Switch agent backend from Anthropic to HF Inference Providers

Uses smolagents InferenceClientModel with the logged-in user's own OAuth token (inference-api scope) instead of an Anthropic API key/Space secret.

app.py

@@ -8,7 +8,7 @@ import spaces
 
 from smolagents import (
     CodeAgent,
-    LiteLLMModel,
+    InferenceClientModel,
     WebSearchTool,
     VisitWebpageTool,
     WikipediaSearchTool,
@@ -22,7 +22,7 @@ DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 @spaces.GPU
 def _zerogpu_startup_check():
     # This Space runs on ZeroGPU hardware but the agent below only makes
-    # network calls (Claude API, web search) and never touches CUDA.
+    # network calls (HF Inference API, web search) and never touches CUDA.
     # ZeroGPU requires at least one @spaces.GPU function to be declared,
     # so this no-op satisfies that check without spending any GPU quota
     # (it is never actually invoked).
@@ -40,13 +40,17 @@ If you are asked for a comma separated list, apply the above rules to each eleme
 # --- Basic Agent Definition ---
 # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 class BasicAgent:
-    def __init__(self):
-        model_id = os.getenv("AGENT_MODEL_ID", "anthropic/claude-sonnet-4-5")
-        api_key = os.getenv("ANTHROPIC_API_KEY")
-        if not api_key:
-            print("Warning: ANTHROPIC_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)
+    def __init__(self, hf_token: str | None = None):
+        # Uses the logged-in user's own HF Inference Providers quota (via the
+        # "Sign in with Hugging Face" OAuth token, scope: inference-api).
+        # Falls back to the HF_TOKEN env var (e.g. for local testing) if no
+        # OAuth token is available.
+        model_kwargs = {"token": hf_token or os.getenv("HF_TOKEN"), "temperature": 0}
+        model_id = os.getenv("AGENT_MODEL_ID")
+        if model_id:
+            model_kwargs["model_id"] = model_id
+
+        self.model = InferenceClientModel(**model_kwargs)
         self.agent = CodeAgent(
             model=self.model,
             tools=[WebSearchTool(), VisitWebpageTool(), WikipediaSearchTool()],
@@ -76,7 +80,7 @@ class BasicAgent:
         print(f"Agent returning answer: {answer}")
         return answer
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+def run_and_submit_all( profile: gr.OAuthProfile | None, oauth_token: gr.OAuthToken | None):
     """
     Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
@@ -97,7 +101,7 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
 
     # 1. Instantiate Agent ( modify this part to create your agent)
     try:
-        agent = BasicAgent()
+        agent = BasicAgent(hf_token=oauth_token.token if oauth_token else None)
     except Exception as e:
         print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
@@ -228,7 +232,7 @@ 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 Hugging Face's Inference Providers via `smolagents`, using your own account's quota through the login below (no separate API key needed). No hardware/model access beyond your normal HF account is required.
         """
     )