feat: US-013 - Self-host ONNX embedding model

Download all-MiniLM-L6-v2 model files to public/models/ and configure
@xenova/transformers to load from local path instead of Hugging Face CDN.
Eliminates external dependency for semantic search embedding model.

scripts/generate-embeddings.ts

@@ -1,8 +1,12 @@
 import { writeFileSync } from 'node:fs'
 import { resolve } from 'node:path'
-import { pipeline } from '@xenova/transformers'
+import { env, pipeline } from '@xenova/transformers'
 import { buildEmbeddingTexts } from '@/lib/search'
 
+// Use local model files from public/models/ (same files the browser uses)
+env.localModelPath = resolve(import.meta.dirname, '..', 'public', 'models')
+env.allowRemoteModels = false
+
 async function main() {
   const items = buildEmbeddingTexts()
   console.log(`Found ${items.length} items to embed.`)