iomgaa
0ac1e01613
src/jev 3 个文件 515 行：判重、查冻结条款、查代码改动三个函数，九问问法和阈值照参考项目，只改说法和字段名，阈值注明未在新项目材料上校准，等真实数据。 新增 npm run test:jev（真实 Jev 三处各问一次）。vocab 加 JevJudgment。 ledger 表结构版本 3：callEnded 四种结局对上 agents，墙钟时间用 Measured（恢复时补写出错、原因"进程中断"、测不到）；退回、提交记录都带 jev。 config 加必填的 models.jev。 用户原话："这次就给提交记录加一个和退回记录同样的 Jev 判断字段"；"墙钟时间改用 Measured，恢复时写出错加测不到（原因'进程中断'）"。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
73 lines
3.3 KiB
TypeScript
73 lines
3.3 KiB
TypeScript
import assert from "node:assert/strict";
|
|
import { checkHunk, checkProtocol, judgeSameChange } from "../src/jev/index.ts";
|
|
import type { JevJudgment } from "../src/vocab/index.ts";
|
|
|
|
// Jev 的真实接线测试（任务书 08 第七部分），npm run test:jev -- <模型名>：要联网、要密钥 TYPESAFE_API_KEY，不放进 npm test。
|
|
// 三处各问一次真实 Jev，材料是随手写的简单填圆材料。只确认请求发得出去、九问都拿回 0 到 1 之间的概率、
|
|
// 请求编号读得到；不判断概率对不对。
|
|
|
|
const model = process.argv[2];
|
|
if (model === undefined || process.argv.length !== 3) throw new Error("用法：npm run test:jev -- <Jev 模型名>，例如 jev-latest");
|
|
|
|
const body =
|
|
"### 不许改什么\n\nharness.py、validate.py 不改。\n\n### 随机性\n\n不用随机数。\n\n" +
|
|
"### 何时停\n\n程序跑完一次 construct_packing 就停。\n\n### 什么运行不算数\n\n校验不通过的运行不算数。";
|
|
|
|
const factor = {
|
|
name: "外圈环半径缩到 0.45",
|
|
method: "把 construct_packing 里外圈环半径常数 0.7 改为 0.45。",
|
|
keySettings: "环半径 0.45",
|
|
continues: null,
|
|
};
|
|
|
|
const all: Array<[string, JevJudgment]> = [];
|
|
|
|
const same = await judgeSameChange(model, [factor], [{ name: "外圈收紧", method: "construct_packing 中外圈 8 个圆所在环的半径从 0.7 改成 0.45。" }]);
|
|
all.push(["判重", same]);
|
|
|
|
const frozen = await checkProtocol(model, {
|
|
factors: [factor],
|
|
safeguards: [],
|
|
metrics: { defined: [], reused: [] },
|
|
body,
|
|
clauses: ["initial.py 的 construct_packing 里，外圈环半径常数 0.7 改为 0.45"],
|
|
});
|
|
for (const j of frozen.judgments) all.push(["冻结条款", j]);
|
|
|
|
const hunk = await checkHunk(
|
|
model,
|
|
{
|
|
path: "initial.py",
|
|
change: "modified",
|
|
text:
|
|
"@@ -33,7 +33,7 @@ def construct_packing():\n" +
|
|
" for i in range(8):\n" +
|
|
" angle = 2 * np.pi * i / 8\n" +
|
|
"- centers[i + 1] = [0.5 + 0.7 * np.cos(angle), 0.5 + 0.7 * np.sin(angle)]\n" +
|
|
"+ centers[i + 1] = [0.5 + 0.45 * np.cos(angle), 0.5 + 0.45 * np.sin(angle)]\n" +
|
|
" \n" +
|
|
" for i in range(16):\n" +
|
|
" angle = 2 * np.pi * i / 16",
|
|
},
|
|
{ body, metrics: [] },
|
|
);
|
|
for (const j of hunk.judgments) all.push(["代码改动", j]);
|
|
|
|
for (const [site, j] of all) {
|
|
console.log(`${site}\t${j.question}\t概率 ${j.probability}\t阈值 ${j.threshold}\t${j.yes ? "是" : "否"}\t请求编号 ${j.requestId}`);
|
|
}
|
|
console.log(`冻结条款有问题：${frozen.flagged}；代码改动有问题：${hunk.flagged}`);
|
|
|
|
assert.deepEqual(
|
|
all.map(([, j]) => j.question),
|
|
["same_change", "self_contradictory", "changes_measurement", "too_vague", "unseeded_randomness", "reads_clock", "touches_measurement", "early_exit", "zero_for_unmeasured"],
|
|
);
|
|
for (const [, j] of all) {
|
|
assert.ok(j.probability >= 0 && j.probability <= 1, `${j.question} 的概率不在 0 到 1 之间`);
|
|
assert.ok(j.requestId.length > 0, `${j.question} 没有请求编号`);
|
|
}
|
|
// 冻结三问各发一次请求，请求编号各不相同；代码改动五问一次请求，编号相同。
|
|
assert.equal(new Set(frozen.judgments.map((j) => j.requestId)).size, 3);
|
|
assert.equal(new Set(hunk.judgments.map((j) => j.requestId)).size, 1);
|
|
console.log("九问都拿回了 0 到 1 之间的概率和请求编号");
|