Varied question openers, readable rationales, plain practice score
All checks were successful
Verify and publish V2 container / build-and-push (push) Successful in 30s

- Stems no longer all open the same way: the writing rules, batch prompt and
  planner ask for varied openings (age openings stay part of the mix), and when
  one opener covers more than a quarter of a quiz the excess stems have only
  their opening reworded, keeping every number, before the check.
- Rationales are asked for as Markdown (a bold key point, then short bullets);
  older one-paragraph rationales are laid out the same way on display.
- The practice score in the quiz header is a plain "x/y correct", with no
  percentage or colour.
- Fix a flaky assertion: the mock's answer-key fix is a no-op when the shuffle
  already put the answer in place.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
Elijah 2026-11-16 12:05:46 -07:00
parent 10be5c39da
commit 517278be71
15 changed files with 382 additions and 24 deletions

View file

@ -84,6 +84,20 @@ garbled or contradictory stem, missing data, two defensible answers), or `remove
model files as cosmetic or informational (answer position, quotes) are not counted as failed
checks; answer order is shuffled whenever a quiz is taken.
Before the check, **openers are varied** (`server/ai/openers.ts`). Models tend to open nearly
every stem the same way ("A 72-year-old client…"). The first two words of each stem are compared,
with ages and numbers folded together. When one opener covers more than a quarter of a quiz of 8 or
more, a spread-out quarter is kept. The rest have only their opening reworded (`submit_stems`); the
options, answer and rationale stay the same. A rewording is kept only when it holds every number
from the original, keeps "Select all that apply." and no longer opens the repeated way.
Calculations keep their wording. The writing rules, the batch prompt (which names openers already
overused) and the planner (setting, role, trigger) also ask for varied openings.
**Rationales** are asked for as Markdown: one bold key sentence, then 2 to 4 short bullet points,
without repeating the per-choice "why" (`RATIONALE_FORMAT`, also in the question schema, the
review's rewrite schema, "improve questions" and the outside-chatbot instructions). The web app
lays out older one-paragraph rationales the same way when it shows them (`formatRationale`).
Then a **second review**: a fresh model call with no Python reads the whole quiz as a careful
student and item writer would, and rewrites or removes questions that are badly written (a
writer changing its mind mid-stem such as "A 78 kg? No — an 80 kg client", contradictions,