voyage/lib/verification/regression-check.mjs

#!/usr/bin/env node
// lib/verification/regression-check.mjs
// K10 at execution time: run ONE step's `Regression:` command through the
// criteria runner's own screens, before the step's checkpoint.
//
//   node lib/verification/regression-check.mjs --plan <plan.md> --step <N> [--cwd <dir>] [--json]
//     0 = the step's `Regression:` passed, or the step has no `Regression:`
//         field (`status: "absent"` — nothing new happens, K10)
//     1 = it failed, the executor denylist blocked it, or it is not runnable
//         (no command, or a command outside the test-runner allowlist): the
//         step is not done, and that is a finding for the fix rounds
//     2 = could not run: bad usage, a plan that cannot be read, no step N, or
//         a runner that could not start (not installed): nothing was measured,
//         as red-proof and done-line say for the same case
//   JSON on stdout: {step, status, progress_status, command, exit_code, output}
//     status: passed | failed | blocked | unrunnable | absent | error
//     progress_status: the value progress.json takes for steps.N.regression
//       (blocked counts as unrunnable, error as not-run), so the executor
//       copies one field and never translates
//
// The command is the field's first backticked span — the same reading as the
// runner's `## Verification` bullets — and it goes through the same two
// screens: the allowlist of test runners, then the plugin's PreToolUse
// denylist. The plan validator rejects a `Regression:` that cannot run once K10
// is in it (wave 2, order 9); this is the run-time check, so a plan validated
// before that is never read as green.
//
// The runner reports `exitCode`; this CLI writes `exit_code`, the key
// progress.json uses (C15). Nothing else is translated.
//
// The command runs exactly as the runner runs a criterion: its own run, with
// no shell and without NODE_TEST_CONTEXT (criteria-runner.mjs `runCommand`).
// This file had a copy of that code, and a fix made in one copy would have
// left K10 regressions running differently from Phase 7 criteria (release
// review of 6.3.0, round 5).

import { readFileSync, realpathSync } from 'node:fs';
import { resolve } from 'node:path';
import { fileURLToPath } from 'node:url';
import { sliceSteps, parseStepFields } from '../parsers/plan-schema.mjs';
import { firstCommand, runCriteria } from './criteria-runner.mjs';

export const REGRESSION_FIELD = 'Regression';
const EXIT = Object.freeze({ passed: 0, absent: 0, failed: 1, blocked: 1, unrunnable: 1, error: 2 });
const PROGRESS = Object.freeze({ passed: 'passed', absent: 'absent', failed: 'failed', blocked: 'unrunnable', unrunnable: 'unrunnable', error: 'not-run' });
const withProgress = (r) => ({ ...r, progress_status: PROGRESS[r.status] ?? 'not-run' });

/**
 * @param {{ planText: string, step: number, cwd?: string, run?: Function }} o
 * @returns {{ step: number, status: string, command: string|null, exit_code: number|null, output: string, exit: 0|1|2 }}
 */
export function checkRegression({ planText, step, cwd = process.cwd(), run = (c, o) => runCriteria(c, o) }) {
  const base = { step, command: null, exit_code: null, output: '' };
  const found = sliceSteps(planText).find((s) => Number(s.n) === step);
  if (!found) return withProgress({ ...base, status: 'error', output: `no "### Step ${step}:" in the plan`, exit: EXIT.error });
  const field = parseStepFields(found.body).get(REGRESSION_FIELD);
  if (!field) return withProgress({ ...base, status: 'absent', output: 'no Regression: field — nothing to run', exit: EXIT.absent });
  const { command, reason } = firstCommand(field.text);
  const [r] = run([{ label: `R${step}`, text: field.text, command, reason }], { cwd });
  // A runner that could not start measured nothing: not a red suite (round 6).
  const status = r.startError ? 'error' : r.status;
  return withProgress({
    step,
    status,
    command: r.command ?? null,
    exit_code: r.exitCode ?? null,
    output: r.output ?? '',
    exit: EXIT[status] ?? EXIT.error,
  });
}

export function main(argv) {
  let plan; let step; let cwd = process.cwd(); let asJson = false;
  for (let i = 0; i < argv.length; i++) {
    const a = argv[i];
    if (a === '--plan' && argv[i + 1]) plan = argv[++i];
    else if (a === '--step' && argv[i + 1]) step = Number(argv[++i]);
    else if (a === '--cwd' && argv[i + 1]) cwd = resolve(argv[++i]);
    else if (a === '--json') asJson = true;
    else {
      process.stderr.write(`regression-check: unknown argument ${a}\n`);
      return 2;
    }
  }
  const say = (r) => {
    const { exit, ...rest } = r;
    process.stdout.write(asJson ? `${JSON.stringify(rest)}\n`
      : `regression step ${rest.step}: ${rest.status}${rest.command ? ` — \`${rest.command}\`` : ''}${rest.exit_code === null ? '' : ` (exit ${rest.exit_code})`}\n`);
    return exit;
  };
  if (!plan || !Number.isInteger(step) || step < 1) {
    process.stderr.write('Usage: regression-check.mjs --plan <plan.md> --step <N> [--cwd <dir>] [--json]\n');
    return 2;
  }
  let planText;
  try { planText = readFileSync(plan, 'utf8'); } catch (e) {
    return say(withProgress({ step, status: 'error', command: null, exit_code: null, output: `cannot read ${plan}: ${e.message}`, exit: 2 }));
  }
  return say(checkRegression({ planText, step, cwd }));
}

function isMain() {
  try {
    return realpathSync(process.argv[1]) === realpathSync(fileURLToPath(import.meta.url));
  } catch {
    return false;
  }
}

if (isMain()) process.exitCode = main(process.argv.slice(2));