eval: 准备正向采纳的真实运行恢复与质量评估

新增单份串行启动入口、首个正向运行杀进程恢复证据、逐候选审阅导出与账目统计；参考只读副本分数对照。456项免费测试通过，尚未启动三份真实验收。同步结构说明与当前工作状态。

eval/forward/export.ts

@@ -0,0 +1,132 @@
+import { mkdirSync, writeFileSync } from "node:fs";
+import { join, resolve } from "node:path";
+import {
+  Board,
+  protocolMetrics,
+  type TaskMaterial,
+} from "../../src/materials/index.ts";
+import { checkoutVersion, compareVersions } from "../../src/workspace/index.ts";
+import { candidateHistory, jsonFile } from "../lib/forward.ts";
+import { ofKind, readLedger } from "../lib/ledger.ts";
+
+// 任务书16五项质量评估的候选审阅材料；不判路线、不代替全新上下文逐条阅读。
+// node eval/forward/export.ts <研究目录> <全新绝对输出目录>
+const [study, output, ...extra] = process.argv.slice(2);
+if (!study || !output || extra.length || output !== resolve(output))
+  throw new Error(
+    "用法：node eval/forward/export.ts <研究目录> <全新绝对输出目录>",
+  );
+mkdirSync(output); // 不覆盖以前的审阅材料。
+const records = readLedger(study);
+const board = new Board(records);
+const repo = join(study, "repo.git");
+const batch = board.decision("batch", 1)!;
+const baseline = board.code(board.baselineOf(1));
+const plans = ofKind(records, "runPlanned").filter(
+  (p) => p.content.round === 1 && p.content.purpose === "forward",
+);
+const index = [];
+for (const candidate of batch.output.chosen) {
+  const dir = join(output, candidate);
+  mkdirSync(dir);
+  const history = candidateHistory(records, candidate);
+  const candidatePlans = plans.filter((p) => p.content.object === candidate);
+  const started = candidatePlans.filter((p) =>
+    ofKind(records, "runStarted").some((s) => s.content.run === p.content.run),
+  );
+  const protocol = ofKind(records, "protocol")
+    .filter((p) => p.content.candidate === candidate)
+    .at(-1)!;
+  jsonFile(join(dir, "protocol.json"), {
+    record: protocol,
+    resolvedMetrics: protocolMetrics(board, board.protocol(candidate)),
+  });
+  mkdirSync(join(dir, "baseline"));
+  checkoutVersion(repo, baseline.version, join(dir, "baseline"));
+  for (const attempt of history.attempts) {
+    const path = join(dir, `code-${attempt.code.seq}`);
+    mkdirSync(path);
+    checkoutVersion(repo, attempt.code.content.version, path);
+    jsonFile(
+      join(dir, `changes-${attempt.code.seq}.json`),
+      compareVersions(repo, baseline.version, attempt.code.content.version),
+    );
+  }
+  // 首轮里每个候选只正式跑一个已通过版本；无启动的候选仍导出历史，但不冒称有最终通过代码。
+  const firstRun = started[0];
+  const finalCode =
+    firstRun === undefined
+      ? null
+      : ofKind(records, "code")
+          .filter((c) => c.content.object === candidate && c.seq < firstRun.seq)
+          .at(-1)!;
+  if (finalCode !== null) {
+    mkdirSync(join(dir, "final"));
+    checkoutVersion(repo, finalCode.content.version, join(dir, "final"));
+  }
+  const finalAttempt =
+    finalCode === null
+      ? null
+      : history.attempts.find((a) => a.code.seq === finalCode.seq)!;
+  jsonFile(join(dir, "final-implementation.json"), finalAttempt);
+  jsonFile(join(dir, "attempts.json"), history.attempts);
+  jsonFile(join(dir, "verifications.json"), history.verifications);
+  const calls = ofKind(records, "callStarted").filter((c) => {
+    const material = c.content.materials as TaskMaterial;
+    return (
+      material.object === candidate &&
+      ["implementation", "repair", "verification"].includes(material.kind)
+    );
+  });
+  jsonFile(
+    join(dir, "calls.json"),
+    calls.map((c) => ({
+      record: c,
+      sessions: join(study, "calls", c.content.call, "sessions"),
+    })),
+  );
+  jsonFile(
+    join(dir, "rejections.json"),
+    ofKind(records, "rejection").filter(
+      (r) =>
+        r.content.target === candidate &&
+        ["implementation", "repair", "verification"].includes(r.content.kind),
+    ),
+  );
+  const manifest = {
+    study,
+    candidate,
+    protocolSeq: protocol.seq,
+    baselineVersion: baseline.version,
+    finalCode,
+    ran: started.length > 0,
+    runs: candidatePlans.map((p) => ({
+      plan: p,
+      result:
+        ofKind(records, "runResult").find(
+          (r) => r.content.run === p.content.run,
+        ) ?? null,
+      artifacts: join(study, "runs", p.content.run),
+    })),
+  };
+  jsonFile(join(dir, "manifest.json"), manifest);
+  writeFileSync(
+    join(dir, "review.txt"),
+    `任务书16第3.2节：只读本候选，分两步评估，中文直接回复，不写文件。\n` +
+      `第一步只读 protocol.json（冻结协议全文及引用指标原定义）、baseline/、final/、final-implementation.json（正文、位置表、concerns）。\n` +
+      `逐条实现条款、因子、保障检查漏做、协议之外的改进、位置表是否准确，每条附代码文件和行号。先形成独立结论，再打开核验历史。\n` +
+      `第二步读 verifications.json、attempts.json、code-<序号>/、changes-<序号>.json；每次核验对照其中code指向的那一版，不拿最终修好版本倒判历史。判断该拒却通过、不该拒却拒绝；修复是否只改指出处。\n` +
+      `需要时读 calls.json 和 rejections.json；模型材料和原始会话都可追溯。不把提交格式退回当成核验失败。\n` +
+      `答案路径只核对每个可能交出最终答案分支的标签，不预测实际走哪个分支。报告先写实现忠实度，再写逐次核验误判和修复范围。\n` +
+      `按任务书15附录一路线代号归类冻结协议，另标是否完整高上限路线（起点、连续改进全部圆、多起点或扰动、合法收尾），附协议原文位置。\n` +
+      `本候选${manifest.ran ? "已启动正式运行" : "未启动正式运行；没有final/，只评历史，不列成跑过的候选"}。\n`,
+  );
+  index.push({
+    candidate,
+    ran: manifest.ran,
+    directory: dir,
+    finalVersion: finalCode?.content.version ?? null,
+  });
+}
+jsonFile(join(output, "index.json"), index);
+console.log(`候选审阅包：${output}`);