Update app.py

app.py

@@ -31,12 +31,6 @@ class BasicAgent:
             to be put in the list is a number or a string."""
         )
 
-
-@app.get("/questions")
-    def get_questions():
-    with open("questions.json", "r") as f:
-        return JSONResponse(content=json.load(f))
-
     def format_final_answer(self, answer: str) -> str:
         cleaned = " ".join(answer.split())
         return f"FINAL ANSWER: {cleaned}"
@@ -142,13 +136,11 @@ def question_scorer(model_answer: str, ground_truth: str) -> bool:
     if model_answer is None:
         model_answer = "None"
 
-    # Case 1: Ground truth is numeric
     if is_float(ground_truth):
         print(f"Evaluating '{model_answer}' as a number.")
         normalized = normalize_number_str(model_answer)
         return normalized == float(ground_truth) if normalized is not None else False
 
-    # Case 2: Ground truth is a list
     elif any(char in ground_truth for char in [",", ";"]):
         print(f"Evaluating '{model_answer}' as a comma/semicolon-separated list.")
         gt_elems = split_string(ground_truth)
@@ -168,11 +160,10 @@ def question_scorer(model_answer: str, ground_truth: str) -> bool:
                     return False
         return True
 
-    # Case 3: Ground truth is a plain string
     else:
         print(f"Evaluating '{model_answer}' as a string.")
         return normalize_str(model_answer) == normalize_str(ground_truth)
-    
+
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
     if profile:
@@ -217,7 +208,7 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
 
     if not answers_payload:
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log) 
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
     submission_data = {
         "username": username.strip(),
         "agent_code": agent_code,
@@ -239,7 +230,6 @@ def run_and_submit_all(profile: gr.OAuthProfile | None):
         return final_status, pd.DataFrame(results_log)
     except Exception as e:
         return f"Submission Failed: {e}", pd.DataFrame(results_log)
-    print(question_scorer("FINAL ANSWER: right",submitted_answer))
 
 # --- Build Gradio Interface ---
 with gr.Blocks() as demo:
@@ -256,4 +246,4 @@ with gr.Blocks() as demo:
 
 if __name__ == "__main__":
     print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+    demo.launch(debug=True, share=False)