InfoRSI/eval/lib/forward.ts

import { writeFileSync } from "node:fs";
import { checkConfig } from "../../src/config/index.ts";
import type { LedgerRecord } from "../../src/ledger/index.ts";
import {
  Board,
  FORWARD_NOT_RUN,
  type StudyRecord,
} from "../../src/materials/index.ts";
import { placement, runBalance } from "../../src/rules/index.ts";
import { verificationOutcome } from "../../src/submissions/index.ts";
import type { Range } from "../../src/vocab/index.ts";
import { finalSubmissions, ofKind } from "./ledger.ts";

export const FORWARD_STOP = "消融还没写（任务书 17）";
export const jsonFile = (path: string, value: unknown): void =>
  writeFileSync(path, `${JSON.stringify(value, null, 2)}\n`);
export const frozenConfig = (records: LedgerRecord[]) =>
  checkConfig((ofKind(records, "config")[0]!.content as StudyRecord).config);

/** 区间边界只是报告口径，不参与研究决定；失败或测不到分数保持 null。 */
export function scoreBand(score: number | null, range: Range): string | null {
  if (score === null) return null;
  return {
    belowQ1: "<q1",
    q1ToQ5: "[q1,q5)",
    q5ToQ9: "[q5,q9]",
    aboveQ9: ">q9",
  }[placement(range, score)];
}

/** 核验要对应当时那版代码，不能拿最终修好后的代码替代历史被审代码。 */
export function candidateHistory(records: LedgerRecord[], candidate: string) {
  const code = ofKind(records, "code").filter(
    (r) => r.content.object === candidate,
  );
  const submissions = ofKind(records, "submission").filter(
    (r) => r.content.target === candidate,
  );
  const attempts = submissions.flatMap((r) => {
    if (r.content.kind !== "implementation" && r.content.kind !== "repair")
      return [];
    // flow 在同一事务里先写 submission，紧接着写 code。
    return [{ submission: r, code: code.find((c) => c.seq === r.seq + 1)! }];
  });
  const verifications = submissions.flatMap((r) =>
    r.content.kind === "verification"
      ? [
          {
            submission: r,
            code: code.filter((c) => c.seq < r.seq).at(-1)!,
            outcome: verificationOutcome(r.content.content),
          },
        ]
      : [],
  );
  return { attempts, verifications };
}

/** 程序验收只读记录重算；基线也算正式运行，没启动的结果不扣次。 */
export function forwardAccounts(records: LedgerRecord[]) {
  const board = new Board(records);
  const config = frozenConfig(records);
  const opens = ofKind(records, "stageOpen");
  const closes = ofKind(records, "stageClose");
  const stages = opens.map((r) => {
    const closing = closes.filter(
      (c) => c.content.stageId === r.content.stageId,
    );
    return {
      ...r.content,
      openSeq: r.seq,
      closeSeqs: closing.map((c) => c.seq),
      pass: closing.length === 1 && closing[0]!.seq > r.seq,
    };
  });
  const orphanCloses = closes.filter(
    (c) => !opens.some((o) => o.content.stageId === c.content.stageId),
  );
  const started = ofKind(records, "runStarted");
  const balance = runBalance(config.runs, board.runStates());
  const runs = ofKind(records, "runPlanned").map((p) => ({
    plan: p,
    starts: started.filter((s) => s.content.run === p.content.run),
    results: ofKind(records, "runResult").filter(
      (r) => r.content.run === p.content.run,
    ),
  }));
  const batch = board.decision("batch", 1);
  const finals = finalSubmissions(records);
  const candidates = (batch?.output.chosen ?? []).map((candidate) => {
    const history = candidateHistory(records, candidate);
    const events = ofKind(records, "event").filter(
      (r) =>
        r.content.event === FORWARD_NOT_RUN &&
        r.content.objects.includes(candidate),
    );
    const candidateRuns = runs.filter(
      (r) =>
        r.plan.content.purpose === "forward" &&
        r.plan.content.round === 1 &&
        r.plan.content.object === candidate,
    );
    const verificationCount = finals.filter(
      (r) =>
        r.content.target === candidate && r.content.kind === "verification",
    ).length;
    const repairCount = finals.filter(
      (r) => r.content.target === candidate && r.content.kind === "repair",
    ).length;
    const lastPassed = history.verifications.at(-1)?.outcome.passed ?? null;
    const exhausted = lastPassed === false && repairCount >= config.maxRepairs;
    return {
      candidate,
      verificationCount,
      repairCount,
      lastPassed,
      exhausted,
      notRunEvents: events,
      started: candidateRuns.some((r) => r.starts.length > 0),
      runs: candidateRuns,
      pass: exhausted
        ? events.length === 1 && candidateRuns.length === 0
        : lastPassed === true &&
          candidateRuns.some(
            (r) => r.starts.length === 1 && r.results.length === 1,
          ),
    };
  });
  const adoption =
    ofKind(records, "decision").find(
      (r) => r.content.decision === "adopt" && r.content.round === 1,
    ) ?? null;
  const halt =
    ofKind(records, "event")
      .filter((r) => r.content.event === "halted")
      .at(-1) ?? null;
  const checks = {
    stagesPaired: stages.every((s) => s.pass) && orphanCloses.length === 0,
    chargedOnce:
      balance.charged === started.length &&
      config.runs - balance.balance === started.length &&
      balance.reserved === 0,
    forwardSerial: runs
      .filter((r) => r.plan.content.purpose === "forward")
      .every(
        (r, i, forwards) =>
          i === 0 ||
          (forwards[i - 1]!.results.length === 1 &&
            forwards[i - 1]!.results[0]!.seq < r.plan.seq),
      ),
    runsFinished: runs.length > 0 && runs.every((r) => r.results.length === 1),
    candidatesFinished:
      candidates.length > 0 && candidates.every((c) => c.pass),
    adoptedAndStopped:
      adoption !== null &&
      halt?.content.reason === FORWARD_STOP &&
      halt.seq === records.at(-1)!.seq,
  };
  return {
    initial: config.runs,
    confirmedStarts: started.length,
    balance,
    runs,
    candidates,
    stages,
    orphanCloses,
    adoption,
    halt,
    checks,
  };
}