feat: flow 第 1 部分（骨架、研究开始、第零轮）与第零轮检验

按任务书 12 实现 src/flow：从账本现算下一步的纯函数、主循环、恢复入口、派模型任务和跑正式运行两个共用动作、冻结配置、基线、第零轮三个研究者阶段和入口分配，走到第 1 轮时停下。materials 导出 finalEntries、加 researcherId 和 StudyRecord。审阅采纳两条：研究编号本机已用过时冻结前报错；docker run 没启动时写完结果就停下，不在本进程里无限起新编号。 eval/ 新增第零轮检验：起研究命令行、回放假模型、检验用 Jev 客户端、六问质量评估、16-real-1 回放、杀进程与两份同时跑。tsc 与 depcruise 也检查 eval/，新增 eval 只经 index.ts 用正式代码的规则。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-10-03 10:58:52 -04:00
parent 8491191a2b
commit 75d7cffd27
36 changed files with 2456 additions and 14 deletions
@@ -0,0 +1,121 @@
+import { runSession, type KindOf, type SessionEnding, type SubmitAttempt, type SubmitReceipt } from "../agents/index.ts";
+import { buildMaterial, callId, queryMaterial, researcherId, type TaskMaterial } from "../materials/index.ts";
+import { receive, type Incoming, type KnownOf } from "../submissions/index.ts";
+import type { JevJudgment, Json, Submission } from "../vocab/index.ts";
+import { checkoutVersion } from "../workspace/index.ts";
+import { callPaths, freshDir, workspaceRepo } from "./paths.ts";
+import type { Study } from "./study.ts";
+
+// 共用动作一：派一个模型任务（任务书 12 第 2.6 节）。先写"模型调用开始"（材料整份存进去），再开会话，
+// 最后写"模型调用结束"，前后顺序由这个入口保证（方法.md 第九部分"先登记、再执行、再登记结果"）。
+// 提交收不收只由 submissions 判；形状不合格的由 agents 报上来，这里直接记退回（"给 flow"）。
+
+/** 一个研究者任务：哪种提交、谁、哪个阶段、对象；known 是交上来之后才知道的东西（submissions 的 KnownOf）。 */
+export type ModelTask<K extends KindOf<"researcher">> = {
+  kind: K;
+  actor: string;
+  stageId: string;
+  object: string | null;
+  known(content: Submission<K>): KnownOf<K>;
+};
+
+/** 派一次任务，等会话结束，交回调用编号和结局。 */
+export async function runModelTask<K extends KindOf<"researcher">>(s: Study, t: ModelTask<K>): Promise<{ call: string; ending: SessionEnding }> {
+  const { ledger } = s;
+  const started = new Set(ledger.records().flatMap((r) => (r.kind === "callStarted" ? [r.content.call] : [])));
+  let attempt = 1;
+  while (started.has(callId(t.stageId, t.actor, t.kind, t.object, attempt))) attempt++;
+  const call = callId(t.stageId, t.actor, t.kind, t.object, attempt);
+  const paths = callPaths(s.dir, call);
+  const material = buildMaterial({
+    kind: t.kind,
+    actor: t.actor,
+    stageId: t.stageId,
+    object: t.object,
+    ledger,
+    study: s.facts,
+    prompts: s.prompts,
+    codeRoot: paths.code,
+    changes: null,
+    artifacts: null,
+  });
+  const model = researcherModel(s, t.actor);
+  // 先登记、后建目录：调用编号只在登记之后才算用掉，被杀在两者之间时下次的编号不会撞上旧目录。
+  ledger.append("callStarted", {
+    call,
+    actor: t.actor,
+    stageId: t.stageId,
+    model: `${model.provider}/${model.model}（思考档位 ${model.thinking}）`,
+    materials: material as unknown as Json,
+  });
+  freshDir(paths.base);
+  freshDir(paths.code);
+  for (const r of material.readable) checkoutVersion(workspaceRepo(s.dir), r.version, freshDir(r.dir));
+  let reply = 0;
+  const outcome = await runSession({
+    role: "researcher",
+    model,
+    systemPrompt: s.prompts.roles.researcher.text,
+    firstMessage: material.firstMessage,
+    workDir: freshDir(paths.work),
+    sessionDir: freshDir(paths.sessions),
+    kind: t.kind,
+    readableDirs: material.readable.map((r) => r.dir),
+    query: (ref) => queryMaterial(material, ref),
+    submit: (attempt) => submit(s, t, material, attempt as SubmitAttempt<K>),
+    usage: (usage) => void ledger.append("callUsage", { call, reply: ++reply, usage }),
+    writeNote: (body) => void ledger.append("note", { author: t.actor, body }),
+    stop: s.stop,
+  });
+  // 会话文件就在这次调用的 sessions 目录里，不另记。
+  const { wallSeconds, sessionFile: _sessionFile, ...ending } = outcome;
+  ledger.append("callEnded", { call, wallSeconds: { status: "measured", value: wallSeconds }, ...ending });
+  return { call, ending };
+}
+
+/** 研究者用的模型：第 i 位研究者（researcherId(i)）用配置里第 i 个。 */
+function researcherModel(s: Study, actor: string) {
+  const models = s.frozen.config.models.researchers;
+  const i = models.findIndex((_, k) => researcherId(k) === actor);
+  if (i < 0) throw new Error(`${actor} 不是这份研究的研究者`);
+  return models[i]!;
+}
+
+/**
+ * 一份提交收不收。这个任务只有一份提交（第零轮每人每阶段一个任务、一份提交）：
+ * 回给模型的提交编号就是这一份的位置，不分版本；替换时写它，接在最新一版后面。
+ * 第一次交以后不写 replaces 又交，或 replaces 写的不是这一份，都退回并说明该怎么写。
+ */
+async function submit<K extends KindOf<"researcher">>(s: Study, t: ModelTask<K>, material: TaskMaterial, attempt: SubmitAttempt<K>): Promise<SubmitReceipt> {
+  const { ledger } = s;
+  const slot = { stageId: t.stageId, author: t.actor, kind: t.kind, target: t.object, item: null };
+  const reject = (submitted: Json, reason: string, jev: JevJudgment[] | null): SubmitReceipt => {
+    ledger.append("rejection", { stageId: t.stageId, author: t.actor, kind: t.kind, target: t.object, submitted, reason, jev });
+    return { accepted: false, reason };
+  };
+  if (attempt.shape === "invalid") return reject(attempt.raw, attempt.reason, null);
+  const id = receiptId(t);
+  const latest = ledger.latestSubmission(slot)?.content.version ?? 0;
+  const content = attempt.content as unknown as Json;
+  if (attempt.replaces === null && latest > 0) {
+    return reject(content, `本阶段你已经交过这一份（提交编号 ${id}）。要改就在 replaces 里写 ${id} 整份替换，不要另交`, null);
+  }
+  if (attempt.replaces !== null && (attempt.replaces !== id || latest === 0)) {
+    const which = latest === 0 ? "你本阶段还没有收下的提交，第一次交时不要带 replaces" : `要替换就写 ${id}`;
+    return reject(content, `replaces 写的 ${attempt.replaces} 不是你本阶段交过的提交：${which}`, null);
+  }
+  const verdict = await receive({
+    kind: t.kind,
+    content: attempt.content,
+    checklist: material.checklist,
+    known: t.known(attempt.content),
+    jevModel: s.frozen.config.models.jev,
+  } as Incoming);
+  if (!verdict.accepted) return reject(content, verdict.reason, verdict.jev);
+  ledger.append("submission", { ...slot, version: latest + 1, content: attempt.content, jev: verdict.jev } as never);
+  return { accepted: true, id };
+}
+
+/** 回给模型的提交编号：阶段、本人、提交种类、对象。 */
+const receiptId = (t: { stageId: string; actor: string; kind: string; object: string | null }): string =>
+  `${t.stageId}.${t.actor}.${t.kind}.${t.object ?? "none"}`;