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>

lyra/chat.py

@@ -81,7 +81,9 @@ def build_messages(session_id: str, user_msg: str) -> list[Message]:
 def respond(session_id: str, user_msg: str, backend: Backend = "cloud") -> str:
     """Produce Lyra's reply to a single user message and persist the exchange."""
     cfg = config.load()
-    model = cfg.local_model if backend == "local" else cfg.cloud_model
+    model = {"local": cfg.local_model, "cloud": cfg.cloud_model, "mi50": cfg.mi50_model}.get(
+        backend, backend
+    )
     logbus.log(
         "info", "chat request", session=session_id, backend=backend,
         model=model, embed=cfg.embed_backend,