feat: add llama-server-fast, a small non-thinking classifier model

Second, always-resident llama.cpp instance (Qwen3-4B-Instruct-2507,
Q8_0 GGUF, ~5GB VRAM) alongside the existing Qwen3.8-27B instance, for
use as qwen-code CLI's Auto Mode classifier fastModel. Model choice
researched in docs/research/fast-model-choice.md: architecturally
non-thinking (unlike Qwen3-1.7B/0.6B), --reasoning off added
defensively per a known (closed) llama.cpp misdetection bug.

- docker-compose.yml: llama-server-fast + downloader-fast services,
  omniroute depends_on updated
- .env.example: LLAMA_FAST_* vars
- scripts/update.sh: runs the new downloader profile

Refs #44

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MrnMEdzeQzqZE5soVEXPCx

scripts/update.sh

@@ -88,6 +88,7 @@ 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-fast
 
 echo "==> bringing up omniroute"
 docker compose up -d --wait omniroute