feat: phase 4 of AI pipeline hardening — quiz & content quality
- src/lib/random.js: Fisher–Yates shuffle/sample/pickInt; replace every
biased .sort(() => 0.5 - Math.random()) site in testService.
- testService: debias correctIndex via prompt + runtime re-roll (up to 2x
when one position holds >50%); quality gate rejecting <4 distinct
options, banned filler ("all of the above" etc) and explanations
shorter than 20 chars; dedup new questions against the existing bank
via normalised question text.
- Quiz schema/tool/prompt require difficulty ('easy'|'medium'|'hard');
db.getQuizBank defaults legacy records to 'medium' on read.
- learningService.generateCustomTopic: kebab-case slug ID from the
polished label with collision suffixes; default learning_relevance
'standard' when the model omits it.
- Tests for random helpers, dedup/quality-gate behaviour and the
extended quiz schema.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
This commit is contained in:
@@ -108,7 +108,7 @@ describe('learning schemas', () => {
|
||||
});
|
||||
|
||||
describe('quizQuestionsSchema', () => {
|
||||
it('accepts a quiz with four options and a valid correctIndex', () => {
|
||||
it('accepts a quiz with four options, a valid correctIndex and a difficulty', () => {
|
||||
const parsed = quizQuestionsSchema.parse({
|
||||
questions: [
|
||||
{
|
||||
@@ -118,10 +118,12 @@ describe('quizQuestionsSchema', () => {
|
||||
options: ['A', 'B', 'C', 'D'],
|
||||
correctIndex: 2,
|
||||
explanation: 'C describes the buddy system best.',
|
||||
difficulty: 'easy',
|
||||
},
|
||||
],
|
||||
});
|
||||
expect(parsed.questions[0].options).toHaveLength(4);
|
||||
expect(parsed.questions[0].difficulty).toBe('easy');
|
||||
});
|
||||
|
||||
it('rejects three options or an out-of-range correctIndex', () => {
|
||||
@@ -135,6 +137,7 @@ describe('quizQuestionsSchema', () => {
|
||||
options: ['A', 'B', 'C'],
|
||||
correctIndex: 0,
|
||||
explanation: 'e',
|
||||
difficulty: 'medium',
|
||||
},
|
||||
],
|
||||
}),
|
||||
@@ -149,11 +152,27 @@ describe('quizQuestionsSchema', () => {
|
||||
options: ['A', 'B', 'C', 'D'],
|
||||
correctIndex: 4,
|
||||
explanation: 'e',
|
||||
difficulty: 'medium',
|
||||
},
|
||||
],
|
||||
}),
|
||||
).toThrow();
|
||||
});
|
||||
|
||||
it('rejects a missing or unknown difficulty', () => {
|
||||
const base = {
|
||||
id: 'q',
|
||||
question: 'q',
|
||||
topicLabel: 't',
|
||||
options: ['A', 'B', 'C', 'D'],
|
||||
correctIndex: 0,
|
||||
explanation: 'because',
|
||||
};
|
||||
expect(() => quizQuestionsSchema.parse({ questions: [base] })).toThrow();
|
||||
expect(() =>
|
||||
quizQuestionsSchema.parse({ questions: [{ ...base, difficulty: 'trivial' }] }),
|
||||
).toThrow();
|
||||
});
|
||||
});
|
||||
|
||||
describe('customTopicSchema', () => {
|
||||
|
||||
Reference in New Issue
Block a user