Freezmo: self-hosted notes-to-activities study app

Next.js 15 app that turns photos, PDFs, DOCX/PPTX and text into a swipeable
feed of AI-generated activities (flashcards, multiple choice, true/false,
fill-in-the-blank, matching, ordering, short answer) using the user's own
Ollama models.

Highlights:
- All AI calls run in server route handlers; the browser never talks to Ollama.
- Bring-your-own-key mode (default): the key lives only in the browser and is
  sent per-request; server, local-daemon and shared-key modes also supported.
- Client-side document extraction (pdf.js, mammoth, jszip) with scanned-PDF
  page rendering for the vision model; notes stay in their original language.
- ChatGPT-style shell: collapsible sidebar / mobile drawer, neutral token-based
  light + dark themes, folder organisation, PWA (manifest, SW, offline page).
- Strict JSON validation with zod + auto-repair, rate limiting, and request
  guards (cross-origin, body-size, API-key sanitising).
- setup.sh bootstraps deps, .env.local and a production build.

Gitignore excludes .env*, the generated pdf.js worker and local scratch files.

lib/xp.ts

@@ -0,0 +1,26 @@
+import type { Difficulty } from "./schemas";
+
+/**
+ * Base XP for a correct answer. Harder decks are worth more, and the
+ * multi-part activity types get a small bonus.
+ */
+export const XP_BY_DIFFICULTY: Record<Difficulty, number> = {
+  easy: 10,
+  medium: 15,
+  hard: 20,
+};
+
+const TYPE_BONUS: Record<string, number> = {
+  matching: 5,
+  ordering: 5,
+  short_answer: 5,
+};
+
+export function xpForActivity(type: string, difficulty: Difficulty): number {
+  return XP_BY_DIFFICULTY[difficulty] + (TYPE_BONUS[type] ?? 0);
+}
+
+/** Consecutive-correct streak multiplier (capped at 3x). */
+export function streakMultiplier(streak: number): number {
+  return Math.min(1 + Math.max(0, streak) * 0.1, 3);
+}