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.

next.config.ts

@@ -1,7 +1,22 @@
 import type { NextConfig } from "next";
 
+/**
+ * Freezmo is meant to be opened from a phone on the same network, so the dev
+ * server (which binds 0.0.0.0:3207) should accept dev-asset requests coming
+ * from private hostnames. Production builds are not affected by this option.
+ *
+ * Add your own hostname here if Next still warns about a cross-origin request.
+ */
 const nextConfig: NextConfig = {
-  /* config options here */
+  allowedDevOrigins: [
+    "127.0.0.1",
+    "localhost",
+    "*.local",
+    "**.local",
+    "192.168.*.*",
+    "10.*.*.*",
+    "*.ts.net", // Tailscale
+  ],
 };
 
 export default nextConfig;