|
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 25s
- Output limits leave room for reasoning (answer plus 8k-64k by effort, up to the model maximum); a call cut off before answering is retried with double the limit. At "max" effort, batches were being cut off at 16k tokens. - Quizzes are planned first (one distinct angle per question), then written in waves of four batches; med math runs alongside the first wave. - Replacements for removed questions are planned and written in parallel. - The Python check and the second review run at the same time each round. Measured live (DeepSeek flash, max reasoning, 50 questions): 7 min 21 s with no duplicates, against 20 min and 29 replaced duplicates without planning. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> |
||
|---|---|---|
| .. | ||
| ai.test.ts | ||
| api.test.ts | ||
| hardening.test.ts | ||
| helpers.ts | ||
| migration.test.ts | ||
| mockAi.ts | ||
| ordering-deadlines.test.ts | ||
| python.test.ts | ||
| revision1.test.ts | ||
| revision2.test.ts | ||
| revision3.test.ts | ||
| revision4.test.ts | ||
| revision5.test.ts | ||
| semantic.test.ts | ||