mirror of
https://github.com/hanzoai/trolley-bench.git
synced 2026-11-02 13:22:03 +00:00
Zachary Landes
247bd2614b
* Packaged the benchmark's working copy with its frozen prompts, runners, raw answers, analysis and built page as committed evidence * Rewrote run-machine paths and left out share credentials, drafts and operator notes; PACKAGING.md lists every exclusion and change * Fixed the models.yaml generator listing rerun models twice, and let the Jev runner take its key from TYPESAFE_API_KEY
18 lines
925 B
JavaScript
18 lines
925 B
JavaScript
// Render every v1 cell once into scenarios/cells-v1.json; runners read only this frozen file
|
|
import crypto from "node:crypto";
|
|
import fs from "node:fs";
|
|
import path from "node:path";
|
|
import { fileURLToPath } from "node:url";
|
|
import { PROMPT_VERSION, v1Cells } from "./scenarios.mjs";
|
|
|
|
const HERE = path.dirname(fileURLToPath(import.meta.url));
|
|
const cells = v1Cells();
|
|
const ids = new Set(cells.map((c) => c.id));
|
|
if (ids.size !== cells.length) throw new Error("duplicate cell ids");
|
|
const body = JSON.stringify({ prompt_version: PROMPT_VERSION, cells });
|
|
fs.writeFileSync(path.join(HERE, "cells-v1.json"), body + "\n");
|
|
const sha = crypto.createHash("sha256").update(body + "\n").digest("hex");
|
|
const counts = {};
|
|
for (const c of cells) counts[c.scenario] = (counts[c.scenario] ?? 0) + 1;
|
|
console.log(JSON.stringify({ prompt_version: PROMPT_VERSION, cells: cells.length, answers: cells.length * 3, sha256: sha, counts }));
|