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
69 lines
2.2 KiB
JavaScript
69 lines
2.2 KiB
JavaScript
// Test fixture for file-based script assertions
|
|
// Used to test that script output is correctly passed to assertion handlers
|
|
|
|
module.exports.rubric = (_output, context) => {
|
|
return `Check that the output correctly addresses: ${context.vars.topic}`;
|
|
};
|
|
|
|
module.exports.expectedValue = () => 'expected string';
|
|
|
|
// For deterministic testing - script returns a known value
|
|
module.exports.knownValue = () => 'SCRIPT_OUTPUT_12345';
|
|
|
|
// Returns an object for llm-rubric (which accepts objects)
|
|
module.exports.rubricObject = () => ({
|
|
role: 'system',
|
|
content: 'Evaluate the response for accuracy',
|
|
});
|
|
|
|
// Returns a number for contains assertion
|
|
module.exports.numericValue = () => 0;
|
|
|
|
// Returns an invalid numeric result for contains assertion
|
|
module.exports.nanValue = () => Number.NaN;
|
|
|
|
// Returns an array for bleu/gleu assertions
|
|
module.exports.referenceArray = () => ['reference one', 'reference two'];
|
|
|
|
// Returns empty string
|
|
module.exports.emptyValue = () => '';
|
|
|
|
// Returns null (edge case)
|
|
module.exports.nullValue = () => null;
|
|
|
|
// Returns undefined (edge case)
|
|
module.exports.undefinedValue = () => undefined;
|
|
|
|
// Returns a function (should cause error for non-script assertions)
|
|
module.exports.functionValue = () => () => 'nested function';
|
|
|
|
// Returns a boolean (should cause error for non-script assertions)
|
|
module.exports.booleanValue = () => true;
|
|
|
|
// Returns a GradingResult (should cause error for non-script assertions)
|
|
module.exports.gradingResultValue = () => ({
|
|
pass: true,
|
|
score: 1,
|
|
reason: 'This is a grading result',
|
|
});
|
|
|
|
// Dynamic regex pattern based on context
|
|
module.exports.getPattern = (_output, context) => {
|
|
return context.vars.pattern || '\\d+';
|
|
};
|
|
|
|
// For regression testing - javascript assertion that returns GradingResult
|
|
module.exports.gradingFunction = (output, _context) => {
|
|
const pass = output.includes('expected');
|
|
return {
|
|
pass,
|
|
score: pass ? 1 : 0,
|
|
reason: pass ? 'Output contains expected' : 'Output missing expected',
|
|
};
|
|
};
|
|
|
|
// Returns trace-derived data for regression testing context.trace in non-trace assertion scripts
|
|
module.exports.traceSpanName = (_output, context) => {
|
|
return context.trace?.spans?.[0]?.name || 'missing-trace';
|
|
};
|