mirror of
https://github.com/garrytan/gstack.git
synced 2026-11-05 16:34:00 +01:00
Garry Tanandcapy-ai[bot]
6f7488a70f
* fix(evals): plan-design focus rating in plain words, docsync own-call rule at the candidate --help, floor Create menu cropped at its rule (GSTA-65) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): floor actor answers Step 0D's focus menu in the template's own words (GSTA-65) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): floor actor identifies Step 0D's focus menu by its structure, not one wording (GSTA-65) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * docs(changelog): GSTA-65 paid-side flaky repairs under [Unreleased] Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * fix(evals): the 0D focus picker moves into plan-design-finding-floor's owned fixture; no harness series reset (GSTA-65) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * test(evals): the 0D picker rows join the floor case's owner test (test-of-test ratchet) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> * v1.91.185.0 fix(evals): plan-design focus rating in plain words, docsync own-call rule, floor Create crop and 0D menu (GSTA-65) (#3358) Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com> --------- Co-authored-by: capy-ai[bot] <230910855+capy-ai[bot]@users.noreply.github.com>
36 lines
2.7 KiB
TypeScript
36 lines
2.7 KiB
TypeScript
/**
|
||
* Case-owned setup answer for test/skill-e2e-plan-design-finding-floor.test.ts.
|
||
* It lives with the case's fixtures so a change to it starts that case's own
|
||
* pass-rate series instead of every case's (scripts/eval-trial-series.ts).
|
||
*/
|
||
import type { NativePlanQuestionCall } from '../helpers/plan-count-transcript';
|
||
|
||
/**
|
||
* The seed declares "Design: review all seven dimensions" for the pending Step 0D
|
||
* focus menu. Pick its single all-seven option only when every other option
|
||
* narrows the review and the brief approves no product action.
|
||
*/
|
||
export function pickDesignFocusAll(q: NativePlanQuestionCall['questions'][number]): number | null {
|
||
if (q.multiSelect || q.options.length < 2 || q.options.length > 4 || new Set(q.options.map(o => o.label)).size !== q.options.length) return null;
|
||
const text = q.question.trim();
|
||
const unquote = (value: string) => value.replace(/`+[^`]*`+|"[^"\n]*"|“[^”\n]*”|‘[^’\n]*’/g, '');
|
||
const sources = [...text.matchAll(/^Project\/branch\/task:\s*([^\n]+)$/gm)].map(match => unquote(match[1]!));
|
||
const explanatory = unquote([text, ...q.options.flatMap(o => [o.label, o.description ?? ''])].join('\n')).replace(/[✅❌*]/g, '');
|
||
// The menu is identified by its structure, not one wording: a title or question about the
|
||
// focus ("Review all 7 design dimensions, or focus?", census 36597762183; "Want me to focus on
|
||
// specific areas instead?" and "Review focus for the landing page plan", GSTA-65 focused
|
||
// trials), one all-seven option, and only narrowing alternatives.
|
||
const sentences = text.split(/(?<=[.!?])\s+|\r?\n/);
|
||
const title = text.split(/\r?\n/, 1)[0]!.replace(/^D[1-9]\d*\s*[—–:-]\s*/i, '');
|
||
const asks = sentences.filter(sentence => sentence.includes('?'));
|
||
if (![title, ...asks].some(line => /\bfocus\b/i.test(line)) ||
|
||
sources.length !== 1 || !/\b(?:PLAN\.md|Marketing landing page)\b/i.test(sources[0]!) ||
|
||
/\b(?:historical|archived|quoted|example|foreign|other|another|previous)\b/i.test(sources[0]!) ||
|
||
(text.match(/\?/g)?.length ?? 0) > 1 || /```|~~~|^\s*>/m.test(text) ||
|
||
/(?:^|[.!?;:\n]|\b(?:and|while))\s*(?:(?:also|please|then|now)\s+)*(?:approv(?:e|ing)|deploy(?:ing)?|implement(?:ing)?|ship(?:ping)?|merg(?:e|ing)|delet(?:e|ing))\b/im.test(explanatory)) return null;
|
||
const labels = q.options.map(o => o.label.trim().replace(/^[A-Z][).:]\s+/i, '').replace(/\s*\(recommended\)\s*$/i, ''));
|
||
const all = labels.flatMap((label, i) => /^(?:Review )?All (?:7|seven) (?:design )?(?:dimensions|passes|areas)$/i.test(label) ? [i + 1] : []);
|
||
if (all.length !== 1 || labels.some((label, i) => i + 1 !== all[0] && !/^(?:Only|Focus)\b|\bonly$/i.test(label))) return null;
|
||
return all[0]!;
|
||
}
|