gstack/test/skill-e2e-plan-design-with-ui.test.ts

/**
 * /plan-design-review with UI scope (gate, paid, real-PTY).
 *
 * The exact UI-heavy plan is committed before the first model turn. Observe
 * an acknowledged Design focus/rating question and a subsequent review
 * question using the existing native counting driver. An initial target menu
 * or a no-UI early exit cannot satisfy this positive path. Option descriptions
 * are proposals, so mentioning "no UI scope" there is not an exit verdict.
 */

import { test } from 'bun:test';
import { PTY_MS } from './helpers/eval-budgets';
import { describeE2ETier } from './helpers/e2e-gate';
import { createDesignReviewPicker, DESIGN_BOARD_ACTOR_PROTOCOL } from './helpers/plan-review-board-feedback';
import * as fs from 'node:fs';
import * as path from 'node:path';
import {
  runPlanSkillCounting,
  type AskUserQuestionFingerprint,
} from './helpers/claude-pty-runner';

const describeE2E = describeE2ETier('gate');
const ROOT = path.resolve(import.meta.dir, '..');
const FIXTURE = path.join(ROOT, 'test', 'fixtures', 'plans', 'ui-heavy-feature.md');

const designFocusBoundary = (fp: AskUserQuestionFingerprint): boolean =>
  fp.nativeCall?.answered === true && !fp.nativeCall.failed && fp.nativeCall.questions.some(({ header, question, options }) => {
    const text = question.trim().replace(/^D\d+(?:\.\d+)?\s*[—–:-]\s*/i, '');
    // A target menu can mention a design system without reviewing this plan.
    // The source Step 0D question, or a native title (first line) that offers all
    // seven design dimensions/passes versus a focus, in any order or wording. The
    // count may be a numeral or a word; the title must name design, unless the
    // body carries the step's own design-completeness rating (run 39199692993).
    const title = text.split(/\r?\n/, 1)[0]!;
    // Step 0A's rating is a sentence that scores the plan's design out of 10,
    // however it is worded ("rated this plan 4/10 for design completeness", run
    // 39363705692; "This plan is a 3/10 on design completeness", the 0A example;
    // the ELI10 plain-words "I rated this plan 4/10 on design.", run 39852003387).
    const rated = (body: string) => body.split(/(?<=[.!?])\s+|\r?\n/).some(sentence =>
      /\bdesign\b/i.test(sentence) && /(?<![\d./])(?:10(?:\.0+)?|[0-9](?:\.\d+)?)\/10(?!\d|\.\d)/.test(sentence));
    // Runs 39298269902 a1/a2: a title that only names the focus ("Review focus.",
    // on one line before Project/branch/task:), with the step's own rating in the
    // body and an option that offers all seven dimensions against a narrower one.
    // The option leads with all seven, whatever it calls them ("All 7 areas", run 39363705692).
    // Run 40664336141 put the offer in the rated title instead ("Should I review all 7 areas
    // or focus on a few?") and lettered its options ("A) Review all 7 areas"). Either place
    // carries the offer; issue-numbered options are a finding, never Step 0D. Runs 41178131219
    // and 41186376825 lettered the leading option itself ("A) All 7 passes (recommended)").
    // Every captured Step 0D (ten calls, runs 39199692993 to 41414111284) set the native header chip
    // to "Focus", and no other captured question did; run 41414111284's label put the count second
    // ("Full review, all 7 (recommended)"). With that header, the rating and an all-7 option suffice.
    const lead = text.split(/\r?\n|\s+(?=Project\/branch\/task:)/, 1)[0]!;
    if (/^\s*focus\s*$/i.test(header ?? '') && rated(text) && options.length >= 2 && !issueLabeled(options)
      && options.some(({ label }) => /\ball (?:7|seven)\b/i.test(label))) return true;
    return /^I(?:['’]ve| have) rated this plan (?:10(?:\.0+)?|[0-9](?:\.\d+)?)\/10 on design completeness\.[\s\S]*\bWant me to focus on specific areas instead(?: of all (?:7|seven))?\?/i.test(text)
      || (/\ball (?:7|seven) (?:design )?(?:dimensions|passes)\b/i.test(title) && /\bfocus\b/i.test(title)
        && (/\bdesign\b/i.test(title) || rated(text.slice(title.length))) && /\?\s*$/.test(title))
      || (/\bfocus\b/i.test(lead) && rated(text) && options.length >= 2 && !issueLabeled(options)
        && (/\ball (?:7|seven)\s+[a-z]/i.test(lead) || options.some(({ label }) => /^\s*(?:[A-Z][).:]\s*)?all (?:7|seven)\s+[a-z]/i.test(label))));
  });

// Require a choice about the supplied UI, not a workflow offer after focus.
// The review labels each finding's options with its issue number and a letter
// ("3A", "3B"; review-sections.md), so a complete issue-labeled option set
// identifies a Design finding whatever vocabulary its title uses. Otherwise both
// the question and an offered remedy must describe concrete UI behavior.
const issueLabeled = (options: Array<{ label: string }>): boolean => {
  const labels = options.map(({ label }) => /^\s*(\d+)([A-Z])(?=[):.\s]|$)/.exec(label));
  return labels.length >= 2 && labels.every(Boolean)
    && new Set(labels.map(match => match![1])).size === 1
    && new Set(labels.map(match => match![2])).size === labels.length;
};
const uiChoice = /\b(?:hierarch(?:y|ies)|see first|layout|compos(?:e|ed|ition)|anchor|regions?|panels?|notifications?|activity|quick actions?|loading|skeletons?|empty|errors?|success|modals?|toasts?|buttons?|links?|copy|typography|fonts?|spacing|contrast|colors?|breakpoints?|responsive|keyboard|focus (?:order|trap|management)|aria|a11y|accessibility)\b/i;
const designReviewFinding = (fp: AskUserQuestionFingerprint): boolean =>
  fp.nativeCall?.answered === true && !fp.nativeCall.failed && !designFocusBoundary(fp) && fp.nativeCall.questions.some(({ question, options }) => {
    const title = question.split(/\r?\n/, 1)[0]!.trim().replace(/^D\d+(?:\.\d+)?\s*[—–:-]\s*/i, '');
    const setup = /\b(?:outside (?:design )?voices|cross[ -]project learnings|review (?:target|scope|mode)|what should I (?:design[ -])?review|which (?:artifact|plan|file))\b/i;
    return !setup.test(title) && (issueLabeled(options)
      || (uiChoice.test(title) && options.some(option => uiChoice.test(`${option.label} ${option.description}`))));
  });

describeE2E('/plan-design-review with UI scope (gate)', () => {
  test(
    'reviews the supplied UI plan through an acknowledged Design finding',
    async () => {
      const startedAt = Date.now();
      const plan = fs.readFileSync(FIXTURE, 'utf8');
      let picker: ReturnType<typeof createDesignReviewPicker> | undefined;
      let pickerCwd: string | undefined;
      const obs = await runPlanSkillCounting({
        skillName: 'plan-design-review', slashCommand: '/plan-design-review',
        followUpPrompt: ['Review the supplied UI plan in review-input.md. Read it before',
          'choosing review scope.', '', plan, '', DESIGN_BOARD_ACTOR_PROTOCOL].join('\n'),
        fixtureFiles: {'review-input.md': plan},
        isLastStep0AUQ: designFocusBoundary,
        isReviewAUQ: designReviewFinding,
        reviewCountCeiling: 1,
        observeSetupQuestions: true,
        bindDesignBoardState: true,
        pickAUQ: (_routing, active, context) => {
          const call = active.nativeCall;
          const index = active.nativeQuestionIndex ?? (call?.questions.length === 1 ? 0 : -1);
          if (!call && (/\/boards\//.test(active.promptSnippet) || active.options.some(option => /\bSubmitted\b/.test(option.label)))) {
            throw new Error('Design board choice requires an owned native question');
          }
          if (!call || call.answered || call.failed || index < 0 || !call.questions[index]) return null;
          if (pickerCwd && pickerCwd !== context.cwd) throw new Error('Design board picker fixture changed');
          pickerCwd = context.cwd;
          picker ??= createDesignReviewPicker(context);
          const question = call.questions[index];
          return picker({...question, multiSelect: question.multiSelect ?? false,
            options: question.options.map(option => ({...option, description: option.description ?? ''}))});
        },
        timeoutMs: 600_000 - (Date.now() - startedAt),
      });
      const focus = obs.fingerprints.findIndex(designFocusBoundary);
      const postFocus = focus >= 0 && obs.fingerprints.slice(focus + 1).some(fp => !fp.preReview && designReviewFinding(fp));
      if (obs.outcome !== 'ceiling_reached' || !postFocus) {
        throw new Error(
          `plan-design-review with UI scope FAILED: outcome=${obs.outcome}; no acknowledged Design focus and subsequent review question\n` +
          `--- evidence (last 3KB) ---\n${obs.evidence}`,
        );
      }
    },
    PTY_MS,
  );
});