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.

src/lib/embedding-model.ts

@@ -1,4 +1,9 @@
-import { pipeline, type FeatureExtractionPipeline } from '@xenova/transformers'
+import { env, pipeline, type FeatureExtractionPipeline } from '@xenova/transformers'
+
+// Serve model files from /models/ (Vite serves public/ at root)
+env.localModelPath = '/models/'
+env.allowRemoteModels = false
+env.useBrowserCache = false
 
 let extractor: FeatureExtractionPipeline | null = null
 let loading = false