feat(llm): switch to DFlash2 speculative decoding, drop qwen-classifier

Replace MTP with draft-dflash and a separate DFlash2 drafter GGUF.
Remove the qwen-classifier backend to free VRAM (GPU was at 100%).

Co-Authored-By: Claude Sonnet 5.5 <noreply@anthropic.com>

scripts/update.sh

@@ -175,7 +175,7 @@ docker compose build --pull
 
 echo "==> ensuring models are downloaded (skips already-present files)"
 docker compose --profile tools run --rm downloader
-docker compose --profile tools run --rm downloader-classifier
+docker compose --profile tools run --rm downloader-draft
 
 echo "==> bringing up omniroute"
 docker compose up -d --wait omniroute