 'response-session-priority',
}),
};
const mockExtension = 'file://test-extension.js';
let capturedContext: any;
const mockedRunExtensionHook = vi.mocked(runExtensionHook);
mockedRunExtensionHook.mockImplementation(async (_extensions, hookName, context) => {
if (hookName === 'afterEach') {
capturedContext = context;
}
return context;
});
const testSuite: TestSuite = {
providers: [mockApiProvider],
prompts: [toPrompt('Test prompt')],
tests: [
{
vars: { var1: 'value1', sessionId: 'vars-session-ignored' },
},
],
extensions: [mockExtension],
};
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
await evaluate(testSuite, evalRecord, {});
expect(capturedContext).toBeDefined();
expect(capturedContext.result.metadata.sessionId).toBe('response-session-priority');
expect(capturedContext.result.metadata.sessionId).not.toBe('vars-session-ignored');
});
it('should handle empty sessionIds array', async () => {
const mockApiProvider = {
id: () => 'test-provider',
callApi: vi.fn().mockResolvedValue({
output: 'Test output',
}),
};
const mockExtension = 'file://test-extension.js';
let capturedContext: any;
const mockedRunExtensionHook = vi.mocked(runExtensionHook);
mockedRunExtensionHook.mockImplementation(async (_extensions, hookName, context) => {
if (hookName === 'afterEach') {
capturedContext = context;
}
return context;
});
const testSuite: TestSuite = {
providers: [mockApiProvider],
prompts: [toPrompt('Test prompt')],
tests: [
{
vars: { var1: 'value1' },
metadata: {
sessionIds: [],
},
},
],
extensions: [mockExtension],
};
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
await evaluate(testSuite, evalRecord, {});
expect(capturedContext).toBeDefined();
expect(capturedContext.result.metadata.sessionIds).toEqual([]);
});
});