mirror of
https://github.com/garrytan/gstack.git
synced 2026-10-10 21:18:47 +02:00
test: attribute quoted prior-record field lists, state the judge reason bound in its schema, move split-overflow to marathon
Census 36629958451 reds: - outside-plan-disabled-no-fallback: the model quoted the pre-existing record as a parenthesized field list with its exact timestamp; attribution now requires that exact timestamp and the record's own field values. - plan-devex-peer-comparison-classification: the judge correctly returned missing but wrote a 1069-character reason, voiding the judgment; structured outputs cannot enforce maxLength, so the bound is stated on the field. - plan-ceo-split-overflow ran 504-1188 s as one PTY flow and set the periodic lane's wall clock; it now runs weekly in the marathon lane.
This commit is contained in:
1 parent
f63e1fb7cb
commit
bf4667146c
6 files changed
+52
-8
No files matched your search
@@ -173,6 +173,24 @@ function withoutAttributedPriorRecordData(output: string, priorRecord?: Record<s
|
||||
spans.push({ start: match.index, end: match.index + match[0].length });
|
||||
}
|
||||
}
|
||||
// A parenthesized field list right after a pre-existing-record owner is that
|
||||
// record when it quotes the record's exact ISO timestamp and every other item
|
||||
// is one of its own field values; a current mutation before the owner fails.
|
||||
const owned = /\b(?:earlier|prior|previous|historical|old(?:er)?|pre[- ]existing)\s+(?:(?:review[- ]log|review|log)\s+)?(?:entry|record|line|row)\s*\(([^()\r\n]+)\)/gi;
|
||||
for (const match of output.matchAll(owned)) {
|
||||
const lineStart = output.lastIndexOf('\n', match.index) + 1;
|
||||
const local = output.slice(lineStart, match.index).split(/(?<=[.!?;])\s+/).at(-1) ?? '';
|
||||
if (/\b(?:now|currently|current|today|new|updat\w*|append\w*|chang\w*|mark\w*|set|write|wrote)\b/i.test(local.replace(/[*`]/g, ''))) continue;
|
||||
const items = match[1]!.split(',').map(item => item.replace(/[*`]/g, '').trim());
|
||||
const fieldsOk = items.every(item => {
|
||||
if (item === priorRecord.timestamp) return true;
|
||||
const field = /^["']?([a-z_]+)["']?\s*[:=]\s*["']?([a-z0-9_.:+-]+)["']?$/i.exec(item);
|
||||
return !!field && fields.has(field[1]!) && field[1] !== 'timestamp' && priorRecord[field[1]!] === field[2];
|
||||
});
|
||||
if (!fieldsOk || !items.includes(String(priorRecord.timestamp)) || !items.some(item => /^["']?outside_status\b/i.test(item))) continue;
|
||||
const start = match.index + match[0].length - match[1]!.length - 1;
|
||||
spans.push({ start, end: start + match[1]!.length + 2 });
|
||||
}
|
||||
for (const span of spans.sort((a, b) => b.start - a.start)) {
|
||||
output = output.slice(0, span.start) + output.slice(span.start, span.end).replace(/[^\r\n]/g, ' ') + output.slice(span.end);
|
||||
}
|
||||
|
||||
Reference in new issue
Block a user