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
CI / Shell Format Check (push) Waiting to run
CI / Check Ruby (3.4) (push) Waiting to run
CI / CI Config (push) Waiting to run
CI / Test on Node ${{ matrix.node }} and ${{ matrix.os }}${{ matrix.shard && format(' (shard {0}/3)', matrix.shard) || '' }} (push) Blocked by required conditions
CI / Build on Node ${{ matrix.node }} (push) Blocked by required conditions
CI / Style Check (push) Waiting to run
CI / Generate Assets (push) Waiting to run
CI / Check Python (3.14) (push) Waiting to run
CI / Check Python (3.9) (push) Waiting to run
CI / Build Docs (push) Waiting to run
CI / Code Scan Action (push) Waiting to run
CI / Site tests (push) Waiting to run
CI / webui tests (push) Waiting to run
CI / Run Integration Tests (push) Waiting to run
CI / Run Smoke Tests (push) Waiting to run
CI / Go Tests (push) Waiting to run
CI / Share Test (push) Waiting to run
CI / Redteam (Production API) (push) Waiting to run
CI / Redteam (Staging API) (push) Waiting to run
CI / GitHub Actions Lint (push) Waiting to run
CI / Check Ruby (3.0) (push) Waiting to run
release-please / release-please (push) Waiting to run
release-please / build (push) Blocked by required conditions
release-please / publish-npm (push) Blocked by required conditions
release-please / publish-npm-backfill (push) Waiting to run
release-please / docker (push) Blocked by required conditions
release-please / publish-code-scan-action (push) Blocked by required conditions
release-please / attest-code-scan-action (push) Blocked by required conditions
Validate Renovate Config / Validate Renovate Configuration (push) Waiting to run
571 lines
18 KiB
TypeScript
571 lines
18 KiB
TypeScript
import './setup';
|
|
|
|
import { randomUUID } from 'crypto';
|
|
import fs from 'fs';
|
|
|
|
import { expect, it, vi } from 'vitest';
|
|
import { evaluate } from '../../src/evaluator';
|
|
import Eval from '../../src/models/eval';
|
|
import { type TestSuite } from '../../src/types/index';
|
|
import { processConfigFileReferences } from '../../src/util/fileReference';
|
|
import { mockApiProvider, mockReasoningApiProvider, toPrompt } from './helpers';
|
|
import { describeEvaluator } from './lifecycle';
|
|
|
|
describeEvaluator('evaluator basic flows', () => {
|
|
it('evaluate with vars', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt {{ var1 }} {{ var2 }}')],
|
|
tests: [
|
|
{
|
|
vars: { var1: 'value1', var2: 'value2' },
|
|
},
|
|
],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledWith(
|
|
'Test prompt value1 value2',
|
|
expect.objectContaining({
|
|
vars: expect.objectContaining({ var1: 'value1', var2: 'value2' }),
|
|
test: testSuite.tests![0],
|
|
prompt: expect.any(Object),
|
|
}),
|
|
undefined,
|
|
);
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 10,
|
|
prompt: 5,
|
|
completion: 5,
|
|
cached: 0,
|
|
numRequests: 1,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt value1 value2');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt {{ var1 }} {{ var2 }}');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate with vars - no escaping', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt {{ var1 }} {{ var2 }}')],
|
|
tests: [
|
|
{
|
|
vars: { var1: '1 < 2', var2: 'he said "hello world"...' },
|
|
},
|
|
],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 10,
|
|
prompt: 5,
|
|
completion: 5,
|
|
cached: 0,
|
|
numRequests: 1,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt 1 < 2 he said "hello world"...');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt {{ var1 }} {{ var2 }}');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate with vars as object', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt {{ var1.prop1 }} {{ var2 }}')],
|
|
tests: [
|
|
{
|
|
vars: { var1: { prop1: 'value1' }, var2: 'value2' },
|
|
},
|
|
],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 10,
|
|
prompt: 5,
|
|
completion: 5,
|
|
cached: 0,
|
|
numRequests: 1,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt value1 value2');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt {{ var1.prop1 }} {{ var2 }}');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate with vars from file', async () => {
|
|
const originalReadFileSync = fs.readFileSync;
|
|
vi.spyOn(fs, 'readFileSync').mockImplementation((path) => {
|
|
if (typeof path === 'string' && path.includes('test_file.txt')) {
|
|
return '<h1>Sample Report</h1><p>This is a test report with some data for the year 2023.</p>';
|
|
}
|
|
return originalReadFileSync(path);
|
|
});
|
|
|
|
const evalHelpers = await import('../../src/evaluatorHelpers');
|
|
const originalRenderPrompt = evalHelpers.renderPrompt;
|
|
|
|
const mockRenderPrompt = vi.spyOn(evalHelpers, 'renderPrompt');
|
|
mockRenderPrompt.mockImplementation(async (prompt, vars) => {
|
|
if (prompt.raw.includes('{{ var1 }}')) {
|
|
return 'Test prompt <h1>Sample Report</h1><p>This is a test report with some data for the year 2023.</p>';
|
|
}
|
|
return originalRenderPrompt(prompt, vars);
|
|
});
|
|
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt {{ var1 }}')],
|
|
tests: [
|
|
{
|
|
vars: { var1: 'file://test/fixtures/test_file.txt' },
|
|
},
|
|
],
|
|
};
|
|
|
|
try {
|
|
const processedTestSuite = await processConfigFileReferences(testSuite);
|
|
const evalRecord = await Eval.create({}, processedTestSuite.prompts, { id: randomUUID() });
|
|
await evaluate(processedTestSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledWith(
|
|
'Test prompt <h1>Sample Report</h1><p>This is a test report with some data for the year 2023.</p>',
|
|
expect.anything(),
|
|
undefined,
|
|
);
|
|
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.results[0].prompt.raw).toBe(
|
|
'Test prompt <h1>Sample Report</h1><p>This is a test report with some data for the year 2023.</p>',
|
|
);
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt {{ var1 }}');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
} finally {
|
|
mockRenderPrompt.mockRestore();
|
|
fs.readFileSync = originalReadFileSync;
|
|
}
|
|
});
|
|
|
|
it('evaluate with named prompt', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [{ raw: 'Test prompt {{ var1 }} {{ var2 }}', label: 'test display name' }],
|
|
tests: [
|
|
{
|
|
vars: { var1: 'value1', var2: 'value2' },
|
|
},
|
|
],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 10,
|
|
prompt: 5,
|
|
completion: 5,
|
|
cached: 0,
|
|
numRequests: 1,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt value1 value2');
|
|
expect(summary.results[0].prompt.label).toBe('test display name');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate with multiple vars', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt {{ var1 }} {{ var2 }}')],
|
|
tests: [
|
|
{
|
|
vars: { var1: ['value1', 'value3'], var2: ['value2', 'value4'] },
|
|
},
|
|
],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(4);
|
|
expect(summary.stats.successes).toBe(4);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 40,
|
|
prompt: 20,
|
|
completion: 20,
|
|
cached: 0,
|
|
numRequests: 4,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt value1 value2');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt {{ var1 }} {{ var2 }}');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate with multiple providers', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider, mockApiProvider],
|
|
prompts: [toPrompt('Test prompt {{ var1 }} {{ var2 }}')],
|
|
tests: [
|
|
{
|
|
vars: { var1: 'value1', var2: 'value2' },
|
|
},
|
|
],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(2);
|
|
expect(summary.stats.successes).toBe(2);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 20,
|
|
prompt: 10,
|
|
completion: 10,
|
|
cached: 0,
|
|
numRequests: 2,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt value1 value2');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt {{ var1 }} {{ var2 }}');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate without tests', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt')],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 10,
|
|
prompt: 5,
|
|
completion: 5,
|
|
cached: 0,
|
|
numRequests: 1,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate without tests with multiple providers', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider, mockApiProvider, mockApiProvider],
|
|
prompts: [toPrompt('Test prompt')],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(3);
|
|
expect(summary.stats.successes).toBe(3);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 30,
|
|
prompt: 15,
|
|
completion: 15,
|
|
cached: 0,
|
|
numRequests: 3,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
|
|
it('evaluate for reasoning', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockReasoningApiProvider],
|
|
prompts: [toPrompt('Test prompt')],
|
|
};
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, { id: randomUUID() });
|
|
await evaluate(testSuite, evalRecord, {});
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockReasoningApiProvider.callApi).toHaveBeenCalledTimes(1);
|
|
expect(summary.stats.successes).toBe(1);
|
|
expect(summary.stats.failures).toBe(0);
|
|
expect(summary.stats.tokenUsage).toEqual({
|
|
total: 21,
|
|
prompt: 9,
|
|
completion: 12,
|
|
cached: 0,
|
|
numRequests: 1,
|
|
completionDetails: {
|
|
reasoning: 11,
|
|
acceptedPrediction: 12,
|
|
rejectedPrediction: 13,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
assertions: {
|
|
total: 0,
|
|
prompt: 0,
|
|
completion: 0,
|
|
cached: 0,
|
|
numRequests: 0,
|
|
completionDetails: {
|
|
reasoning: 0,
|
|
acceptedPrediction: 0,
|
|
rejectedPrediction: 0,
|
|
cacheReadInputTokens: 0,
|
|
cacheCreationInputTokens: 0,
|
|
},
|
|
},
|
|
});
|
|
expect(summary.results[0].prompt.raw).toBe('Test prompt');
|
|
expect(summary.results[0].prompt.label).toBe('Test prompt');
|
|
expect(summary.results[0].response?.output).toBe('Test output');
|
|
});
|
|
it('allows test case repeat to override global repeat option', async () => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt')],
|
|
tests: [
|
|
{
|
|
options: {
|
|
repeat: 3,
|
|
},
|
|
},
|
|
],
|
|
};
|
|
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, {
|
|
id: randomUUID(),
|
|
});
|
|
|
|
await evaluate(testSuite, evalRecord, { repeat: 2 });
|
|
|
|
const summary = await evalRecord.toEvaluateSummary();
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(3);
|
|
expect(
|
|
vi.mocked(mockApiProvider.callApi).mock.calls.map(([, context]) => context?.repeatIndex),
|
|
).toEqual([0, 1, 2]);
|
|
expect(summary.results).toHaveLength(3);
|
|
});
|
|
|
|
it.each([
|
|
['zero', 0],
|
|
['negative', -1],
|
|
['fractional', 1.5],
|
|
['NaN', Number.NaN],
|
|
['infinite', Number.POSITIVE_INFINITY],
|
|
['unsafe', Number.MAX_SAFE_INTEGER + 1],
|
|
])('falls back to global repeat for a %s per-test repeat', async (_label, repeat) => {
|
|
const testSuite: TestSuite = {
|
|
providers: [mockApiProvider],
|
|
prompts: [toPrompt('Test prompt')],
|
|
tests: [
|
|
{
|
|
options: {
|
|
repeat,
|
|
},
|
|
},
|
|
],
|
|
};
|
|
|
|
const evalRecord = await Eval.create({}, testSuite.prompts, {
|
|
id: randomUUID(),
|
|
});
|
|
|
|
await evaluate(testSuite, evalRecord, { repeat: 2 });
|
|
|
|
expect(mockApiProvider.callApi).toHaveBeenCalledTimes(2);
|
|
});
|
|
});
|