Finish the routing wording in the desktop docs

Two sentences still described llama.cpp routing on the loaded set after
931647a made every facade route on the advertised catalog.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
Signed-off-by: pgoode41 <pgoode41@gmail.com>

Author: pgoode41

desktop/docs/architecture.md

@@ -229,8 +229,8 @@ so both entry points validate, restart, and persist identically.
 
 The Ollama, LM Studio, and llama.cpp proxies are cluster-aware. For
 model-bearing inference, each proxy first keeps only nodes whose per-engine
-discovery inventory advertises the requested model. llama.cpp uses the **loaded**
-set, not the on-disk catalog. Empty and non-matching inventories are excluded; an
+discovery inventory advertises the requested model. Empty and non-matching
+inventories are excluded; an
 empty owner set returns a local `502`. Routing precedence within the eligible set
 is:
 

desktop/docs/services-backend.md

@@ -156,7 +156,7 @@ no managed update: the bridge refuses `update` for it rather than substituting
 an uninstall and reinstall. The desktop uses reported install support and
 ownership; external runtimes remain read-only. Downloaded cache entries remain
 distinct from runtime residency. The app endpoint is `http://127.0.0.1:8080/v1`;
-routing requires the model **loaded** on the serving node. Remote cluster
+a downloaded model loads on the first request that names it. Remote cluster
 operations use the engine manager's remote control surface where supported.
 
 ### Engine settings