feat(router,inference,config): pin narration to a configured model_id

[router.narration] model_id selects which provider handles narration turns
instead of generic capability routing — lets a small/fast model own narration
while the main model keeps CHAT/STEERING.

- NarrationSettings.modelId parsed from TOML, threaded via RouterConfig
  .narrationModelId into DefaultRouterFacade.narrate (3-arg route)
- DefaultInferenceRouter: exact-id match against healthy providers, with a
  post-select health check; any miss logs WARN and falls back to capability
  routing (never fails the narration turn)
- onUserInput unchanged — only narrate uses the pinned model (tested)

apps/server/src/main/kotlin/com/correx/apps/server/Main.kt

@@ -306,6 +306,7 @@ fun main() {
                 topP = rc.narration.topP,
                 maxTokens = rc.narration.maxTokens,
             ),
+            narrationModelId = rc.narration.modelId,
         )
         return InfrastructureModule.createRouterFacade(
             eventStore = eventStore,