feat: 任务书 08，jev 模块与账本记 Jev 判断

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>
2026-10-03 02:10:55 -04:00
parent 68e49fd01a
commit 0ac1e01613
18 changed files with 1228 additions and 57 deletions
@@ -3,7 +3,7 @@ import { join } from "node:path";
 import { DatabaseSync } from "node:sqlite";
 import { test } from "node:test";
 import { Ledger, type LedgerRecord } from "../src/ledger/index.ts";
-import { hash } from "../src/vocab/index.ts";
+import { hash, type JevJudgment } from "../src/vocab/index.ts";
 import {
  callStart,
  closeStage,
@@ -111,8 +111,11 @@ test("唯一约束：同一次模型调用开始两次报错", (t) => {
 test("唯一约束：同一次模型调用结束两次报错", (t) => {
  const { ledger, path } = freshLedger(t);
  ledger.append("callStarted", callStart("k1"));
-  ledger.append("callEnded", { call: "k1", ending: "completed" });
-  assert.throws(() => ledger.append("callEnded", { call: "k1", ending: "failed", reason: "又报了一次" }), /call_ended_once/);
+  ledger.append("callEnded", { call: "k1", wallSeconds: { status: "measured", value: 12.5 }, status: "submitted" });
+  assert.throws(
+    () => ledger.append("callEnded", { call: "k1", wallSeconds: { status: "measured", value: 3 }, status: "failed", reason: "又报了一次" }),
+    /call_ended_once/,
+  );
  assert.equal(countRows(path), 2);
 });

@@ -162,19 +165,19 @@ test("内容不符合定义时不写入：多出的字段、提交内容不合
  openStage(ledger, "s1", "wrapUp", 1);
  assert.throws(() => ledger.append("runStarted", { run: "r1", extra: 1 } as never), /runStarted/);
  assert.throws(
-    () => ledger.append("submission", { stageId: "s1", author: "r1", target: null, item: null, version: 1, kind: "wrapUp", content: { body: "" } }),
+    () => ledger.append("submission", { stageId: "s1", author: "r1", target: null, item: null, version: 1, jev: null, kind: "wrapUp", content: { body: "" } }),
    /wrapUp/,
  );
  // 提案、挑刺一人能交好几份，必须带编号；实现一人对一个候选只交一份，编号必须为空，
  // 否则另起一个编号就能绕开"实现不能替换"。
  openStage(ledger, "prop", "proposal", 1);
  assert.throws(
-    () => ledger.append("submission", { stageId: "prop", author: "r1", target: null, item: null as never, version: 1, kind: "proposal", content: proposal(range(1, 2, 3)) }),
+    () => ledger.append("submission", { stageId: "prop", author: "r1", target: null, item: null as never, version: 1, jev: null, kind: "proposal", content: proposal(range(1, 2, 3)) }),
    /proposal/,
  );
  openStage(ledger, "impl", "implementation", 1, ["e1"]);
  assert.throws(
-    () => ledger.append("submission", { stageId: "impl", author: "e1", target: "c1", item: "x" as never, version: 1, kind: "implementation", content: implementation() }),
+    () => ledger.append("submission", { stageId: "impl", author: "e1", target: "c1", item: "x" as never, version: 1, jev: null, kind: "implementation", content: implementation() }),
    /implementation/,
  );
  assert.equal(countRows(path), 3); // 三条开阶段
@@ -184,7 +187,7 @@ test("写提案：作者自评拆成一条封存，提案记录里不带它", (t
  const { ledger } = freshLedger(t);
  openStage(ledger, "s1", "proposal", 1);
  const record = ledger.append("submission", {
-    stageId: "s1", author: "r1", target: null, item: "r1-1", version: 1, kind: "proposal", content: proposal(range(1, 2, 3)),
+    stageId: "s1", author: "r1", target: null, item: "r1-1", version: 1, kind: "proposal", content: proposal(range(1, 2, 3)), jev: null,
  });
  const all = ledger.records();
  const stored = all.find((r) => r.kind === "submission")!;
@@ -197,17 +200,174 @@ test("写提案：作者自评拆成一条封存，提案记录里不带它", (t
  assert.equal(seal.seq, record.seq + 1);
 });

-test("退回：被退回的内容原样存，带退回理由；来自 Jev 的带原始概率和结论", (t) => {
-  const { ledger } = freshLedger(t);
+// Jev 判断的样子照 src/vocab/jev.ts 的 JevJudgment 手写：问题名、问题全文哈希（64 位十六进制）、阈值、原始概率、结论、请求编号。
+const judgment = (question: string, probability: number, threshold: number, requestId: string): JevJudgment => ({
+  question,
+  questionHash: "ab".repeat(32),
+  threshold,
+  probability,
+  yes: probability > threshold,
+  requestId,
+});
+
+test("退回：被退回的内容原样存；程序检查退回的 jev 为 null，Jev 退回的原样存它用到的几条判断", (t) => {
+  const path = join(tempDir(t), "ledger.db");
+  const ledger = Ledger.open(path);
  const malformed = { factors: "不是数组" };
+  // 冻结条款一次问三问，退回时三条判断都存，包括判"否"的两条。
+  const clauses = [
+    judgment("changes_measurement", 0.97, 0.5, "req-1"),
+    judgment("self_contradictory", 0.02, 0.6, "req-2"),
+    judgment("too_vague", 0.1, 0.7, "req-3"),
+  ];
  ledger.append("rejection", { stageId: "s1", author: "r1", kind: "proposal", submitted: malformed, reason: "因子清单格式不对", jev: null });
  ledger.append("rejection", {
-    stageId: "s6", author: "r2", kind: "response", submitted: { body: "改了评测" }, reason: "冻结条款改动了评测",
-    jev: { probabilities: { yes: 0.97, no: 0.03 }, conclusion: "changesEvaluation" },
+    stageId: "s6", author: "r2", kind: "response", submitted: { body: "改了评测" }, reason: "冻结条款改动了评测", jev: clauses,
  });
-  const rejections = ledger.records().filter((r) => r.kind === "rejection");
+  ledger.close();
+  const reopened = Ledger.open(path);
+  t.after(() => reopened.close());
+  const rejections = reopened.records().filter((r) => r.kind === "rejection");
  assert.deepEqual(rejections.map((r) => r.content.submitted), [malformed, { body: "改了评测" }]);
-  assert.deepEqual(rejections[1]!.content.jev, { probabilities: { yes: 0.97, no: 0.03 }, conclusion: "changesEvaluation" });
+  assert.equal(rejections[0]!.content.jev, null);
+  assert.deepEqual(rejections[1]!.content.jev, [
+    { question: "changes_measurement", questionHash: "ab".repeat(32), threshold: 0.5, probability: 0.97, yes: true, requestId: "req-1" },
+    { question: "self_contradictory", questionHash: "ab".repeat(32), threshold: 0.6, probability: 0.02, yes: false, requestId: "req-2" },
+    { question: "too_vague", questionHash: "ab".repeat(32), threshold: 0.7, probability: 0.1, yes: false, requestId: "req-3" },
+  ]);
+});
+
+test("退回：jev 不合 JevJudgment 的拒收，一条都不写", (t) => {
+  const { ledger, path } = freshLedger(t);
+  const good = judgment("same_change", 0.9, 0.5, "req-1");
+  const { requestId: _, ...withoutRequest } = good;
+  const bad: unknown[] = [
+    [], // 空数组：Jev 退回至少有一条判断，程序退回写 null
+    { probabilities: { yes: 0.97, no: 0.03 }, conclusion: "changesEvaluation" }, // 旧写法：不是数组
+    good, // 一条判断也要放进数组
+    [{ ...good, probability: 1.2 }], // 概率超出 0 到 1
+    [{ ...good, threshold: -0.1 }], // 阈值超出 0 到 1
+    [withoutRequest], // 缺请求编号
+    [{ ...good, requestId: "" }], // 请求编号为空
+    [{ ...good, questionHash: "abc" }], // 哈希不是 64 位十六进制
+    [{ ...good, question: "Same Change" }], // 问题名格式不对
+    [{ ...good, yes: "true" }], // 结论不是布尔值
+    [{ ...good, note: "多写一项" }], // 不认识的字段
+  ];
+  for (const jev of bad) {
+    assert.throws(
+      () => ledger.append("rejection", { stageId: "s1", author: "r1", kind: "proposal", submitted: {}, reason: "判为同一个改法", jev } as never),
+      /账本记录"rejection"的内容不符合定义/,
+      JSON.stringify(jev),
+    );
+  }
+  assert.equal(countRows(path), 0);
+});
+
+test("模型调用结束：四种结局各存一条，墙钟时间（秒）测到带值、测不到带原因，关掉再打开读出不变", (t) => {
+  const path = join(tempDir(t), "ledger.db");
+  const ledger = Ledger.open(path);
+  const endings = [
+    { call: "k1", wallSeconds: { status: "measured", value: 812.25 }, status: "submitted" },
+    { call: "k2", wallSeconds: { status: "measured", value: 95 }, status: "notSubmitted", reason: "模型自己停下了，一份都没交" },
+    { call: "k3", wallSeconds: { status: "unmeasured", reason: "进程中断" }, status: "failed", reason: "进程中断，恢复时补写" },
+    { call: "k4", wallSeconds: { status: "measured", value: 0 }, status: "stopped" },
+  ] as const;
+  for (const e of endings) {
+    ledger.append("callStarted", callStart(e.call));
+    ledger.append("callEnded", e);
+  }
+  ledger.close();
+  const reopened = Ledger.open(path);
+  t.after(() => reopened.close());
+  const ended = reopened.records().filter((r) => r.kind === "callEnded").map((r) => r.content);
+  assert.deepEqual(ended, [
+    { call: "k1", wallSeconds: { status: "measured", value: 812.25 }, status: "submitted" },
+    { call: "k2", wallSeconds: { status: "measured", value: 95 }, status: "notSubmitted", reason: "模型自己停下了，一份都没交" },
+    { call: "k3", wallSeconds: { status: "unmeasured", reason: "进程中断" }, status: "failed", reason: "进程中断，恢复时补写" },
+    { call: "k4", wallSeconds: { status: "measured", value: 0 }, status: "stopped" },
+  ]);
+  assert.deepEqual(reopened.pending().calls, []);
+});
+
+test("模型调用结束：结局和原因对不上、墙钟时间缺失或不合 Measured、测到的值为负，都拒收", (t) => {
+  const { ledger, path } = freshLedger(t);
+  const s3 = { status: "measured", value: 3 };
+  const bad: unknown[] = [
+    { call: "k1", wallSeconds: s3, status: "notSubmitted" }, // 没交要带原因
+    { call: "k1", wallSeconds: s3, status: "failed" }, // 出错要带原因
+    { call: "k1", wallSeconds: s3, status: "failed", reason: "" }, // 原因不能为空
+    { call: "k1", wallSeconds: s3, status: "submitted", reason: "交了" }, // 交了不带原因
+    { call: "k1", wallSeconds: s3, status: "stopped", reason: "用户停下" }, // 被停下不带原因
+    { call: "k1", wallSeconds: s3, status: "completed" }, // 旧写法
+    { call: "k1", status: "submitted" }, // 缺墙钟时间
+    { call: "k1", wallSeconds: 3, status: "submitted" }, // 裸数字，不是 Measured
+    { call: "k1", wallSeconds: null, status: "submitted" }, // 测不到不能写 null
+    { call: "k1", wallSeconds: { status: "measured", value: "3" }, status: "submitted" }, // 值不是数
+    { call: "k1", wallSeconds: { status: "measured" }, status: "submitted" }, // 测到却没带值
+    { call: "k1", wallSeconds: { status: "unmeasured" }, status: "failed", reason: "进程中断" }, // 测不到却没带原因
+    { call: "k1", wallSeconds: { status: "unmeasured", reason: "" }, status: "failed", reason: "进程中断" }, // 原因为空
+    { call: "k1", wallSeconds: { status: "unmeasured", reason: "进程中断", value: 0 }, status: "failed", reason: "进程中断" }, // 测不到又带值
+  ];
+  for (const content of bad) {
+    assert.throws(() => ledger.append("callEnded", content as never), /账本记录"callEnded"的内容不符合定义/, JSON.stringify(content));
+  }
+  assert.equal(countRows(path), 0);
+});
+
+test("提交：jev 在外层与 content 并列，null 或 JevJudgment 数组都能存能读；提案拆封存不受影响", (t) => {
+  const path = join(tempDir(t), "ledger.db");
+  const ledger = Ledger.open(path);
+  openStage(ledger, "s1", "proposal", 1);
+  openStage(ledger, "s9", "implementation", 1);
+  // 代码改动五问都判"否"才收下，五条判断连同原始概率都存。
+  const checks = [
+    judgment("unseeded_randomness", 0.01, 0.5, "req-1"),
+    judgment("reads_clock", 0.02, 0.5, "req-2"),
+    judgment("touches_measurement", 0.2, 0.6, "req-3"),
+    judgment("early_exit", 0.05, 0.5, "req-4"),
+    judgment("zero_for_unmeasured", 0.3, 0.7, "req-5"),
+  ];
+  const p = ledger.append("submission", { stageId: "s1", author: "r1", target: null, item: "r1-1", version: 1, kind: "proposal", content: proposal(range(1, 2, 3)), jev: null });
+  ledger.append("submission", { stageId: "s9", author: "e1", target: "c1", item: null, version: 1, kind: "implementation", content: implementation(), jev: checks });
+  ledger.close();
+  const reopened = Ledger.open(path);
+  t.after(() => reopened.close());
+  const all = reopened.records();
+  const subs = all.filter((r) => r.kind === "submission");
+  assert.deepEqual(subs.map((r) => r.content.jev), [
+    null,
+    [
+      { question: "unseeded_randomness", questionHash: "ab".repeat(32), threshold: 0.5, probability: 0.01, yes: false, requestId: "req-1" },
+      { question: "reads_clock", questionHash: "ab".repeat(32), threshold: 0.5, probability: 0.02, yes: false, requestId: "req-2" },
+      { question: "touches_measurement", questionHash: "ab".repeat(32), threshold: 0.6, probability: 0.2, yes: false, requestId: "req-3" },
+      { question: "early_exit", questionHash: "ab".repeat(32), threshold: 0.5, probability: 0.05, yes: false, requestId: "req-4" },
+      { question: "zero_for_unmeasured", questionHash: "ab".repeat(32), threshold: 0.7, probability: 0.3, yes: false, requestId: "req-5" },
+    ],
+  ]);
+  assert.equal("jev" in (subs[1]!.content.content as object), false);
+  const seal = all.find((r) => r.kind === "seal")!;
+  assert.deepEqual(seal.content, { proposal: p.seq, range: range(1, 2, 3) });
+  assert.equal(seal.seq, p.seq + 1);
+});
+
+test("提交：缺 jev、jev 不合 JevJudgment 数组、jev 写进 content 里，都拒收", (t) => {
+  const { ledger, path } = freshLedger(t);
+  openStage(ledger, "s1", "wrapUp", 1);
+  const good = judgment("same_change", 0.1, 0.5, "req-1");
+  const base = { stageId: "s1", author: "r1", target: null, item: null, version: 1, kind: "wrapUp", content: { body: "收尾" } };
+  const bad: unknown[] = [
+    base, // 缺 jev：没用到 Jev 要写 null，不靠省略
+    { ...base, jev: [] }, // 空数组
+    { ...base, jev: good }, // 一条也要放进数组
+    { ...base, jev: [{ ...good, probability: -0.1 }] }, // 概率超出 0 到 1
+    { ...base, jev: [{ ...good, extra: 1 }] }, // 不认识的字段
+    { ...base, jev: null, content: { body: "收尾", jev: null } }, // jev 不进 content
+  ];
+  for (const content of bad) {
+    assert.throws(() => ledger.append("submission", content as never), /账本记录"submission（提交种类 wrapUp）"的内容不符合定义/, JSON.stringify(content));
+  }
+  assert.equal(countRows(path), 1);
 });

 test("事务：中途出错，一条都没写进去；中途被拒收，前面写的也撤销；正常结束则全部写进去", (t) => {
@@ -253,7 +413,7 @@ test("关掉再打开：读出的记录不变，序号接着往下排", (t) => {
  const ledger = Ledger.open(path);
  ledger.append("config", { researchers: ["r1", "r2"] });
  openStage(ledger, "s1", "proposal", 1);
-  ledger.append("submission", { stageId: "s1", author: "r1", target: null, item: "r1-1", version: 1, kind: "proposal", content: proposal(range(1, 2, 3)) });
+  ledger.append("submission", { stageId: "s1", author: "r1", target: null, item: "r1-1", version: 1, jev: null, kind: "proposal", content: proposal(range(1, 2, 3)) });
  ledger.append("note", { author: "r2", body: "笔记" });
  closeStage(ledger, "s1");
  planRun(ledger, "run1", "forward", 1);
@@ -276,6 +436,13 @@ test("打开：表结构版本不对报错；不是空文件也不是账本的
  db.close();
  assert.throws(() => Ledger.open(wrongVersion), /版本是 99/);

+  // 版本 2 是"模型调用结束"还没有墙钟时间、退回还没有 Jev 判断数组时的账本，不迁移，打开报错。
+  const previous = join(dir, "v2.db");
+  const v2 = new DatabaseSync(previous);
+  v2.exec("PRAGMA user_version = 2");
+  v2.close();
+  assert.throws(() => Ledger.open(previous), /版本是 2.*只认版本 3/s);
+
  const foreign = join(dir, "foreign.db");
  const other = new DatabaseSync(foreign);
  other.exec("CREATE TABLE t (x INTEGER)");
@@ -311,9 +478,9 @@ test("查询：阶段关了没有、某份提交的最新一版（同一人对
  assert.equal(ledger.stageClosed("s1"), false);
  const slot = { stageId: "s1", author: "r1", kind: "critique" as const, target: "c1", item: "k1" };
  assert.equal(ledger.latestSubmission(slot), undefined);
-  ledger.append("submission", { ...slot, version: 1, content: { target: "whole", body: "第一版" } });
-  const v2 = ledger.append("submission", { ...slot, version: 2, content: { target: "whole", body: "第二版" } });
-  ledger.append("submission", { ...slot, item: "k2", version: 1, content: { target: "p1", body: "另一份" } });
+  ledger.append("submission", { ...slot, version: 1, jev: null, content: { target: "whole", body: "第一版" } });
+  const v2 = ledger.append("submission", { ...slot, version: 2, jev: null, content: { target: "whole", body: "第二版" } });
+  ledger.append("submission", { ...slot, item: "k2", version: 1, jev: null, content: { target: "p1", body: "另一份" } });
  assert.deepEqual(ledger.latestSubmission(slot), v2);
  closeStage(ledger, "s1");
  assert.equal(ledger.stageClosed("s1"), true);