Study/tests
Elijah 2454ab6e95
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 25s
Faster quiz generation: planned parallel batches, room to reason
- 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>
2026-11-16 11:00:27 -07:00
..
ai.test.ts Faster quiz generation: planned parallel batches, room to reason 2026-11-16 11:00:27 -07:00
api.test.ts First revision: DeepSeek, numeric questions, background assistant, UI fixes 2026-11-15 12:48:17 -07:00
hardening.test.ts Verify V1 scheduling and static boundaries; record Terra workflow and visual QA 2026-11-11 19:36:24 -07:00
helpers.ts Add HTTP routes, app wiring, V1 migration, backups, templates and API tests 2026-11-11 08:22:47 -07:00
migration.test.ts Verify V1 scheduling and static boundaries; record Terra workflow and visual QA 2026-11-11 19:36:24 -07:00
mockAi.ts Faster quiz generation: planned parallel batches, room to reason 2026-11-16 11:00:27 -07:00
ordering-deadlines.test.ts Add drag reordering, exam deadlines, frozen shared quizzes, batched OCR and semantic search 2026-11-12 11:48:20 -07:00
python.test.ts Add sandboxed Python for the assistant and a Python check of generated quizzes 2026-11-15 13:03:24 -07:00
revision1.test.ts First revision: DeepSeek, numeric questions, background assistant, UI fixes 2026-11-15 12:48:17 -07:00
revision2.test.ts Share-link generation and med math on request 2026-11-15 22:04:08 -07:00
revision3.test.ts Third revision: web search, MCP sign-in, exams, intelligent UI, clarifying questions 2026-11-15 20:30:00 -07:00
revision4.test.ts Fifth revision: share-link AI safety, sturdier generation, cleaner UI 2026-11-16 09:17:50 -07:00
revision5.test.ts Faster quiz generation: planned parallel batches, room to reason 2026-11-16 11:00:27 -07:00
semantic.test.ts Add drag reordering, exam deadlines, frozen shared quizzes, batched OCR and semantic search 2026-11-12 11:48:20 -07:00