Pull intent model on startup alongside main model

If OLLAMA_INTENT_MODEL is configured and differs from OLLAMA_MODEL,
both are pulled concurrently as fire-and-forget tasks at startup.
Deduplicates via a set so pulling the same model twice is never attempted.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

src/fabledassistant/app.py

@@ -93,18 +93,23 @@ def create_app() -> Quart:
         start_log_retention_loop()
         start_notification_loop()
 
-        async def _pull_model():
+        async def _pull_model(model: str) -> None:
             try:
-                await ensure_model(Config.OLLAMA_MODEL)
+                await ensure_model(model)
             except Exception:
                 logger.warning(
                     "Failed to ensure model '%s' — chat may not work until model is available",
-                    Config.OLLAMA_MODEL,
+                    model,
                     exc_info=True,
                 )
 
-        # Fire-and-forget so model pull doesn't block startup
+        # Pull main model and (if configured) a separate intent model concurrently.
-        asyncio.create_task(_pull_model())
+        # Fire-and-forget so pulls don't block startup.
+        models_to_pull = {Config.OLLAMA_MODEL}
+        if Config.OLLAMA_INTENT_MODEL and Config.OLLAMA_INTENT_MODEL != Config.OLLAMA_MODEL:
+            models_to_pull.add(Config.OLLAMA_INTENT_MODEL)
+        for _model in models_to_pull:
+            asyncio.create_task(_pull_model(_model))
 
     @app.route("/")
     async def serve_index():