426e9eeabd
Voice Workbench / headless workbench (mocked backends) (push) Has been cancelled
Voice Workbench / real acoustic lane (nightly, provisioned only) (push) Has been cancelled
ci / test (push) Has been cancelled
ci / lint-and-format (push) Has been cancelled
ci / build (push) Has been cancelled
ci / dev-startup (push) Has been cancelled
gitleaks / gitleaks (push) Has been cancelled
Markdown Links / Relative Markdown Links (push) Has been cancelled
Quality (Extended) / Homepage Build (PR smoke) (push) Has been cancelled
Quality (Extended) / Comment-only diff guard (push) Has been cancelled
Quality (Extended) / Format + Type Safety Ratchet (push) Has been cancelled
Quality (Extended) / Develop Gate (secret scan + UI determinism) (push) Has been cancelled
Quality (Extended) / Develop Gate (lint) (push) Has been cancelled
Chat shell gestures / Chat shell gesture + parity e2e (push) Has been cancelled
Cloud Gateway Discord / Test (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx @biomejs/biome check packages/lifeops-bench/src, benchmark-lint) (push) Has been cancelled
Benchmark Bridge Tests / benchmark (bunx vitest run --config packages/lifeops-bench/vitest.config.ts --root packages/lifeops-bench --passWithNoTests, benchmark-tests) (push) Has been cancelled
Build Agent Image / build-and-push (push) Has been cancelled
Dev Smoke / bun run dev onboarding chat (push) Has been cancelled
Dev Smoke / Vite HMR dependency-level smoke (push) Has been cancelled
Electrobun Submodule Guard / electrobun gitlink is fetchable (push) Has been cancelled
Publish @elizaos/example-code / check_npm (push) Has been cancelled
Publish @elizaos/example-code / publish_npm (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / verify_version (push) Has been cancelled
Publish @elizaos/plugin-elizacloud / publish_npm (push) Has been cancelled
Sandbox Live Smoke / Sandbox live smoke (push) Has been cancelled
Snap Build & Test / Build Snap (amd64) (push) Has been cancelled
Snap Build & Test / Build Snap (arm64) (push) Has been cancelled
Test Packaging / elizaos CLI global-install smoke (node + bun) (push) Has been cancelled
Cloud Gateway Webhook / Test (push) Has been cancelled
Cloud Tests / lint-and-types (push) Has been cancelled
Cloud Tests / unit-tests (push) Has been cancelled
Cloud Tests / integration-tests (push) Has been cancelled
Cloud Tests / e2e-tests (push) Has been cancelled
CodeQL Advanced / Analyze (javascript-typescript) (push) Has been cancelled
Deploy Apps Worker (Product 2) / Determine environment (push) Has been cancelled
Deploy Apps Worker (Product 2) / Deploy apps worker to apps-control host (${{ needs.determine-env.outputs.environment }}) (push) Has been cancelled
Deploy Eliza Provisioning Worker / Determine environment (push) Has been cancelled
Deploy Eliza Provisioning Worker / Deploy worker to Hetzner host (${{ needs.determine-env.outputs.environment }} @ ${{ needs.determine-env.outputs.deployment_sha }}) (push) Has been cancelled
Dev Smoke / Classify changed paths (push) Has been cancelled
supply-chain / sbom (push) Has been cancelled
supply-chain / vulnerability-scan (push) Has been cancelled
Build, Push & Deploy to Phala Cloud / build-and-push (push) Has been cancelled
Test Packaging / Validate Packaging Configs (push) Has been cancelled
Test Packaging / Build & Test PyPI Package (push) Has been cancelled
Test Packaging / PyPI on Python ${{ matrix.python }} (push) Has been cancelled
Test Packaging / Pack & Test JS Tarballs (push) Has been cancelled
UI Fixture E2E / ui-fixture-e2e (push) Has been cancelled
UI Fixture E2E / fixture-e2e (push) Has been cancelled
UI Story Gate / story-gate (push) Has been cancelled
vault-ci / test (macos-latest) (push) Has been cancelled
vault-ci / test (ubuntu-latest) (push) Has been cancelled
vault-ci / test (windows-latest) (push) Has been cancelled
vault-ci / app-core wiring tests (push) Has been cancelled
verify-patches / verify patches/CHECKSUMS.sha256 (push) Has been cancelled
Voice Benchmark Smoke / voice-emotion fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voiceagentbench fixture smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench-quality unit smoke (push) Has been cancelled
Voice Benchmark Smoke / voicebench TypeScript unit (no audio) (push) Has been cancelled
Voice Benchmark Smoke / voice bench smoke summary (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/app-core test bun run --cwd packages/elizaos test bun run --cwd packages/cloud/shared test], app-and-cli) (push) Has been cancelled
Windows CI / windows ([bun run --cwd packages/scenario-runner test bun run --cwd packages/vault test bun run --cwd packages/security test bun run --cwd plugins/plugin-coding-tools test], framework-packages) (push) Has been cancelled
Windows CI / windows ([bun run --cwd plugins/plugin-elizacloud test bun run --cwd plugins/plugin-discord test bun run --cwd plugins/plugin-anthropic test bun run --cwd plugins/plugin-openai test bun run --cwd plugins/plugin-app-control test bun run --cwd plugins/pl… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run build --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/agent --concurrency=4 node packages/scripts/run-bash-linux-only.mjs scripts/verify-riscv64-buildpaths.sh node packages/scripts/run… (push) Has been cancelled
Windows CI / windows ([node packages/scripts/run-turbo.mjs run typecheck --filter=@elizaos/core --filter=@elizaos/shared --filter=@elizaos/cloud-shared --concurrency=4 bun run --cwd packages/core test bun run --cwd packages/shared test], core-runtime, 75) (push) Has been cancelled
143 lines
4.7 KiB
TypeScript
143 lines
4.7 KiB
TypeScript
/** Unit tests for `buildWorkflowEvaluationSuite` JSONL sampling from executions (deterministic). */
|
|
import { describe, expect, test } from 'bun:test';
|
|
import { buildWorkflowEvaluationSuite } from '../../src/utils/evaluation-samples';
|
|
import { createExecution, createWorkflowResponse } from '../fixtures/workflows';
|
|
|
|
describe('buildWorkflowEvaluationSuite', () => {
|
|
test('builds Smithers JSONL samples from successful workflow executions', () => {
|
|
const workflow = createWorkflowResponse({
|
|
id: 'wf-cerebras',
|
|
versionId: 'version-1',
|
|
name: 'Cerebras review workflow',
|
|
});
|
|
const execution = createExecution({
|
|
id: 'exec-success',
|
|
workflowId: 'wf-cerebras',
|
|
mode: 'trigger',
|
|
customData: {
|
|
triggerData: {
|
|
model: 'cerebras/gpt-oss-120b',
|
|
prompt: 'Review this workflow.',
|
|
},
|
|
},
|
|
data: {
|
|
resultData: {
|
|
lastNodeExecuted: 'Add Review Fields',
|
|
engine: {
|
|
provider: 'smithers',
|
|
nodes: 2,
|
|
levels: 2,
|
|
maxConcurrency: 1,
|
|
started: 2,
|
|
finished: 2,
|
|
failed: 0,
|
|
skipped: 0,
|
|
retries: 0,
|
|
},
|
|
runData: {
|
|
'Add Review Fields': [
|
|
{
|
|
executionTime: 8,
|
|
data: {
|
|
main: [[{ json: { source: 'cerebras', verified: true } }]],
|
|
},
|
|
},
|
|
],
|
|
},
|
|
},
|
|
},
|
|
});
|
|
|
|
const suite = buildWorkflowEvaluationSuite(workflow, [execution], {
|
|
generatedAt: '2026-06-20T12:00:00.000Z',
|
|
});
|
|
const sample = JSON.parse(suite.jsonl) as (typeof suite.samples)[number];
|
|
|
|
expect(suite.sampleCount).toBe(1);
|
|
expect(suite.optimizer.engine).toBe('smithers-gepa');
|
|
expect(suite.optimizer.caseFile).toBe('evals/cerebras-review-workflow.jsonl');
|
|
expect(suite.optimizer.suiteName).toBe('cerebras-review-workflow');
|
|
expect(suite.optimizer.recommendedCommand).toContain('smithers-orchestrator eval');
|
|
expect(suite.optimizer.recommendedEvalCommand).toContain(
|
|
'--cases evals/cerebras-review-workflow.jsonl --suite cerebras-review-workflow'
|
|
);
|
|
expect(suite.optimizer.recommendedOptimizeCommand).toBe('bunx smithers-orchestrator optimize');
|
|
expect(suite.optimizer.recommendedObservabilityCommand).toBe(
|
|
'bunx smithers-orchestrator observability --detach'
|
|
);
|
|
expect(suite.optimizer.recommendedMetricsCommand).toBe(
|
|
'bunx smithers-orchestrator up <workflow.tsx> --serve --metrics'
|
|
);
|
|
expect(sample.input.triggerData?.model).toBe('cerebras/gpt-oss-120b');
|
|
expect(sample.expected.passed).toBe(true);
|
|
expect(sample.expected.engine?.provider).toBe('smithers');
|
|
expect(sample.expected.nodes[0]).toEqual(
|
|
expect.objectContaining({
|
|
name: 'Add Review Fields',
|
|
status: 'success',
|
|
itemCount: 1,
|
|
preview: '{"source":"cerebras","verified":true}',
|
|
})
|
|
);
|
|
expect(sample.score).toEqual({
|
|
pass: true,
|
|
value: 1,
|
|
reason: 'Execution completed successfully.',
|
|
});
|
|
});
|
|
|
|
test('preserves failed executions as regression samples', () => {
|
|
const workflow = createWorkflowResponse({ id: 'wf-fail' });
|
|
const execution = createExecution({
|
|
id: 'exec-fail',
|
|
workflowId: 'wf-fail',
|
|
status: 'error',
|
|
data: {
|
|
resultData: {
|
|
error: { message: 'HTTP request failed' },
|
|
runData: {
|
|
'HTTP Request': [
|
|
{
|
|
executionTime: 12,
|
|
error: { message: 'HTTP request failed' },
|
|
data: { main: [[]] },
|
|
},
|
|
],
|
|
},
|
|
},
|
|
},
|
|
});
|
|
|
|
const suite = buildWorkflowEvaluationSuite(workflow, [execution]);
|
|
|
|
expect(suite.samples[0].expected.error).toBe('HTTP request failed');
|
|
expect(suite.samples[0].expected.nodes[0]).toEqual(
|
|
expect.objectContaining({
|
|
name: 'HTTP Request',
|
|
status: 'error',
|
|
error: 'HTTP request failed',
|
|
})
|
|
);
|
|
expect(suite.samples[0].score).toEqual({
|
|
pass: false,
|
|
value: 0,
|
|
reason: 'Execution failed: HTTP request failed',
|
|
});
|
|
});
|
|
|
|
test('limits samples for compact clipboard exports', () => {
|
|
const workflow = createWorkflowResponse();
|
|
const executions = [
|
|
createExecution({ id: 'exec-1' }),
|
|
createExecution({ id: 'exec-2' }),
|
|
createExecution({ id: 'exec-3' }),
|
|
];
|
|
|
|
const suite = buildWorkflowEvaluationSuite(workflow, executions, { limit: 2 });
|
|
|
|
expect(suite.sampleCount).toBe(2);
|
|
expect(suite.samples.map((sample) => sample.executionId)).toEqual(['exec-1', 'exec-2']);
|
|
expect(suite.jsonl.split('\n')).toHaveLength(2);
|
|
});
|
|
});
|