feat: Refine model fallback messaging to reflect reality. (#1527)

docs/cli/authentication.md

@@ -8,7 +8,7 @@ The Gemini CLI requires you to authenticate with Google's AI services. On initia
     - During initial startup, Gemini CLI will direct you to a webpage for authentication. Once authenticated, your credentials will be cached locally so the web login can be skipped on subsequent runs.
     - Note that the web login must be done in a browser that can communicate with the machine Gemini CLI is being run from. (Specifically, the browser will be redirected to a localhost url that Gemini CLI will be listening on).
 
-2.  **Gemini API key:**
+2.  **<a id="gemini-api-key"></a>Gemini API key:**
 
     - Obtain your API key from Google AI Studio: [https://aistudio.google.com/app/apikey](https://aistudio.google.com/app/apikey)
     - Set the `GEMINI_API_KEY` environment variable. In the following methods, replace `YOUR_GEMINI_API_KEY` with the API key you obtained from Google AI Studio:

packages/cli/src/ui/App.tsx

@@ -241,7 +241,9 @@ const App = ({ config, settings, startupWarnings = [] }: AppProps) => {
       addItem(
         {
           type: MessageType.INFO,
-          text: `⚡ Rate limiting detected. Automatically switching from ${currentModel} to ${fallbackModel} for faster responses for the remainder of this session.`,
+          text: `⚡ Slow response times detected. Automatically switching from ${currentModel} to ${fallbackModel} for faster responses for the remainder of this session.
+⚡ To avoid this you can utilize a Gemini API Key. See: https://goo.gle/gemini-cli-docs-auth#gemini-api-key
+⚡ You can switch authentication methods by typing /auth`,
         },
         Date.now(),
       );