feat: MI50 as a Lyra backend (OpenAI-compatible local GPU)

The MI50 box (CT202) runs an OpenAI-compatible llama.cpp server on
10.0.0.44:8080. Wire it in as a third backend:

- llm.complete gains backend="mi50" (OpenAI client pointed at MI50_BASE_URL)
- config: MI50_BASE_URL (default http://10.0.0.44:8080/v1) + MI50_MODEL
- chat.respond labels the model per backend; web _backend_for maps "mi50"
- UI backend selector adds "MI50 — local GPU"

Verified end-to-end: llm.complete(backend="mi50") returns from the live server.
See homelab-inference memory for the box topology.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.env.example

@@ -2,6 +2,10 @@
 LOCAL_BASE_URL=http://localhost:11434
 LOCAL_MODEL=qwen2.5:7b-instruct
 
+# MI50 backend — OpenAI-compatible llama.cpp server on the home-lab GPU box.
+MI50_BASE_URL=http://10.0.0.44:8080/v1
+MI50_MODEL=local-gpu
+
 # Cloud backend (OpenAI) — higher quality, costs money.
 OPENAI_API_KEY=
 CLOUD_MODEL=gpt-4o-mini