Files
wehub-resource-sync 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
chore: import upstream snapshot with attribution
2026-07-13 12:43:05 +08:00

103 lines
3.2 KiB
JavaScript

#!/usr/bin/env bun
/**
* MiniWoB++ browser benchmark runner (#9476).
*
* Runs the MiniWoB++ task suite through the REAL plugin-browser command router
* (`executeBrowserWorkspaceCommand`, web mode) and writes a run-report artifact.
* This is the plugin-browser analog of plugin-computeruse's OSWorld benchmark
* runner — proof that a web-interaction benchmark is wired end-to-end through
* plugin-browser BROWSER actions, not bypassing it via the inference layer.
*
* Usage:
* bun scripts/run-miniwob-benchmark.mjs [--policy oracle|noop|wrong]
* [--seeds N] [--out <file>]
*/
import { mkdir, writeFile } from "node:fs/promises";
import path from "node:path";
import { fileURLToPath } from "node:url";
import {
NoopPolicy,
OraclePolicy,
runBenchmarkSuite,
WrongPolicy,
} from "../src/benchmark/index.ts";
const here = path.dirname(fileURLToPath(import.meta.url));
const repoRoot = path.resolve(here, "../../..");
function parseArgs(argv) {
const opts = { policy: "oracle", seeds: 3, out: null };
for (let i = 0; i < argv.length; i++) {
const a = argv[i];
if (a === "--policy") opts.policy = argv[++i];
else if (a === "--seeds") opts.seeds = Number(argv[++i]);
else if (a === "--out") opts.out = argv[++i];
}
return opts;
}
function makePolicy(name) {
if (name === "noop") return new NoopPolicy();
if (name === "wrong") return new WrongPolicy();
return new OraclePolicy();
}
async function main() {
const opts = parseArgs(process.argv.slice(2));
const seeds = Array.from({ length: Math.max(1, opts.seeds) }, (_, i) => i);
const outPath =
opts.out ??
path.join(
repoRoot,
"test-results/evidence/9476-browser-benchmark",
`miniwob-${opts.policy}-run.json`,
);
const report = await runBenchmarkSuite({
seeds,
policy: makePolicy(opts.policy),
});
// Stamp the artifact after the deterministic run (clock is not part of the run).
const stamped = { generatedAt: new Date().toISOString(), ...report };
await mkdir(path.dirname(outPath), { recursive: true });
await writeFile(outPath, `${JSON.stringify(stamped, null, 2)}\n`);
// Human-readable summary.
console.log(
`\nMiniWoB++ benchmark — engine=${report.engine} policy=${report.policy}`,
);
console.log("─".repeat(64));
for (const t of report.summary.byTask) {
const bar = t.solved === t.total ? "✓" : "✗";
console.log(` ${bar} ${t.taskId.padEnd(24)} ${t.solved}/${t.total}`);
}
console.log("─".repeat(64));
console.log(
` TOTAL solved ${report.summary.solved}/${report.summary.total} ` +
`(success rate ${(report.summary.successRate * 100).toFixed(1)}%)`,
);
const failures = report.episodes.filter((e) => !e.success);
if (failures.length > 0) {
console.log("\n failing episodes:");
for (const f of failures) {
const steps = f.trajectory
.map((s) => `${s.action.type}${s.error ? `!${s.error}` : ""}`)
.join(" → ");
console.log(
` - ${f.taskId}#${f.seed} reward=${f.reward} steps=[${steps}]` +
`${f.error ? ` err=${f.error}` : ""}`,
);
}
}
console.log(`\n artifact → ${path.relative(repoRoot, outPath)}\n`);
}
main().catch((err) => {
console.error(err);
process.exit(1);
});