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>
82 lines
3.8 KiB
TypeScript
82 lines
3.8 KiB
TypeScript
import assert from "node:assert/strict";
|
|
import { join } from "node:path";
|
|
import { test } from "node:test";
|
|
import { Ledger } from "../src/ledger/index.ts";
|
|
import { callStart, exited, freshLedger, notStarted, planRun, tempDir, usage } from "./ledger-helpers.ts";
|
|
|
|
// 未完成的动作（方法.md 第九部分"中断与恢复时的记账含义"：先登记、再执行、再登记结果）：
|
|
// 登记了但没有结果的运行、开始了但没有结束的模型调用能被找出来；写了结果之后就不再出现。
|
|
|
|
test("运行：登记了没结果的被找出来，带着有没有确认启动；写了结果就不再出现", (t) => {
|
|
const { ledger } = freshLedger(t);
|
|
planRun(ledger, "base", "baseline", 0);
|
|
planRun(ledger, "run1", "forward", 1);
|
|
planRun(ledger, "run2", "forward", 1);
|
|
ledger.append("runStarted", { run: "base" });
|
|
ledger.append("runStarted", { run: "run1" });
|
|
ledger.append("runResult", { run: "base", process: exited, judged: null });
|
|
assert.deepEqual(
|
|
ledger.pending().runs.map((r) => [r.plan.content.run, r.started]),
|
|
[
|
|
["run1", true],
|
|
["run2", false],
|
|
],
|
|
);
|
|
ledger.append("runResult", { run: "run2", process: notStarted, judged: null });
|
|
assert.deepEqual(ledger.pending().runs.map((r) => r.plan.content.run), ["run1"]);
|
|
ledger.append("runResult", { run: "run1", process: exited, judged: null });
|
|
assert.deepEqual(ledger.pending().runs, []);
|
|
});
|
|
|
|
test("模型调用：开始了没结束的被找出来，带着这次任务的全部材料；有用量也还算没结束；结束后不再出现", (t) => {
|
|
const { ledger } = freshLedger(t);
|
|
ledger.append("callStarted", callStart("k1", "r1", "s1"));
|
|
ledger.append("callStarted", callStart("k2", "e1"));
|
|
ledger.append("callUsage", { call: "k1", reply: 1, usage });
|
|
ledger.append("callEnded", { call: "k2", wallSeconds: { status: "measured", value: 30 }, status: "failed", reason: "接口超时" });
|
|
const calls = ledger.pending().calls;
|
|
assert.deepEqual(calls.map((c) => c.content.call), ["k1"]);
|
|
assert.deepEqual(calls[0]!.content.materials, callStart("k1").materials);
|
|
ledger.append("callEnded", { call: "k1", wallSeconds: { status: "measured", value: 600 }, status: "notSubmitted", reason: "模型自己停下了" });
|
|
assert.deepEqual(ledger.pending(), { runs: [], calls: [] });
|
|
});
|
|
|
|
test("中断后恢复：给没结束的旧调用补写出错加测不到（进程中断），补写后不再算未完成", (t) => {
|
|
const path = join(tempDir(t), "ledger.db");
|
|
const ledger = Ledger.open(path);
|
|
ledger.append("callStarted", callStart("k1", "r1", "s1"));
|
|
ledger.append("callUsage", { call: "k1", reply: 1, usage });
|
|
ledger.close(); // 控制进程被系统杀掉
|
|
const reopened = Ledger.open(path);
|
|
t.after(() => reopened.close());
|
|
assert.deepEqual(reopened.pending().calls.map((c) => c.content.call), ["k1"]);
|
|
reopened.append("callEnded", {
|
|
call: "k1",
|
|
wallSeconds: { status: "unmeasured", reason: "进程中断" },
|
|
status: "failed",
|
|
reason: "进程中断",
|
|
});
|
|
assert.deepEqual(reopened.pending(), { runs: [], calls: [] });
|
|
assert.deepEqual(reopened.records().at(-1)!.content, {
|
|
call: "k1",
|
|
wallSeconds: { status: "unmeasured", reason: "进程中断" },
|
|
status: "failed",
|
|
reason: "进程中断",
|
|
});
|
|
});
|
|
|
|
test("关掉再打开：未完成的动作照样找得出来", (t) => {
|
|
const path = join(tempDir(t), "ledger.db");
|
|
const ledger = Ledger.open(path);
|
|
planRun(ledger, "run1", "forward", 1);
|
|
ledger.append("runStarted", { run: "run1" });
|
|
ledger.append("callStarted", callStart("k1"));
|
|
const before = ledger.pending();
|
|
ledger.close();
|
|
const reopened = Ledger.open(path);
|
|
t.after(() => reopened.close());
|
|
assert.deepEqual(reopened.pending(), before);
|
|
assert.equal(before.runs.length, 1);
|
|
assert.equal(before.calls.length, 1);
|
|
});
|