Switch model backend from Claude to Gemini

Uses GEMINI_API_KEY (free tier) instead of ANTHROPIC_API_KEY, model_id gemini/gemini-3.6-flash via LiteLLMModel.

app.py

@@ -63,10 +63,10 @@ class RateLimiter:
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
     def __init__(self):
-        model_id = os.getenv("AGENT_MODEL_ID", "anthropic/claude-sonnet-5")
-        api_key = os.getenv("ANTHROPIC_API_KEY")
+        model_id = os.getenv("AGENT_MODEL_ID", "gemini/gemini-3.6-flash")
+        api_key = os.getenv("GEMINI_API_KEY")
         if not api_key:
-            print("Warning: ANTHROPIC_API_KEY is not set - the agent will fail to call the model.")
+            print("Warning: GEMINI_API_KEY is not set - the agent will fail to call the model.")
 
         self.model = LiteLLMModel(model_id=model_id, api_key=api_key, temperature=0)
         self.agent = CodeAgent(
@@ -251,7 +251,7 @@ with gr.Blocks() as demo:
         Once clicking on the "submit button, it can take quite some time ( this is the time for the agent to go through all the questions).
         This space provides a basic setup and is intentionally sub-optimal to encourage you to develop your own, more robust solution. For instance for the delay process of the submit button, a solution could be to cache the answers and submit in a seperate action or even to answer the questions in async.
 
-        **Setup:** This agent calls Anthropic's Claude via `smolagents`. Set the `ANTHROPIC_API_KEY` secret in this Space's settings before running.
+        **Setup:** This agent calls Google's Gemini via `smolagents`. Get a free key at https://aistudio.google.com/apikey and set it as the `GEMINI_API_KEY` secret in this Space's settings before running.
         """
     )