InfoRSI/tests/flow-docker.test.ts

import assert from "node:assert/strict";
import { spawnSync } from "node:child_process";
import { cpSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from "node:fs";
import { tmpdir } from "node:os";
import { join } from "node:path";
import { test, type TestContext } from "node:test";
import { lightChecker } from "../src/flow/task-code.ts";
import { recover } from "../src/flow/recover.ts";
import { containerName, freshDir, runPaths } from "../src/flow/paths.ts";
import type { Study } from "../src/flow/study.ts";
import { Board, protocolMetrics, type FrozenProtocol } from "../src/materials/index.ts";
import { loadTask, formalRun as runDefinition, prepareRun } from "../src/tasks/index.ts";
import { runBalance } from "../src/rules/index.ts";
import { runStudy } from "../src/flow/index.ts";
import { Ledger } from "../src/ledger/index.ts";
import { Runner } from "../src/runner/index.ts";
import { fullConfig } from "./config-helpers.ts";

// flow 碰到 Docker 的两处边界，用真实 Docker 测，不花模型的钱：走不到派模型任务就停下。
// 镜像一律 inforsi-test- 开头的固定名字；本机还有别的项目在建删容器和镜像，只动自己前缀的。

const TASK_DIR = join(import.meta.dirname, "..", "tasks", "circle_packing");

function docker(args: string[]): { status: number | null; stdout: string; stderr: string } {
  return spawnSync("docker", args, { encoding: "utf8" });
}

/** 删掉测试自己的镜像标签；不存在不算错，别的错误照样报。 */
function removeImage(tag: string): void {
  const removed = docker(["rmi", tag]);
  if (removed.status !== 0 && !removed.stderr.includes("No such image")) throw new Error(removed.stderr);
}

/** 一个测试用的研究编号：先清掉上次没删干净的同名镜像，测试结束后再删。 */
function studyId(t: TestContext, suffix: string): string {
  const id = `test-flow-${suffix}`;
  removeImage(`inforsi-${id}`);
  t.after(() => removeImage(`inforsi-${id}`));
  return id;
}

function tempDir(t: TestContext): string {
  const dir = mkdtempSync(join(tmpdir(), "inforsi-flow-"));
  t.after(() => rmSync(dir, { recursive: true, force: true }));
  return dir;
}

function ledgerKinds(studyDir: string): string[] {
  const ledger = Ledger.open(join(studyDir, "ledger.sqlite"));
  try {
    return ledger.records().map((r) => r.kind);
  } finally {
    ledger.close();
  }
}

test("研究编号本机用过（已有 inforsi-<研究编号> 镜像）：冻结配置前报错停下，不建镜像、不写研究配置记录", async (t) => {
  const id = studyId(t, "dup");
  // 一份旧研究冻结配置时建下的镜像。
  await new Runner(null).buildImage(TASK_DIR, `inforsi-${id}`);
  const dir = tempDir(t);
  await assert.rejects(
    runStudy({ studyDir: dir, config: { ...fullConfig(), studyId: id }, stop: new AbortController().signal }),
    new RegExp(`研究编号 ${id} 已被本机用过（已有镜像 inforsi-${id}）`),
  );
  assert.deepEqual(ledgerKinds(dir), []);
});

test("docker run 没启动：写结果\"没启动\"后停下，原因带 Docker 报错原文，不在本进程里起新编号重跑", { timeout: 120_000 }, async (t) => {
  // 任务事实里写一个本机没有的 Docker 运行时，docker run 每次都失败，也不建容器。
  const task = join(tempDir(t), "task");
  cpSync(TASK_DIR, task, { recursive: true });
  const facts = JSON.parse(readFileSync(join(task, "task.json"), "utf8")) as { run: { runtime: string } };
  facts.run.runtime = "inforsi-test-no-such-runtime";
  writeFileSync(join(task, "task.json"), JSON.stringify(facts));
  const dir = tempDir(t);
  const ending = await runStudy({
    studyDir: dir,
    config: { ...fullConfig(), studyId: studyId(t, "not-started"), task },
    stop: new AbortController().signal,
  });
  assert.equal(ending.status, "halted");
  assert.match((ending as { reason: string }).reason, /运行 base-1 没有启动.*unknown or invalid runtime name: inforsi-test-no-such-runtime/);
  assert.deepEqual(ledgerKinds(dir), ["config", "code", "runPlanned", "runResult", "event"]);
});


/** 不派模型，只接真实任务镜像、账本和运行器，检查 flow 的两处 Docker 接线。 */
async function runtimeStudy(t: TestContext, suffix: string): Promise<Study> {
  const dir = tempDir(t);
  const id = studyId(t, suffix);
  const task = loadTask(TASK_DIR);
  const runner = new Runner(null);
  const image = await runner.buildImage(task.dir, `inforsi-${id}`);
  const ledger = Ledger.open(join(dir, "ledger.sqlite"));
  t.after(() => ledger.close());
  return { dir, task, runner, ledger, stop: new AbortController().signal,
    frozen: { config: { ...fullConfig(), studyId: id, lightChecks: { maxCount: 1, seconds: 7 } }, facts: task.facts, image, seed: 1 } } as Study;
}

test("flow 轻量检查：每次调用各自限次和限时，真实 Docker 只检查当前目录，不登记正式运行", { timeout: 120_000 }, async (t) => {
  const s = await runtimeStudy(t, "light");
  const work = join(s.dir, "work");
  mkdirSync(work);
  writeFileSync(join(work, "initial.py"), "raise RuntimeError('不应执行候选代码')\ndef run_packing():\n    pass\n");
  for (const call of ["first-call", "second-call"]) {
    freshDir(join(s.dir, "calls", call));
    const check = lightChecker(s, call, work);
    const result = JSON.parse(await check());
    assert.deepEqual(result, { used: 1, maxCount: 1, seconds: 7, result: { passed: true } });
    assert.match(await check(), /已用完（上限 1 次）/);
    assert.equal(await s.runner.status(containerName(s.frozen.config.studyId, `${call}-check-1`)), "absent");
  }
  assert.deepEqual(s.ledger.records(), []);
});

test("正向恢复：接上原容器不重跑，补启动只扣一次，引用指标沿用原登记缺失作废规则", { timeout: 120_000 }, async (t) => {
  const s = await runtimeStudy(t, "forward-recover");
  const metric = { id: "old-c.required", meaning: "必测量", unit: "次", direction: "maximize" as const, howMeasured: "原登记定义", missing: "invalidateRun" as const };
  const original: FrozenProtocol = { round: 0, baseline: "base", proposals: [], factors: [], safeguards: [], metrics: { defined: [metric], reused: [] }, clauses: [], body: "登记" };
  const current: FrozenProtocol = { ...original, round: 1, metrics: { defined: [], reused: [metric.id] } };
  s.ledger.append("protocol", { candidate: "old-c", protocol: original });
  s.ledger.append("protocol", { candidate: "r1-c1", protocol: current });
  const board = new Board(s.ledger.records());
  const run = "forward-1";
  const paths = runPaths(s.dir, run);
  const definition = runDefinition(s.task, s.frozen.image, "1");
  s.ledger.append("runPlanned", { run, purpose: "forward", round: 1, object: "r1-c1", definition });
  freshDir(paths.base);
  prepareRun(s.task, s.task.baselineDir, freshDir(paths.run), protocolMetrics(board, current));
  const name = containerName(s.frozen.config.studyId, run);
  t.after(() => { const result = docker(["rm", "-f", name]); if (result.status !== 0 && !result.stderr.includes("No such container")) throw new Error(result.stderr); });
  assert.deepEqual(await s.runner.start(name, definition, paths.run), { started: true });
  // 中断点：容器已启动，账本还没写 runStarted。恢复不调用 formalRun，而是找到原容器等它。
  assert.equal(await recover(s), null);
  const records = s.ledger.records();
  assert.equal(records.filter((r) => r.kind === "runPlanned").length, 1);
  assert.equal(records.filter((r) => r.kind === "runStarted").length, 1);
  assert.equal(records.filter((r) => r.kind === "runResult").length, 1);
  const result = records.find((r) => r.kind === "runResult")!;
  if (result.kind !== "runResult") throw new Error("缺运行结果");
  assert.equal(result.content.judged!.verdict, "invalid");
  assert.match(result.content.judged!.verdictReason, /old-c.required/);
  assert.equal(result.content.judged!.metrics[metric.id]!.status, "unmeasured");
  assert.deepEqual(runBalance(13, new Board(records).runStates()), { charged: 1, reserved: 0, balance: 12 });
  assert.equal(await s.runner.status(name), "absent");
  assert.equal(await recover(s), null);
  assert.equal(s.ledger.records().length, records.length);
});