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>

pb_migrations/1780500000_updated_topics_relevance_locked.js

@@ -0,0 +1,23 @@
+/// <reference path="../pb_data/types.d.ts" />
+migrate((app) => {
+  const collection = app.findCollectionByNameOrId("pbc_2800040823")
+
+  // add field — relevance_locked is set to true whenever an admin edits
+  // learning_relevance via the UI; mergeKnowledgeGraph must never overwrite
+  // learning_relevance on a locked topic during re-extraction.
+  collection.fields.addAt(5, new Field({
+    "hidden": false,
+    "id": "bool_relevance_locked",
+    "name": "relevance_locked",
+    "presentable": false,
+    "required": false,
+    "system": false,
+    "type": "bool"
+  }))
+
+  return app.save(collection)
+}, (app) => {
+  const collection = app.findCollectionByNameOrId("pbc_2800040823")
+  collection.fields.removeById("bool_relevance_locked")
+  return app.save(collection)
+})

pb_migrations/1780500001_normalize_relation_types.js

@@ -0,0 +1,43 @@
+/// <reference path="../pb_data/types.d.ts" />
+// One-shot data migration: rewrite legacy "executes" relations to the
+// canonical "executed_by" vocabulary by swapping source and target.
+// Previously `role --executes--> process`; canonical is
+// `process --executed_by--> role`.
+migrate((app) => {
+  const records = app.findRecordsByFilter(
+    "pbc_1883724256",  // relations collection
+    'type = "executes"',
+    '',
+    0,
+    0,
+  )
+
+  for (const rec of records) {
+    const source = rec.get("source")
+    const target = rec.get("target")
+    rec.set("type", "executed_by")
+    rec.set("source", target)
+    rec.set("target", source)
+    app.save(rec)
+  }
+}, (app) => {
+  // Reverse: turn executed_by back into executes (best-effort — only those
+  // created before this migration would have been "executes"; rolling back
+  // will affect any newer executed_by rows too).
+  const records = app.findRecordsByFilter(
+    "pbc_1883724256",
+    'type = "executed_by"',
+    '',
+    0,
+    0,
+  )
+
+  for (const rec of records) {
+    const source = rec.get("source")
+    const target = rec.get("target")
+    rec.set("type", "executes")
+    rec.set("source", target)
+    rec.set("target", source)
+    app.save(rec)
+  }
+})

src/components/admin/KnowledgeGraph.jsx

@@ -180,10 +180,17 @@ const KnowledgeGraph = () => {
   };
 
   const saveEdit = async () => {
-    await db.upsertTopic({ ...selectedNode, ...editData });
-    const updated = topics.map(t => t.id === selectedNode.id ? { ...t, ...editData } : t);
+    // If the admin touched learning_relevance, lock it so re-extraction won't overwrite the choice.
+    // But an explicit relevance_locked in editData (the unlock checkbox) always wins.
+    const relevanceChanged =
+      editData.learning_relevance !== undefined &&
+      editData.learning_relevance !== selectedNode.learning_relevance;
+    const next = { ...editData };
+    if (relevanceChanged && next.relevance_locked === undefined) next.relevance_locked = true;
+    await db.upsertTopic({ ...selectedNode, ...next });
+    const updated = topics.map(t => t.id === selectedNode.id ? { ...t, ...next } : t);
     setTopics(updated);
-    setSelectedNode({ ...selectedNode, ...editData });
+    setSelectedNode({ ...selectedNode, ...next });
     setIsEditing(false);
   };
 
@@ -265,22 +272,11 @@ const KnowledgeGraph = () => {
           setSyncProgress(`Processing ${count} of ${filesToProcess.length}: ${file.name}...`);
           try {
             const rawContent = await getFileContent('respellion', 'employee-handbook', file.path);
+            // Pacing is handled centrally by extractionLimiter inside analyzeHandbookDelta.
             await analyzeHandbookDelta(rawContent, file.path);
             await db.updateHandbookSyncState(file.path, file.sha);
-            
-            // To respect Anthropic's 5 requests per minute rate limit on this tier, 
-            // we pause for 15 seconds before processing the next file.
-            if (count < filesToProcess.length) {
-              setSyncProgress(`Waiting 15s to avoid rate limits... (${count}/${filesToProcess.length})`);
-              await new Promise(resolve => setTimeout(resolve, 15000));
-            }
           } catch (err) {
             console.error('Failed to process file:', file.path, err);
-            // We continue processing other files even if one fails, but still wait to avoid further rate limits
-            if (count < filesToProcess.length) {
-              setSyncProgress(`Error on ${file.name}. Waiting 15s... (${count}/${filesToProcess.length})`);
-              await new Promise(resolve => setTimeout(resolve, 15000));
-            }
           }
         }
         setSyncProgress('Sync Complete! Click "Analyze & Optimize Graph" above to clean up and merge.');
@@ -369,7 +365,7 @@ ${JSON.stringify({ topics: compactTopics, relations: compactRelations })}`;
       if (actions.relevanceUpdates && Array.isArray(actions.relevanceUpdates)) {
         for (const update of actions.relevanceUpdates) {
           const topicIndex = updatedTopics.findIndex(t => t.id === update.id);
-          if (topicIndex !== -1) {
+          if (topicIndex !== -1 && !updatedTopics[topicIndex].relevance_locked) {
             updatedTopics[topicIndex] = { ...updatedTopics[topicIndex], learning_relevance: update.learning_relevance };
           }
         }
@@ -532,6 +528,17 @@ ${JSON.stringify({ topics: compactTopics, relations: compactRelations })}`;
                   <option value="peripheral">Peripheral</option>
                   <option value="exclude">Exclude</option>
                 </select>
+                {selectedNode.relevance_locked && (
+                  <label className="flex items-center gap-2 text-xs text-fg-muted mt-2 cursor-pointer">
+                    <input
+                      type="checkbox"
+                      checked={editData.relevance_locked !== false}
+                      onChange={e => setEditData({...editData, relevance_locked: e.target.checked})}
+                      className="rounded bg-bg-warm border-transparent focus:ring-0 text-teal"
+                    />
+                    Locked — re-extraction will not change this
+                  </label>
+                )}
               </div>
               <div>
                 <label className="text-xs text-fg-muted uppercase tracking-wider mb-1 block">Description</label>
@@ -554,9 +561,12 @@ ${JSON.stringify({ topics: compactTopics, relations: compactRelations })}`;
               </div>
               <div>
                 <p className="text-xs text-fg-muted uppercase tracking-wider mb-1">Type & Relevance</p>
-                <div className="flex gap-2">
+                <div className="flex gap-2 flex-wrap">
                   <span className="inline-block px-2 py-1 bg-bg-warm rounded-[var(--r-pill)] text-xs font-mono">{selectedNode.type}</span>
                   <span className="inline-block px-2 py-1 bg-bg-warm rounded-[var(--r-pill)] text-xs font-mono opacity-80">{selectedNode.learning_relevance || 'standard'}</span>
+                  {selectedNode.relevance_locked && (
+                    <span className="inline-block px-2 py-1 bg-teal/10 text-teal rounded-[var(--r-pill)] text-xs font-mono" title="Re-extraction will not change relevance for this topic.">locked</span>
+                  )}
                 </div>
               </div>
               <div>

src/components/admin/TestManager.jsx

@@ -34,7 +34,7 @@ const TestManager = () => {
     loadData();
   }, [selectedTopic]);
 
-  const handleGenerate = async (topic, count = 10) => {
+  const handleGenerate = async (topic, count = 5) => {
     setLoadingTopicId(topic.id);
     setError(null);
     try {
@@ -97,8 +97,8 @@ const TestManager = () => {
           {questions.length === 0 ? (
             <Card className="text-center py-12 text-fg-muted border-dashed border-2">
               <p>No questions generated for this topic yet.</p>
-              <Button className="mt-4" onClick={() => handleGenerate(selectedTopic, 10)} disabled={loadingTopicId === selectedTopic.id}>
-                Generate 10 Questions
+              <Button className="mt-4" onClick={() => handleGenerate(selectedTopic, 5)} disabled={loadingTopicId === selectedTopic.id}>
+                Generate 5 Questions
               </Button>
             </Card>
           ) : (

src/components/admin/UploadZone.jsx

@@ -1,5 +1,5 @@
 import { useState, useRef } from 'react';
-import { UploadCloud, AlertCircle, CheckCircle } from 'lucide-react';
+import { UploadCloud, AlertCircle, CheckCircle, X } from 'lucide-react';
 import { processSourceText } from '../../lib/extractionPipeline';
 import Card from '../ui/Card';
 import Button from '../ui/Button';
@@ -12,24 +12,36 @@ const UploadZone = ({ onUploadComplete }) => {
   const [status, setStatus]                 = useState(null);
 
   const fileInputRef = useRef(null);
+  const abortRef     = useRef(null);
 
   // ── File upload (drag & drop / browse) ────────────────────────────────────
 
   const processFile = async (file) => {
     setIsProcessing(true);
     setStatus(null);
+    const controller = new AbortController();
+    abortRef.current = controller;
     try {
       const text = await file.text();
-      await processSourceText(text, file.name);
+      await processSourceText(text, file.name, { signal: controller.signal });
       setStatus({ type: 'success', msg: `Successfully processed: ${file.name}` });
       if (onUploadComplete) onUploadComplete();
     } catch (error) {
-      setStatus({ type: 'error', msg: `Error processing file: ${error.message}` });
+      if (error?.name === 'AbortError') {
+        setStatus({ type: 'error', msg: `Cancelled: ${file.name}` });
+      } else {
+        setStatus({ type: 'error', msg: `Error processing file: ${error.message}` });
+      }
     } finally {
+      abortRef.current = null;
       setIsProcessing(false);
     }
   };
 
+  const cancelProcessing = () => {
+    abortRef.current?.abort(new DOMException('Cancelled by user', 'AbortError'));
+  };
+
   const handleDragOver  = (e) => { e.preventDefault(); setIsDragging(true); };
   const handleDragLeave = ()  => setIsDragging(false);
 
@@ -80,6 +92,19 @@ const UploadZone = ({ onUploadComplete }) => {
         />
       </Card>
 
+      {/* Cancel sits outside the upload card so pointer-events-none doesn't disable it. */}
+      {isProcessing && (
+        <div className="flex justify-center">
+          <button
+            type="button"
+            onClick={cancelProcessing}
+            className="flex items-center gap-1 text-sm text-red-600 hover:text-red-700 underline"
+          >
+            <X size={14} /> Cancel extraction
+          </button>
+        </div>
+      )}
+
       {/* ─── Status messages ─── */}
       {status && (
         <div className={`p-4 rounded-[var(--r-sm)] flex items-start gap-3 ${

src/lib/__tests__/extractionPipeline.test.js

@@ -0,0 +1,89 @@
+import { describe, expect, it, vi, beforeEach, afterEach } from 'vitest';
+
+vi.mock('../pb', () => ({
+  pb: { collection: () => ({ create: () => ({ catch: () => {} }) }) },
+}));
+
+import { chunkText, buildKnownIdsHint, MAX_CHUNK_CHARS, OVERLAP_CHARS } from '../extractionPipeline';
+
+describe('chunkText', () => {
+  let warnSpy;
+  beforeEach(() => { warnSpy = vi.spyOn(console, 'warn').mockImplementation(() => {}); });
+  afterEach(() => { warnSpy.mockRestore(); });
+
+  it('returns the original text as a single chunk when below maxChars', () => {
+    const result = chunkText('A short paragraph.');
+    expect(result).toEqual(['A short paragraph.']);
+  });
+
+  it('returns empty array for empty/whitespace input', () => {
+    expect(chunkText('')).toEqual([]);
+    expect(chunkText('   \n  ')).toEqual([]);
+  });
+
+  it('splits along sentence boundaries with overlap between adjacent chunks', () => {
+    const sentence = 'This is a sentence with exactly a known length. ';
+    const text = sentence.repeat(100); // ~5000 chars
+    const chunks = chunkText(text, { maxChars: 600, overlapChars: 150 });
+
+    expect(chunks.length).toBeGreaterThan(1);
+    for (const c of chunks) {
+      expect(c.length).toBeLessThanOrEqual(600);
+    }
+    // Adjacent chunks share trailing text — the overlap should be non-empty.
+    for (let i = 1; i < chunks.length; i++) {
+      const tail = chunks[i - 1].slice(-150);
+      // The new chunk must begin with content that appears at the tail of the prior chunk.
+      const firstHundred = chunks[i].slice(0, 100);
+      // At least one word from the tail should appear in the head of the next chunk.
+      const words = tail.split(/\s+/).filter((w) => w.length > 3);
+      const shared = words.some((w) => firstHundred.includes(w));
+      expect(shared).toBe(true);
+    }
+  });
+
+  it('hard-splits a single sentence that exceeds maxChars and logs a warning', () => {
+    const huge = 'word '.repeat(400).trim() + '.'; // ~2000 chars, no sentence break
+    const chunks = chunkText(huge, { maxChars: 500, overlapChars: 50 });
+    expect(chunks.length).toBeGreaterThan(1);
+    expect(warnSpy).toHaveBeenCalled();
+    for (const c of chunks) expect(c.length).toBeLessThanOrEqual(500);
+  });
+
+  it('handles paragraph-only splits when no sentence punctuation is present', () => {
+    const paragraphs = Array.from({ length: 10 }, (_, i) => `paragraph ${i} content here`).join('\n\n');
+    const chunks = chunkText(paragraphs, { maxChars: 80, overlapChars: 20 });
+    expect(chunks.length).toBeGreaterThan(1);
+  });
+
+  it('uses the documented defaults', () => {
+    expect(MAX_CHUNK_CHARS).toBe(8000);
+    expect(OVERLAP_CHARS).toBe(800);
+  });
+});
+
+describe('buildKnownIdsHint', () => {
+  it('returns empty string when no IDs are known', () => {
+    expect(buildKnownIdsHint([])).toBe('');
+    expect(buildKnownIdsHint(undefined)).toBe('');
+    expect(buildKnownIdsHint(null)).toBe('');
+  });
+
+  it('formats the known IDs as a bulleted list with a leading instruction', () => {
+    const hint = buildKnownIdsHint(['software-engineer', 'onboarding-buddy']);
+    expect(hint).toContain('Already-extracted topic IDs');
+    expect(hint).toContain('- software-engineer');
+    expect(hint).toContain('- onboarding-buddy');
+    expect(hint.endsWith('\n')).toBe(true);
+  });
+
+  it('caps the hint at the 200 most recent IDs', () => {
+    const ids = Array.from({ length: 250 }, (_, i) => `topic-${i}`);
+    const hint = buildKnownIdsHint(ids);
+    // The newest IDs must appear; the oldest must not.
+    expect(hint).toContain('topic-249');
+    expect(hint).toContain('topic-50');
+    expect(hint).not.toContain('topic-49');
+    expect(hint).not.toContain('topic-0\n');
+  });
+});

src/lib/__tests__/llmRetry.test.js

@@ -0,0 +1,72 @@
+import { describe, expect, it, vi, afterEach } from 'vitest';
+import { createLimiter, extractionLimiter } from '../llmRetry';
+
+afterEach(() => { vi.useRealTimers(); });
+
+describe('createLimiter', () => {
+  it('rejects an invalid rps', () => {
+    expect(() => createLimiter({ rps: 0 })).toThrow();
+    expect(() => createLimiter({ rps: -1 })).toThrow();
+  });
+
+  it('rejects an invalid burst', () => {
+    expect(() => createLimiter({ rps: 1, burst: 0 })).toThrow();
+  });
+
+  it('lets the first call through immediately (initial burst token)', async () => {
+    const limiter = createLimiter({ rps: 1, burst: 1 });
+    const start = Date.now();
+    await limiter.acquire();
+    expect(Date.now() - start).toBeLessThan(50);
+  });
+
+  it('queues subsequent calls to respect the spacing', async () => {
+    vi.useFakeTimers();
+    const limiter = createLimiter({ rps: 10, burst: 1 }); // 100ms spacing
+    await limiter.acquire(); // consume initial token
+
+    let resolved = false;
+    const p = limiter.acquire().then(() => { resolved = true; });
+
+    await vi.advanceTimersByTimeAsync(50);
+    expect(resolved).toBe(false);
+
+    await vi.advanceTimersByTimeAsync(100);
+    await p;
+    expect(resolved).toBe(true);
+  });
+
+  it('honours pauseUntil — no acquire returns before the pause expires', async () => {
+    vi.useFakeTimers();
+    const limiter = createLimiter({ rps: 100, burst: 5 });
+    limiter.pauseUntil(Date.now() + 1000);
+
+    let resolved = false;
+    const p = limiter.acquire().then(() => { resolved = true; });
+
+    await vi.advanceTimersByTimeAsync(500);
+    expect(resolved).toBe(false);
+
+    await vi.advanceTimersByTimeAsync(600);
+    await p;
+    expect(resolved).toBe(true);
+  });
+
+  it('aborts a queued acquire when the signal fires', async () => {
+    const limiter = createLimiter({ rps: 1, burst: 1 });
+    await limiter.acquire(); // consume
+
+    const ctl = new AbortController();
+    const p = limiter.acquire({ signal: ctl.signal });
+    ctl.abort();
+
+    await expect(p).rejects.toBeInstanceOf(DOMException);
+  });
+});
+
+describe('extractionLimiter', () => {
+  it('is exported and exposes the limiter shape', () => {
+    expect(typeof extractionLimiter.acquire).toBe('function');
+    expect(typeof extractionLimiter.pauseUntil).toBe('function');
+  });
+});

src/lib/__tests__/llmSchemas.test.js

@@ -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', () => {

src/lib/__tests__/random.test.js

@@ -0,0 +1,48 @@
+import { describe, expect, it } from 'vitest';
+import { shuffle, sample, pickInt } from '../random';
+
+describe('shuffle', () => {
+  it('returns a new array containing the same elements', () => {
+    const input = [1, 2, 3, 4, 5];
+    const out = shuffle(input);
+    expect(out).not.toBe(input);
+    expect([...out].sort()).toEqual([...input].sort());
+    expect(input).toEqual([1, 2, 3, 4, 5]);
+  });
+
+  it('handles empty and single-element arrays', () => {
+    expect(shuffle([])).toEqual([]);
+    expect(shuffle([42])).toEqual([42]);
+  });
+});
+
+describe('sample', () => {
+  it('returns up to n unique elements from the source array', () => {
+    const out = sample([1, 2, 3, 4, 5], 3);
+    expect(out).toHaveLength(3);
+    expect(new Set(out).size).toBe(3);
+    for (const v of out) expect([1, 2, 3, 4, 5]).toContain(v);
+  });
+
+  it('returns the full shuffled array when n exceeds length', () => {
+    const out = sample([1, 2, 3], 10);
+    expect(out).toHaveLength(3);
+    expect([...out].sort()).toEqual([1, 2, 3]);
+  });
+
+  it('returns an empty array when n is zero or negative', () => {
+    expect(sample([1, 2, 3], 0)).toEqual([]);
+    expect(sample([1, 2, 3], -2)).toEqual([]);
+  });
+});
+
+describe('pickInt', () => {
+  it('returns an integer in the inclusive range', () => {
+    for (let i = 0; i < 100; i++) {
+      const v = pickInt(2, 5);
+      expect(Number.isInteger(v)).toBe(true);
+      expect(v).toBeGreaterThanOrEqual(2);
+      expect(v).toBeLessThanOrEqual(5);
+    }
+  });
+});

src/lib/__tests__/testService.test.js

@@ -0,0 +1,112 @@
+import { describe, expect, it, vi, beforeEach, afterEach } from 'vitest';
+
+const bankStore = new Map();
+const callLLMMock = vi.fn();
+
+vi.mock('../pb', () => ({ pb: { collection: () => ({}) } }));
+
+vi.mock('../db', () => ({
+  getQuizBank: vi.fn(async (topicId) => bankStore.get(topicId) || []),
+  setQuizBank: vi.fn(async (topicId, qs) => { bankStore.set(topicId, qs); }),
+  getTopics: vi.fn(async () => []),
+  deleteQuestionFromBank: vi.fn(),
+  getCachedQuiz: vi.fn(),
+  setCachedQuiz: vi.fn(),
+  getQuizResult: vi.fn(),
+  saveQuizResult: vi.fn(),
+  getTeamMembers: vi.fn(async () => []),
+  upsertLeaderboardEntry: vi.fn(),
+  getCurriculum: vi.fn(),
+}));
+
+vi.mock('../llm', () => ({ callLLM: (...args) => callLLMMock(...args) }));
+vi.mock('../curriculumService', () => ({
+  getCurriculumTopic: vi.fn(async () => ({ topic: null })),
+  getQuarterForWeek: vi.fn(() => 1),
+}));
+
+import { forceGenerateTopicQuestions } from '../testService';
+
+const topic = { id: 'onboarding', label: 'Onboarding', type: 'concept', description: 'Onboarding for new joiners.' };
+
+function makeQuestion(i, overrides = {}) {
+  return {
+    id: `q-${i}`,
+    question: `Sample question ${i}?`,
+    topicLabel: 'Onboarding',
+    options: ['A) one', 'B) two', 'C) three', 'D) four'],
+    correctIndex: i % 4,
+    explanation: 'This is a substantive explanation for the correct answer.',
+    difficulty: 'medium',
+    ...overrides,
+  };
+}
+
+function llmEmits(questions) {
+  callLLMMock.mockResolvedValueOnce({ toolUses: [{ name: 'emit_quiz_questions', input: { questions } }] });
+}
+
+describe('forceGenerateTopicQuestions', () => {
+  let debugSpy, warnSpy;
+  beforeEach(() => {
+    bankStore.clear();
+    callLLMMock.mockReset();
+    debugSpy = vi.spyOn(console, 'debug').mockImplementation(() => {});
+    warnSpy = vi.spyOn(console, 'warn').mockImplementation(() => {});
+  });
+  afterEach(() => { debugSpy.mockRestore(); warnSpy.mockRestore(); });
+
+  it('persists a well-formed batch and assigns topic-scoped ids', async () => {
+    llmEmits([0, 1, 2, 3, 4].map((i) => makeQuestion(i)));
+    const out = await forceGenerateTopicQuestions(topic, 5);
+    expect(out).toHaveLength(5);
+    for (const q of out) expect(q.id.startsWith('onboarding-')).toBe(true);
+    expect(bankStore.get('onboarding')).toHaveLength(5);
+  });
+
+  it('re-rolls when one correctIndex dominates the batch, then accepts on the third try', async () => {
+    const allZero = [0, 1, 2, 3, 4].map((i) => makeQuestion(i, { correctIndex: 0 }));
+    llmEmits(allZero);
+    llmEmits(allZero);
+    llmEmits(allZero);
+    const out = await forceGenerateTopicQuestions(topic, 5);
+    expect(callLLMMock).toHaveBeenCalledTimes(3);
+    expect(out).toHaveLength(5);
+    expect(warnSpy).toHaveBeenCalledWith(expect.stringContaining('correctIndex dominated'));
+  });
+
+  it('rejects a batch containing a banned "all of the above" option', async () => {
+    const bad = [0, 1, 2, 3, 4].map((i) =>
+      makeQuestion(i, { options: ['A) x', 'B) y', 'C) z', 'D) All of the above'] }),
+    );
+    llmEmits(bad);
+    llmEmits(bad);
+    llmEmits(bad);
+    await expect(forceGenerateTopicQuestions(topic, 5)).rejects.toThrow(/banned filler|rejected/i);
+  });
+
+  it('rejects a batch where an explanation is too short', async () => {
+    const bad = [0, 1, 2, 3, 4].map((i) => makeQuestion(i, { explanation: 'Because.' }));
+    llmEmits(bad);
+    llmEmits(bad);
+    llmEmits(bad);
+    await expect(forceGenerateTopicQuestions(topic, 5)).rejects.toThrow(/too short|rejected/i);
+  });
+
+  it('drops duplicates whose normalized text matches an existing bank entry', async () => {
+    bankStore.set('onboarding', [
+      { ...makeQuestion(99), id: 'old-1', question: 'What is the BUDDY system???' },
+    ]);
+    llmEmits([
+      makeQuestion(0, { question: 'what is the buddy system!' }),
+      makeQuestion(1, { question: 'Brand new question one?' }),
+      makeQuestion(2, { question: 'Brand new question two?' }),
+      makeQuestion(3, { question: 'Brand new question three?' }),
+      makeQuestion(4, { question: 'Brand new question four?' }),
+    ]);
+    const out = await forceGenerateTopicQuestions(topic, 5);
+    expect(out).toHaveLength(4);
+    expect(out.find((q) => q.question.toLowerCase().includes('buddy'))).toBeUndefined();
+    expect(debugSpy).toHaveBeenCalledWith(expect.stringContaining('dropped duplicate'), expect.any(String));
+  });
+});

src/lib/db.js

@@ -18,6 +18,7 @@ export async function saveTopics(topics) {
       type: t.type,
       description: t.description,
       learning_relevance: t.learning_relevance || 'standard',
+      relevance_locked: t.relevance_locked === true,
     }, { requestKey: null });
   }
 }
@@ -89,10 +90,15 @@ export async function deleteContent(topicId) {
 
 // ── Quiz Banks ───────────────────────────────────────────────────────────────
 
+function normalizeQuizQuestion(q) {
+  if (!q || typeof q !== 'object') return q;
+  return q.difficulty ? q : { ...q, difficulty: 'medium' };
+}
+
 export async function getQuizBank(topicId) {
   try {
     const r = await pb.collection('quiz_banks').getFirstListItem(`topic_id="${topicId}"`);
-    return r.questions || [];
+    return (r.questions || []).map(normalizeQuizQuestion);
   } catch { return []; }
 }
 

src/lib/extractionPipeline.js

@@ -1,8 +1,28 @@
 import * as db from './db';
 import { callLLM } from './llm';
+import { extractionLimiter } from './llmRetry';
 import { EMIT_KNOWLEDGE_GRAPH_TOOL, EMIT_HANDBOOK_DELTA_TOOL } from './llmTools';
 import { normalizeHandbookResult } from './llmSchemas';
 
+const MAX_KNOWN_IDS_HINT = 200;
+
+/**
+ * Build the "already-extracted topic IDs" hint that prepends every chunk
+ * after the first. Capped at the most-recent `MAX_KNOWN_IDS_HINT` IDs so
+ * the prompt stays a bounded size; the model uses this list to reuse IDs
+ * rather than invent variants like `software-developer` for
+ * `software-engineer`.
+ */
+export function buildKnownIdsHint(ids) {
+  if (!ids || !ids.length) return '';
+  const recent = ids.slice(-MAX_KNOWN_IDS_HINT);
+  return [
+    'Already-extracted topic IDs (do NOT create new IDs for these — reuse them if the same concept appears here):',
+    ...recent.map((id) => `- ${id}`),
+    '',
+  ].join('\n');
+}
+
 const EXTRACTION_SYSTEM_PROMPT = `You are an AI knowledge extractor for Respellion, an IT company built on radical transparency.
 You receive a source text. Extract every distinct concept, role, and process from it and emit them through the emit_knowledge_graph tool.
 
@@ -28,17 +48,17 @@ Relation types: related_to | depends_on | part_of | executed_by.
 const HANDBOOK_SYSTEM_PROMPT = `You are analysing an update to the Respellion Employee Handbook. Emit the extracted topics and relations through the emit_handbook_delta tool.
 
 CRITICAL INSTRUCTIONS:
-- Every process must have a role attached (the role that executes it).
+- Every process must have a role attached. Express this as: process --executed_by--> role.
 - Every concept must connect to a process or role.
 - Mark handbook topics with metadata.source = "github_handbook".
 - Assign learning_relevance using the same scale as extraction: core | standard | peripheral | exclude.
 
-Relation types: related_to | depends_on | part_of | executed_by. (Legacy "executes" relations are normalised by the client into executed_by with source/target swapped.)
+Relation types: related_to | depends_on | part_of | executed_by.
 `;
 
 const cachedSystem = (text) => [{ type: 'text', text, cache_control: { type: 'ephemeral' } }];
 
-export async function analyzeHandbookDelta(fileContent, filePath) {
+export async function analyzeHandbookDelta(fileContent, filePath, { signal } = {}) {
   const result = await callLLM({
     task: 'extract.handbook',
     tier: 'standard',
@@ -47,6 +67,8 @@ export async function analyzeHandbookDelta(fileContent, filePath) {
     tools: [EMIT_HANDBOOK_DELTA_TOOL],
     toolChoice: { type: 'tool', name: EMIT_HANDBOOK_DELTA_TOOL.name },
     maxTokens: 8192,
+    limiter: extractionLimiter,
+    signal,
   });
 
   const raw = result.toolUses[0]?.input;
@@ -57,24 +79,79 @@ export async function analyzeHandbookDelta(fileContent, filePath) {
   return { success: true, data: extractedData };
 }
 
-function chunkText(text, maxChunkSize = 4000) {
-  const paragraphs = text.split(/\n+/);
-  const chunks = [];
-  let currentChunk = '';
+/**
+ * Sentence-aware chunker with overlap.
+ *
+ * Targets ~2000 input tokens per chunk (`MAX_CHUNK_CHARS / 4`). Splits on
+ * sentence boundaries first, then falls back to paragraph boundaries, and
+ * hard-splits inside an oversized sentence as a last resort. Adjacent chunks
+ * share `overlapChars` of trailing text to preserve cross-boundary context
+ * for the model.
+ *
+ * Exported for unit tests; callers in this module use it directly.
+ *
+ * @param {string} text
+ * @param {{ maxChars?: number, overlapChars?: number }} [opts]
+ * @returns {string[]}
+ */
+export const MAX_CHUNK_CHARS = 8000;
+export const OVERLAP_CHARS = 800;
 
-  for (const para of paragraphs) {
-    if ((currentChunk + '\n' + para).length > maxChunkSize) {
-      if (currentChunk) chunks.push(currentChunk.trim());
-      currentChunk = para;
-    } else {
-      currentChunk = currentChunk ? currentChunk + '\n' + para : para;
+export function chunkText(text, { maxChars = MAX_CHUNK_CHARS, overlapChars = OVERLAP_CHARS } = {}) {
+  if (typeof text !== 'string' || !text.trim()) return [];
+  const trimmed = text.trim();
+  if (trimmed.length <= maxChars) return [trimmed];
+
+  const units = splitIntoChunkableUnits(trimmed, maxChars);
+  if (units.length === 0) return [];
+
+  const chunks = [];
+  let buf = '';
+  let bufLen = 0; // length of new (non-overlap) content added since last flush
+
+  for (const unit of units) {
+    const wouldOverflow = (buf ? buf.length + 1 + unit.length : unit.length) > maxChars;
+    if (wouldOverflow && bufLen > 0) {
+      chunks.push(buf.trim());
+      const overlap = buf.length > overlapChars ? buf.slice(-overlapChars) : '';
+      buf = overlap;
+      bufLen = 0;
     }
+    // If the overlap + unit still won't fit, drop the overlap so the unit fits cleanly.
+    if (buf && (buf.length + 1 + unit.length) > maxChars) {
+      buf = '';
+    }
+    buf = buf ? buf + ' ' + unit : unit;
+    bufLen += unit.length + (bufLen > 0 ? 1 : 0);
   }
-  if (currentChunk) chunks.push(currentChunk.trim());
+  if (bufLen > 0 && buf.trim()) chunks.push(buf.trim());
   return chunks;
 }
 
-export async function processSourceText(textContent, sourceName) {
+function splitIntoChunkableUnits(text, maxChars) {
+  const paragraphs = text.split(/\n\s*\n+/);
+  const units = [];
+  for (const para of paragraphs) {
+    const trimmedPara = para.trim();
+    if (!trimmedPara) continue;
+    const sentences = trimmedPara.split(/(?<=[.!?])\s+/);
+    for (const s of sentences) {
+      const sentence = s.trim();
+      if (!sentence) continue;
+      if (sentence.length <= maxChars) {
+        units.push(sentence);
+      } else {
+        for (let i = 0; i < sentence.length; i += maxChars) {
+          units.push(sentence.slice(i, i + maxChars));
+        }
+        console.warn(`[chunkText] Hard-split a sentence of ${sentence.length} chars (exceeds maxChars=${maxChars}).`);
+      }
+    }
+  }
+  return units;
+}
+
+export async function processSourceText(textContent, sourceName, { signal } = {}) {
   const existing = await db.getSources();
   const alreadyDone = existing.find(
     s => s.name === sourceName && s.status === 'completed'
@@ -87,36 +164,42 @@ export async function processSourceText(textContent, sourceName) {
   const sourceId = rec.id;
 
   try {
-    const chunks = chunkText(textContent, 4000);
+    const chunks = chunkText(textContent);
     console.log(`[Pipeline] Split "${sourceName}" into ${chunks.length} chunks for processing.`);
 
-    let allExtractedTopics = [];
-    let allExtractedRelations = [];
+    const existingTopics = await db.getTopics();
+    const knownIds = existingTopics.map((t) => t.id);
+
+    const allExtractedTopics = [];
+    const allExtractedRelations = [];
 
     for (let i = 0; i < chunks.length; i++) {
-      if (i > 0) {
-        console.log(`[Pipeline] Pacing delay (12s) to prevent rate limits before chunk ${i + 1}/${chunks.length}...`);
-        await new Promise(r => setTimeout(r, 12000));
-      }
+      if (signal?.aborted) throw signal.reason ?? new DOMException('Aborted', 'AbortError');
 
       console.log(`[Pipeline] Processing chunk ${i + 1}/${chunks.length} (${chunks[i].length} chars)...`);
+      const hint = i > 0 ? buildKnownIdsHint(knownIds) : '';
       const result = await callLLM({
         task: 'extract.source',
         tier: 'standard',
         system: cachedSystem(EXTRACTION_SYSTEM_PROMPT),
-        user: `Analyze this part of the document (${i + 1}/${chunks.length}):\n\n${chunks[i]}`,
+        user: `${hint}Analyze this part of the document (${i + 1}/${chunks.length}):\n\n${chunks[i]}`,
         tools: [EMIT_KNOWLEDGE_GRAPH_TOOL],
         toolChoice: { type: 'tool', name: EMIT_KNOWLEDGE_GRAPH_TOOL.name },
         maxTokens: 8192,
+        limiter: extractionLimiter,
+        signal,
       });
 
       const extractedData = result.toolUses[0]?.input;
       if (!extractedData) throw new Error(`Extraction did not emit a tool result for chunk ${i + 1}.`);
 
-      if (extractedData.topics && Array.isArray(extractedData.topics)) {
+      if (Array.isArray(extractedData.topics)) {
         allExtractedTopics.push(...extractedData.topics);
+        for (const t of extractedData.topics) {
+          if (t?.id && !knownIds.includes(t.id)) knownIds.push(t.id);
+        }
       }
-      if (extractedData.relations && Array.isArray(extractedData.relations)) {
+      if (Array.isArray(extractedData.relations)) {
         allExtractedRelations.push(...extractedData.relations);
       }
     }
@@ -127,7 +210,8 @@ export async function processSourceText(textContent, sourceName) {
     return { success: true, data: { topics: allExtractedTopics, relations: allExtractedRelations } };
 
   } catch (error) {
-    await db.updateSourceStatus(sourceId, 'failed', error.message);
+    const isAbort = error?.name === 'AbortError';
+    await db.updateSourceStatus(sourceId, isAbort ? 'cancelled' : 'failed', isAbort ? 'cancelled by user' : error.message);
     throw error;
   }
 }
@@ -142,11 +226,16 @@ async function mergeKnowledgeGraph(newData) {
     for (const t of newData.topics) {
       if (topicsMap.has(t.id)) {
         const existing = topicsMap.get(t.id);
-        topicsMap.set(t.id, {
+        const merged = {
           ...existing,
           ...t,
           description: t.description || existing.description,
-        });
+        };
+        if (existing.relevance_locked) {
+          merged.learning_relevance = existing.learning_relevance;
+          merged.relevance_locked = true;
+        }
+        topicsMap.set(t.id, merged);
       } else {
         topicsMap.set(t.id, t);
       }

src/lib/learningService.js

@@ -154,6 +154,28 @@ export async function deleteCachedContent(topicId) {
   return db.deleteContent(topicId);
 }
 
+function slugify(label) {
+  const base = String(label || '')
+    .toLowerCase()
+    .normalize('NFKD')
+    .replace(/\p{Diacritic}/gu, '')
+    .replace(/[^a-z0-9]+/g, '-')
+    .replace(/^-+|-+$/g, '');
+  return base || 'topic';
+}
+
+async function pickUniqueTopicId(label) {
+  const existing = await db.getTopics();
+  const used = new Set(existing.map((t) => t.id));
+  const base = slugify(label);
+  if (!used.has(base)) return base;
+  for (let i = 2; i < 1000; i++) {
+    const candidate = `${base}-${i}`;
+    if (!used.has(candidate)) return candidate;
+  }
+  return `${base}-${Date.now().toString(36)}`;
+}
+
 export async function generateCustomTopic(label) {
   const result = await callLLM({
     task: 'topic.custom',
@@ -168,7 +190,12 @@ export async function generateCustomTopic(label) {
   const emitted = result.toolUses[0]?.input;
   if (!emitted) throw new Error('Could not process custom topic. Please try again.');
 
-  const newTopic = { ...emitted, id: 'custom_' + Date.now().toString(36) };
+  const id = await pickUniqueTopicId(emitted.label);
+  const newTopic = {
+    ...emitted,
+    id,
+    learning_relevance: emitted.learning_relevance || 'standard',
+  };
   await db.upsertTopic(newTopic);
   return newTopic;
 }

src/lib/llm.js

@@ -272,6 +272,7 @@ function validateToolInputs(toolUses, task, toolSchemas) {
  * @property {number} [maxTokens=4096]
  * @property {number} [temperature=0]
  * @property {AbortSignal} [signal]
+ * @property {{ acquire: (opts?:{signal?:AbortSignal}) => Promise<void>, pauseUntil: (untilMs:number) => void }} [limiter]
  */
 
 /**
@@ -291,6 +292,7 @@ export async function callLLM(options) {
     maxTokens = 4096,
     temperature = 0,
     signal,
+    limiter,
   } = options;
   if (!task) throw new Error('callLLM requires a `task` label.');
 
@@ -318,6 +320,7 @@ export async function callLLM(options) {
   try {
     result = await withRetry(
       async () => {
+        if (limiter) await limiter.acquire({ signal });
         const timeoutCtl = signal ? null : new AbortController();
         const timer = timeoutCtl ? setTimeout(() => timeoutCtl.abort(new DOMException('Timeout', 'AbortError')), DEFAULT_TIMEOUT_MS) : null;
         const fetchSignal = linkSignals(signal, timeoutCtl?.signal);
@@ -337,6 +340,9 @@ export async function callLLM(options) {
             const errBody = await response.json().catch(() => ({}));
             if (isRetryableStatus(response.status)) {
               const retryAfterMs = parseRetryAfter(response.headers.get('Retry-After'));
+              if (response.status === 429 && retryAfterMs != null && limiter) {
+                limiter.pauseUntil(Date.now() + retryAfterMs);
+              }
               throw new RetryableError(response.status, retryAfterMs, `HTTP ${response.status}`);
             }
             throw new LLMHttpError(response.status, response.statusText, errBody);

src/lib/llmRetry.js

@@ -62,6 +62,109 @@ function sleep(ms, signal) {
   });
 }
 
+/**
+ * Token-bucket rate limiter shared by callers that hit the same upstream
+ * quota (e.g. handbook extraction loops). Replaces the static
+ * `setTimeout(..., 12000)` / 15s sleeps that Phase 1 relied on. The bucket
+ * refills continuously; `acquire` resolves either immediately (token
+ * available) or after the next refill tick.
+ *
+ * `rps` is "requests per second" (use fractional values for per-minute
+ * limits: `5/60` for 5 req/min). `burst` is the maximum number of tokens
+ * the bucket can hold; default 1 means strict spacing.
+ *
+ * Call `pauseUntil(timestampMs)` after a 429 with a `Retry-After` hint —
+ * no acquire returns before that timestamp.
+ *
+ * @param {{ rps?: number, burst?: number }} [opts]
+ */
+export function createLimiter({ rps = 1, burst = 1 } = {}) {
+  if (rps <= 0) throw new Error('createLimiter: rps must be > 0');
+  if (burst < 1) throw new Error('createLimiter: burst must be >= 1');
+  const intervalMs = 1000 / rps;
+  let tokens = burst;
+  let lastRefill = Date.now();
+  let pausedUntil = 0;
+  const waiters = [];
+
+  function refill(now) {
+    const elapsed = now - lastRefill;
+    if (elapsed <= 0) return;
+    const earned = elapsed / intervalMs;
+    if (earned >= 1) {
+      tokens = Math.min(burst, tokens + Math.floor(earned));
+      lastRefill = now;
+    }
+  }
+
+  function drain() {
+    while (waiters.length) {
+      const now = Date.now();
+      if (now < pausedUntil) {
+        scheduleWake(pausedUntil - now);
+        return;
+      }
+      refill(now);
+      if (tokens >= 1) {
+        tokens -= 1;
+        const w = waiters.shift();
+        w.resolve();
+      } else {
+        const wait = Math.max(intervalMs - (now - lastRefill), 0);
+        scheduleWake(wait);
+        return;
+      }
+    }
+  }
+
+  let wakeTimer = null;
+  function scheduleWake(ms) {
+    if (wakeTimer) return;
+    wakeTimer = setTimeout(() => {
+      wakeTimer = null;
+      drain();
+    }, ms);
+  }
+
+  return {
+    /** @param {{signal?:AbortSignal}} [opts] */
+    async acquire({ signal } = {}) {
+      if (signal?.aborted) throw signal.reason ?? new DOMException('Aborted', 'AbortError');
+      return new Promise((resolve, reject) => {
+        const entry = { resolve, reject };
+        const onAbort = () => {
+          const i = waiters.indexOf(entry);
+          if (i !== -1) waiters.splice(i, 1);
+          reject(signal.reason ?? new DOMException('Aborted', 'AbortError'));
+        };
+        if (signal) signal.addEventListener('abort', onAbort, { once: true });
+        const wrapped = {
+          resolve: () => { if (signal) signal.removeEventListener('abort', onAbort); resolve(); },
+          reject,
+        };
+        waiters.push(wrapped);
+        drain();
+      });
+    },
+    /** Block all `acquire`s until `untilMs` (epoch milliseconds). */
+    pauseUntil(untilMs) {
+      if (untilMs > pausedUntil) pausedUntil = untilMs;
+      drain();
+    },
+    /** Inspect state — primarily for tests. */
+    _state() {
+      return { tokens, pausedUntil, waiters: waiters.length };
+    },
+  };
+}
+
+/**
+ * Shared limiter for the multi-call extraction loops (source chunks,
+ * handbook file sync). 5 requests/minute matches the lowest published
+ * Anthropic tier so we stay well clear of 429.
+ */
+export const extractionLimiter = createLimiter({ rps: 5 / 60, burst: 1 });
+
 /**
  * Run `fn(attempt)` with retry. `fn` may throw a `RetryableError` to request
  * a retry, or any other error to fail immediately.

src/lib/llmSchemas.js

@@ -122,6 +122,8 @@ export const learningAllSchema = z.object({
   infographic: infographicBodySchema,
 });
 
+const quizDifficultyEnum = z.enum(['easy', 'medium', 'hard']);
+
 const quizQuestionSchema = z.object({
   id: z.string().min(1),
   question: z.string().min(1),
@@ -129,6 +131,7 @@ const quizQuestionSchema = z.object({
   options: z.array(z.string().min(1)).length(4),
   correctIndex: z.number().int().min(0).max(3),
   explanation: z.string().min(1),
+  difficulty: quizDifficultyEnum,
 });
 
 export const quizQuestionsSchema = z.object({

src/lib/llmTools.js

@@ -205,6 +205,8 @@ export const EMIT_CUSTOM_TOPIC_TOOL = {
   },
 };
 
+const QUIZ_DIFFICULTIES = ['easy', 'medium', 'hard'];
+
 const quizQuestionSchema = {
   type: 'object',
   properties: {
@@ -214,8 +216,9 @@ const quizQuestionSchema = {
     options: { type: 'array', items: { type: 'string' }, minItems: 4, maxItems: 4 },
     correctIndex: { type: 'integer', minimum: 0, maximum: 3 },
     explanation: { type: 'string', description: 'Why the correct answer is correct (1–2 sentences).' },
+    difficulty: { type: 'string', enum: QUIZ_DIFFICULTIES, description: 'Per-question difficulty tag.' },
   },
-  required: ['id', 'question', 'topicLabel', 'options', 'correctIndex', 'explanation'],
+  required: ['id', 'question', 'topicLabel', 'options', 'correctIndex', 'explanation', 'difficulty'],
 };
 
 export const EMIT_QUIZ_QUESTIONS_TOOL = {

src/lib/random.js

@@ -0,0 +1,29 @@
+/**
+ * Shared randomness helpers.
+ *
+ * `Array.prototype.sort(() => 0.5 - Math.random())` is biased — modern V8
+ * sorts use Timsort, which compares each element more than once and skews
+ * the resulting permutation. Use `shuffle` for anything user-visible
+ * (quiz options, review topic selection, leaderboards).
+ */
+
+export function shuffle(arr) {
+  const out = [...arr];
+  for (let i = out.length - 1; i > 0; i--) {
+    const j = Math.floor(Math.random() * (i + 1));
+    [out[i], out[j]] = [out[j], out[i]];
+  }
+  return out;
+}
+
+export function sample(arr, n) {
+  if (n <= 0) return [];
+  if (n >= arr.length) return shuffle(arr);
+  return shuffle(arr).slice(0, n);
+}
+
+export function pickInt(min, maxInclusive) {
+  const lo = Math.ceil(min);
+  const hi = Math.floor(maxInclusive);
+  return lo + Math.floor(Math.random() * (hi - lo + 1));
+}

src/lib/testService.js

@@ -2,81 +2,73 @@ import * as db from './db';
 import { callLLM } from './llm';
 import { EMIT_QUIZ_QUESTIONS_TOOL } from './llmTools';
 import { getCurriculumTopic, getQuarterForWeek } from './curriculumService';
+import { shuffle, sample } from './random';
 
 const QUIZ_SYSTEM = `You are a quiz generator for Respellion, an internal IT company learning platform.
 You generate multiple-choice questions to test employee knowledge on specific topics.
 Always write in clear, professional English.
 
-Emit questions through the emit_quiz_questions tool. Each question has exactly four options; correctIndex is 0-based; mix difficulty roughly 4 easy / 4 medium / 2 hard.`;
+Emit questions through the emit_quiz_questions tool. Each question has exactly four options; correctIndex is 0-based. Tag every question with difficulty ('easy', 'medium' or 'hard'). For a typical 5-question batch, mix difficulty roughly 2 easy / 2 medium / 1 hard; scale the ratio proportionally for larger batches.
+
+Distribute correctIndex roughly evenly across 0, 1, 2, and 3. Do not place the correct answer at the same position more than 4 out of 10 times.
+
+Never use filler options such as "all of the above", "none of the above", or "both A and B". Every explanation must be a substantive sentence (≥ 20 characters) describing why the correct answer is correct.`;
+
+const BANNED_OPTION_PATTERNS = [
+  /all of the above/i,
+  /none of the above/i,
+  /both a and b/i,
+  /both b and c/i,
+  /both c and d/i,
+  /both a and c/i,
+  /both b and d/i,
+  /both a and d/i,
+];
 
 const cachedSystem = (text) => [{ type: 'text', text, cache_control: { type: 'ephemeral' } }];
 
-async function selectTestTopics(userId, weekNumber) {
-  const allTopics = await db.getTopics();
-  const topics = allTopics.filter(t => t.type !== 'fact' && t.learning_relevance !== 'exclude');
-  if (!topics || topics.length === 0) return { primaryTopic: null, reviewTopics: [], isReviewWeek: false };
-
-  // Try curriculum-based selection first
-  try {
-    const { topic, curriculumEntry } = await getCurriculumTopic(weekNumber);
-
-    if (curriculumEntry?.is_review_week) {
-      // Review week: pull topics from the whole quarter
-      const quarter = getQuarterForWeek(weekNumber);
-      const curriculum = await db.getCurriculum(new Date().getFullYear());
-      const quarterTopicIds = curriculum
-        .filter(w => w.quarter === quarter && w.topic_id && !w.is_review_week)
-        .map(w => w.topic_id);
-      const quarterTopics = topics.filter(t => quarterTopicIds.includes(t.id));
-      // Use all quarter topics as review topics (no single primary)
-      return {
-        primaryTopic: quarterTopics[0] || topics[0],
-        reviewTopics: quarterTopics.slice(1),
-        isReviewWeek: true,
-      };
-    }
-
-    if (topic) {
-      const others = topics.filter(t => t.id !== topic.id);
-      const shuffled = others.sort(() => 0.5 - Math.random());
-      const reviewTopics = shuffled.slice(0, Math.min(5, shuffled.length));
-      return { primaryTopic: topic, reviewTopics, isReviewWeek: false };
-    }
-  } catch (e) {
-    console.warn('[Test] Curriculum lookup failed, falling back to hash:', e.message);
-  }
-
-  // Fallback: hash-based selection
-  const str = `${userId}:${weekNumber}`;
-  let hash = 0;
-  for (let i = 0; i < str.length; i++) {
-    hash = (hash << 5) - hash + str.charCodeAt(i);
-    hash |= 0;
-  }
-  const primaryIndex = Math.abs(hash) % topics.length;
-  const primaryTopic = topics[primaryIndex];
-
-  const others = topics.filter((_, i) => i !== primaryIndex);
-  const shuffled = others.sort(() => 0.5 - Math.random());
-  const reviewTopics = shuffled.slice(0, Math.min(5, shuffled.length));
-
-  return { primaryTopic, reviewTopics, isReviewWeek: false };
+function normalizeQuestionText(text) {
+  return String(text || '')
+    .toLowerCase()
+    .replace(/[\p{P}\p{S}]/gu, ' ')
+    .replace(/\s+/g, ' ')
+    .trim();
 }
 
-export async function getCachedQuiz(userId, weekNumber) {
-  return db.getCachedQuiz(userId, weekNumber);
+function dominantCorrectIndex(questions) {
+  if (!questions.length) return null;
+  const counts = [0, 0, 0, 0];
+  for (const q of questions) counts[q.correctIndex] = (counts[q.correctIndex] || 0) + 1;
+  const max = Math.max(...counts);
+  return max / questions.length > 0.5 ? { index: counts.indexOf(max), ratio: max / questions.length } : null;
 }
 
-export async function forceGenerateTopicQuestions(topic, count = 10) {
-  let bank = await db.getQuizBank(topic.id);
+function validateBatchQuality(questions) {
+  for (const q of questions) {
+    const distinct = new Set(q.options.map((o) => o.trim().toLowerCase()));
+    if (distinct.size < 4) {
+      return `Question "${q.question}" has duplicate options.`;
+    }
+    for (const opt of q.options) {
+      if (BANNED_OPTION_PATTERNS.some((re) => re.test(opt))) {
+        return `Question "${q.question}" uses a banned filler option ("${opt}").`;
+      }
+    }
+    if (!q.explanation || q.explanation.trim().length < 20) {
+      return `Question "${q.question}" has an explanation that is too short.`;
+    }
+  }
+  return null;
+}
 
+async function callQuizModel(topic, count) {
   const prompt = `Generate exactly ${count} multiple-choice quiz questions for this knowledge topic and emit them via the emit_quiz_questions tool:
 
 Topic: ${topic.label}
 Type: ${topic.type}
 Description: ${topic.description}
 
-Options must be prefixed "A) ", "B) ", "C) ", "D) ". Make questions specific and practical, not trivial.`;
+Options must be prefixed "A) ", "B) ", "C) ", "D) ". Make questions specific and practical, not trivial. Example: a question whose correct answer is option C uses "correctIndex": 2.`;
 
   const result = await callLLM({
     task: 'quiz.generate',
@@ -89,28 +81,125 @@ Options must be prefixed "A) ", "B) ", "C) ", "D) ". Make questions specific and
   });
 
   const emitted = result.toolUses[0]?.input;
-  if (!emitted) throw new Error(`Could not generate questions for ${topic.label}`);
+  if (!emitted?.questions?.length) {
+    throw new Error(`Could not generate questions for ${topic.label}`);
+  }
+  return emitted.questions;
+}
 
-  const newQuestions = (emitted.questions || []).map(q => ({
-    ...q,
-    id: `${topic.id}-${Math.random().toString(36).slice(2, 11)}`,
-  }));
+async function selectTestTopics(userId, weekNumber) {
+  const allTopics = await db.getTopics();
+  const topics = allTopics.filter(t => t.type !== 'fact' && t.learning_relevance !== 'exclude');
+  if (!topics || topics.length === 0) return { primaryTopic: null, reviewTopics: [], isReviewWeek: false };
 
-  bank = [...bank, ...newQuestions];
-  await db.setQuizBank(topic.id, bank);
-  return newQuestions;
+  try {
+    const { topic, curriculumEntry } = await getCurriculumTopic(weekNumber);
+
+    if (curriculumEntry?.is_review_week) {
+      const quarter = getQuarterForWeek(weekNumber);
+      const curriculum = await db.getCurriculum(new Date().getFullYear());
+      const quarterTopicIds = curriculum
+        .filter(w => w.quarter === quarter && w.topic_id && !w.is_review_week)
+        .map(w => w.topic_id);
+      const quarterTopics = topics.filter(t => quarterTopicIds.includes(t.id));
+      return {
+        primaryTopic: quarterTopics[0] || topics[0],
+        reviewTopics: quarterTopics.slice(1),
+        isReviewWeek: true,
+      };
+    }
+
+    if (topic) {
+      const others = topics.filter(t => t.id !== topic.id);
+      const reviewTopics = sample(others, Math.min(5, others.length));
+      return { primaryTopic: topic, reviewTopics, isReviewWeek: false };
+    }
+  } catch (e) {
+    console.warn('[Test] Curriculum lookup failed, falling back to hash:', e.message);
+  }
+
+  const str = `${userId}:${weekNumber}`;
+  let hash = 0;
+  for (let i = 0; i < str.length; i++) {
+    hash = (hash << 5) - hash + str.charCodeAt(i);
+    hash |= 0;
+  }
+  const primaryIndex = Math.abs(hash) % topics.length;
+  const primaryTopic = topics[primaryIndex];
+
+  const others = topics.filter((_, i) => i !== primaryIndex);
+  const reviewTopics = sample(others, Math.min(5, others.length));
+
+  return { primaryTopic, reviewTopics, isReviewWeek: false };
+}
+
+export async function getCachedQuiz(userId, weekNumber) {
+  return db.getCachedQuiz(userId, weekNumber);
+}
+
+export async function forceGenerateTopicQuestions(topic, count = 5) {
+  const existingBank = await db.getQuizBank(topic.id);
+  const existingKeys = new Set(existingBank.map((q) => normalizeQuestionText(q.question)));
+
+  let lastQualityError = null;
+  let candidates = null;
+
+  for (let attempt = 0; attempt < 3; attempt++) {
+    const questions = await callQuizModel(topic, count);
+
+    const qualityError = validateBatchQuality(questions);
+    if (qualityError) {
+      lastQualityError = qualityError;
+      console.warn(`[quiz] batch rejected (attempt ${attempt + 1}): ${qualityError}`);
+      continue;
+    }
+
+    const dominant = dominantCorrectIndex(questions);
+    if (dominant && attempt < 2) {
+      console.warn(`[quiz] correctIndex dominated by ${dominant.index} (${Math.round(dominant.ratio * 100)}%) — re-rolling`);
+      continue;
+    }
+
+    candidates = questions;
+    break;
+  }
+
+  if (!candidates) {
+    throw new Error(`Quality gate rejected the generated batch for ${topic.label}: ${lastQualityError || 'unbalanced answer distribution'}. Click "Generate" to try again.`);
+  }
+
+  const accepted = [];
+  for (const q of candidates) {
+    const key = normalizeQuestionText(q.question);
+    if (existingKeys.has(key)) {
+      console.debug('[quiz] dropped duplicate:', q.question);
+      continue;
+    }
+    existingKeys.add(key);
+    accepted.push({
+      ...q,
+      id: `${topic.id}-${Math.random().toString(36).slice(2, 11)}`,
+    });
+  }
+
+  if (!accepted.length) {
+    throw new Error(`All generated questions for ${topic.label} were duplicates of existing ones.`);
+  }
+
+  const merged = [...existingBank, ...accepted];
+  await db.setQuizBank(topic.id, merged);
+  return accepted;
 }
 
 async function getOrGenerateTopicQuestions(topic, count) {
   let bank = await db.getQuizBank(topic.id);
 
   if (bank.length < count) {
-    await forceGenerateTopicQuestions(topic, 10);
+    await forceGenerateTopicQuestions(topic, 5);
     bank = await db.getQuizBank(topic.id);
   }
 
-  const shuffled = [...bank].sort(() => 0.5 - Math.random());
-  return shuffled.slice(0, Math.min(count, shuffled.length));
+  return sample(bank, Math.min(count, bank.length));
 }
 
 export async function getTopicQuestionBank(topicId) {
@@ -151,10 +240,10 @@ export async function generateWeeklyQuiz(userId, weekNumber, force = false) {
     }
   }
 
-  questions.sort(() => 0.5 - Math.random());
+  const shuffled = shuffle(questions);
 
   const quiz = {
-    questions,
+    questions: shuffled,
     meta: {
       userId,
       weekNumber,