fix: set OLLAMA_HOST explicitly for model pull

- ollama pull failed because the CLI didn't know where the server was
- Uses OLLAMA_HOST=http://127.0.0.1:11434 to connect regardless of user

install.sh

@@ -199,12 +199,9 @@ case "$AI_CHOICE" in
             sleep 2
         done
         info "Pulling model $AI_MODEL (this may take a while)..."
-        # Pull as the ollama user so models are in the right place
-        if id -u ollama &>/dev/null; then
-            sudo -u ollama ollama pull "$AI_MODEL" 2>&1 | tail -3
-        else
-            ollama pull "$AI_MODEL" 2>&1 | tail -3
-        fi
+        # Pull explicitly via the API URL so it works regardless of which user
+        # runs the command (the Ollama service listens on 127.0.0.1:11434)
+        sudo_if sh -c "OLLAMA_HOST=http://127.0.0.1:11434 ollama pull $AI_MODEL" 2>&1 | tail -3
         AI_BASE_URL="http://localhost:11434"
         ;;
     *)