InfoRSI/tests/flow-next-step.test.ts

import assert from "node:assert/strict";
import { readFileSync } from "node:fs";
import { join } from "node:path";
import { test } from "node:test";
import { stepList, type ResearchConfig } from "../src/config/index.ts";
import type { AppendKind, Content, LedgerRecord } from "../src/ledger/index.ts";
import type { StudyRecord } from "../src/materials/index.ts";
import { nextStep } from "../src/flow/next-step.ts";
import type { Json } from "../src/vocab/index.ts";
import { fullConfig } from "./config-helpers.ts";

// flow 的"下一步做什么"（任务书 12 第六部分）：纯函数，手写账本记录，看它给出的下一步。
// 其余都由真实运行证明（任务书 12 第五部分），这里不写假模型、假 Docker。

const TASK_FACTS = JSON.parse(readFileSync(join(import.meta.dirname, "..", "tasks", "circle_packing", "task.json"), "utf8")) as Json;
const HASH = "0".repeat(64);
const measured = (value: number) => ({ status: "measured", value }) as const;

/** 调用结束记录去掉调用编号（四种结局各自去掉）。 */
type Ended = Content<"callEnded"> extends infer E ? (E extends unknown ? Omit<E, "call"> : never) : never;

/** 一本手写的账本：按写入先后编序号。内容照账本的形状写，nextStep 不再检查。 */
class Book {
  readonly records: LedgerRecord[] = [];

  add<K extends AppendKind>(kind: K, content: Content<K>): this {
    this.records.push({ seq: this.records.length + 1, kind, hash: HASH, content } as LedgerRecord);
    return this;
  }

  config(config: ResearchConfig): this {
    const record: StudyRecord = {
      config: config as unknown as Json,
      steps: stepList(config) as unknown as Json,
      prompts: { roles: {} as StudyRecord["prompts"]["roles"], tasks: {} as StudyRecord["prompts"]["tasks"] },
      image: `sha256:${HASH}`,
      task: TASK_FACTS,
      seed: 1,
    };
    return this.add("config", record as unknown as Json);
  }

  baselineCode(): this {
    return this.add("code", { object: "base", version: "v-base", locations: null });
  }

  /** 一次基线运行：没启动，或启动了、判分算数或不算数。 */
  baselineRun(run: string, outcome: "notStarted" | "valid" | "invalid"): this {
    const definition: Content<"runPlanned">["definition"] = {
      command: ["python", "harness.py"],
      workdir: "/work",
      image: { digest: `sha256:${HASH}`, runtime: "runc" },
      wallSeconds: 120,
      cores: 1,
      inheritEnv: false,
      env: {},
    };
    this.add("runPlanned", { run, purpose: "baseline", round: 0, object: null, definition });
    if (outcome === "notStarted") {
      return this.add("runResult", { run, process: { ending: "notStarted", reason: "docker run 失败" }, judged: null });
    }
    this.add("runStarted", { run });
    const process = { ending: "exited", exitCode: 0, cpuSeconds: measured(10), wallSeconds: measured(10), peakMemoryBytes: measured(1) } as const;
    const judged = {
      verdict: outcome,
      verdictReason: outcome === "valid" ? "合法" : "不合法：圆重叠",
      score: measured(0.9597642169962064),
      metrics: {},
      answerPath: { status: "unmeasured", reason: "基线不写" },
      safeguardTriggers: { status: "unmeasured", reason: "基线不写" },
      extra: null,
    } as unknown as Content<"runResult">["judged"];
    return this.add("runResult", { run, process, judged });
  }

  open(stageId: string, stage: Content<"stageOpen">["stage"], roster: string[]): this {
    return this.add("stageOpen", { stageId, stage, round: 0, roster });
  }

  /** 一份被收下的提交。nextStep 只看这个人在这个阶段有没有被收下的提交，种类一律写成入口。 */
  entry(stageId: string, author: string): this {
    const content = { entries: [{ name: "入口一", body: "从这里开始看" }, { name: "入口二", body: "从那里开始看" }] };
    return this.add("submission", { stageId, author, target: null, item: null, version: 1, kind: "entry", content, jev: null });
  }

  /** 一次模型调用：开始和结束。 */
  call(stageId: string, actor: string, n: number, ended: Ended): this {
    const call = `${stageId}.${actor}.entry.none.${n}`;
    this.add("callStarted", { call, actor, stageId, model: "iomgaa/glm-5.3", materials: null });
    return this.add("callEnded", { call, ...ended } as Content<"callEnded">);
  }
}

const R = ["researcher-1", "researcher-2", "researcher-3"];

/** 冻结了配置、基线跑完算数的账本。 */
function afterBaseline(config: ResearchConfig = fullConfig()): Book {
  return new Book().config(config).baselineCode().baselineRun("base-1", "valid");
}

test("空账本：冻结配置", () => {
  assert.deepEqual(nextStep([]), { do: "freezeConfig" });
});

test("有配置、没有基线：先存基线代码，再用 base-1 跑基线", () => {
  const book = new Book().config(fullConfig());
  assert.deepEqual(nextStep(book.records), { do: "saveBaseline" });
  book.baselineCode();
  assert.deepEqual(nextStep(book.records), { do: "baselineRun", run: "base-1" });
});

test("基线最近一次是\"没启动\"：起新编号再跑", () => {
  const book = new Book().config(fullConfig()).baselineCode().baselineRun("base-1", "notStarted");
  assert.deepEqual(nextStep(book.records), { do: "baselineRun", run: "base-2" });
  book.baselineRun("base-2", "notStarted");
  assert.deepEqual(nextStep(book.records), { do: "baselineRun", run: "base-3" });
});

test("基线判为不算数：停下，原因写明", () => {
  const book = new Book().config(fullConfig()).baselineCode().baselineRun("base-1", "invalid");
  const next = nextStep(book.records);
  assert.equal(next.do, "halt");
  assert.match((next as { reason: string }).reason, /base-1 判为不算数（不合法：圆重叠）/);
});

test("基线算数之后：开写入口阶段，名单是全部研究者", () => {
  assert.deepEqual(nextStep(afterBaseline().records), { do: "openStage", stageId: "r0-entryDraft", stage: "entryDraft", roster: R });
});

test("阶段开着、一人已交、两人没交：派那两人", () => {
  const book = afterBaseline().open("r0-entryDraft", "entryDraft", R).entry("r0-entryDraft", "researcher-1");
  assert.deepEqual(nextStep(book.records), { do: "dispatch", stageId: "r0-entryDraft", kind: "entry", actors: ["researcher-2", "researcher-3"] });
});

test("都交了：关阶段；关了以后开第 1 次讨论", () => {
  const book = afterBaseline().open("r0-entryDraft", "entryDraft", R);
  for (const r of R) book.entry("r0-entryDraft", r);
  assert.deepEqual(nextStep(book.records), { do: "closeStage", stageId: "r0-entryDraft" });
  book.add("stageClose", { stageId: "r0-entryDraft" });
  assert.deepEqual(nextStep(book.records), { do: "openStage", stageId: "r0-discussion1", stage: "discussion", roster: R });
});

test("有人最近一次是\"没交\"：开发入口关着先派能派的、再停下；开着重新派", () => {
  const stuck = (devEntry: boolean) =>
    new Book()
      .config({ ...fullConfig(), devEntry })
      .baselineCode()
      .baselineRun("base-1", "valid")
      .open("r0-entryDraft", "entryDraft", R)
      .entry("r0-entryDraft", "researcher-1")
      .call("r0-entryDraft", "researcher-2", 1, { wallSeconds: measured(30), status: "notSubmitted", reason: "模型结束了回复，没有一份提交被收下" });
  // researcher-3 还没派过，先派他。
  assert.deepEqual(nextStep(stuck(false).records), { do: "dispatch", stageId: "r0-entryDraft", kind: "entry", actors: ["researcher-3"] });
  // researcher-3 交上以后只剩"没交"的 researcher-2：停下，附调用编号。
  const closed = stuck(false).entry("r0-entryDraft", "researcher-3");
  const next = nextStep(closed.records);
  assert.equal(next.do, "halt");
  assert.match((next as { reason: string }).reason, /^交不出合格提交/);
  assert.deepEqual((next as { objects: string[] }).objects, ["r0-entryDraft.researcher-2.entry.none.1"]);
  // 开发入口开着：重新派。
  const dev = stuck(true).entry("r0-entryDraft", "researcher-3");
  assert.deepEqual(nextStep(dev.records), { do: "dispatch", stageId: "r0-entryDraft", kind: "entry", actors: ["researcher-2"] });
});

test("有人最近一次是\"出错\"或\"进程中断\"：重新派；只看最近一次调用", () => {
  const book = afterBaseline()
    .open("r0-entryDraft", "entryDraft", R)
    .entry("r0-entryDraft", "researcher-1")
    .call("r0-entryDraft", "researcher-2", 1, { wallSeconds: measured(5), status: "notSubmitted", reason: "没交" })
    .call("r0-entryDraft", "researcher-2", 2, { wallSeconds: measured(5), status: "failed", reason: "模型服务报错" })
    .call("r0-entryDraft", "researcher-3", 1, { wallSeconds: { status: "unmeasured", reason: "进程中断" }, status: "failed", reason: "进程中断" });
  assert.deepEqual(nextStep(book.records), { do: "dispatch", stageId: "r0-entryDraft", kind: "entry", actors: ["researcher-2", "researcher-3"] });
});

test("只有一位研究者：两次讨论各写一条按配置跳过，接着开认领", () => {
  const one = fullConfig();
  one.models.researchers = [one.models.researchers[0]!];
  const book = afterBaseline(one).open("r0-entryDraft", "entryDraft", ["researcher-1"]).entry("r0-entryDraft", "researcher-1");
  book.add("stageClose", { stageId: "r0-entryDraft" });
  const reason = "只有一位研究者，第零轮不讨论（方法.md 4.2）";
  assert.deepEqual(nextStep(book.records), { do: "skip", step: "discussion1", reason });
  book.add("event", { event: "skippedByConfig", reason, objects: ["discussion1"] });
  assert.deepEqual(nextStep(book.records), { do: "skip", step: "discussion2", reason });
  book.add("event", { event: "skippedByConfig", reason, objects: ["discussion2"] });
  assert.deepEqual(nextStep(book.records), { do: "openStage", stageId: "r0-claim", stage: "claim", roster: ["researcher-1"] });
});

test("认领关了：分配；分配做完：停下，原因\"第 1 轮还没写\"", () => {
  const book = afterBaseline();
  const stages = [
    ["r0-entryDraft", "entryDraft"],
    ["r0-discussion1", "discussion"],
    ["r0-discussion2", "discussion"],
    ["r0-claim", "claim"],
  ] as const;
  for (const [stageId, stage] of stages) {
    book.open(stageId, stage, R);
    for (const r of R) book.entry(stageId, r);
    book.add("stageClose", { stageId });
  }
  assert.deepEqual(nextStep(book.records), { do: "assignEntries" });
  const output = R.map((researcher, i) => ({ researcher, entry: `e-${researcher}-1`, rank: i + 1 }));
  book.add("decision", { decision: "entries", round: 0, rule: "assignEntries", ruleVersion: 1, params: null, seed: null, input: null, output });
  assert.deepEqual(nextStep(book.records), { do: "halt", reason: "第 1 轮还没写（任务书 13）", objects: [] });
});