Update app.py

app.py

@@ -1,18 +1,8 @@
-additional_authorized_imports=["pandas", "numpy", "datetime", "re", "json", "math"]
-
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-from smolagents import CodeAgent, DuckDuckGoSearchTool, InferenceClientModel, WikipediaSearchTool
-
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
-
-import os
 from smolagents import (
     CodeAgent,
     DuckDuckGoSearchTool,
@@ -20,20 +10,7 @@ from smolagents import (
     WikipediaSearchTool,
 )
 
-SYSTEM_HINT = (
-    "Answer with ONLY the final answer — no explanation, no units unless asked, "
-    "no leading articles. If it's a number, write digits. "
-    "If it's a list, comma-separated."
-)
-
-
-import os
-from smolagents import (
-    CodeAgent,
-    DuckDuckGoSearchTool,
-    InferenceClientModel,
-    WikipediaSearchTool,
-)
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
 GAIA_SYSTEM_PROMPT = """You are a general AI assistant. I will ask you a question. Report your thoughts, and finish your answer with the following template:
 FINAL ANSWER: [YOUR FINAL ANSWER].
@@ -45,11 +22,13 @@ If you are asked for a comma separated list, apply the above rules depending on
 
 class BasicAgent:
     def __init__(self):
+        token = os.getenv("HF_TOKEN")
+        print(f"[BasicAgent] HF_TOKEN loaded: {bool(token)}, length: {len(token) if token else 0}")
         self.agent = CodeAgent(
             tools=[DuckDuckGoSearchTool(), WikipediaSearchTool()],
             model=InferenceClientModel(
                 model_id="Qwen/Qwen2.5-Coder-32B-Instruct",
-                token=os.getenv("HF_TOKEN"),
+                token=token,
             ),
             max_steps=12,
             additional_authorized_imports=["pandas", "numpy", "datetime", "re", "json", "math"],
@@ -58,15 +37,88 @@ class BasicAgent:
     def __call__(self, question: str) -> str:
         try:
             raw = str(self.agent.run(f"{GAIA_SYSTEM_PROMPT}\n\nQuestion: {question}"))
+            print(f"[Agent raw output, first 300 chars]: {raw[:300]}")
             if "FINAL ANSWER:" in raw:
-                answer = raw.split("FINAL ANSWER:")[-1].strip()
-                answer = answer.rstrip(".").strip()
-                return answer
+                return raw.split("FINAL ANSWER:")[-1].strip().rstrip(".").strip()
             return raw.strip()
         except Exception as e:
-            print(f"Agent failed: {e}")
-            return "unable to answer"
-    
+            err = f"ERR: {type(e).__name__}: {str(e)[:200]}"
+            print(f"[Agent exception]: {err}")
+            return err
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+
+    if profile:
+        username = f"{profile.username}"
+        print(f"User logged in: {username}")
+    else:
+        return "Please Login to Hugging Face with the button.", None
+
+    api_url = DEFAULT_API_URL
+    questions_url = f"{api_url}/questions"
+    submit_url = f"{api_url}/submit"
+
+    try:
+        agent = BasicAgent()
+    except Exception as e:
+        return f"Error initializing agent: {e}", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+
+    try:
+        response = requests.get(questions_url, timeout=15)
+        response.raise_for_status()
+        questions_data = response.json()
+        if not questions_data:
+            return "Fetched questions list is empty or invalid format.", None
+    except Exception as e:
+        return f"Error fetching questions: {e}", None
+
+    results_log = []
+    answers_payload = []
+    for item in questions_data:
+        task_id = item.get("task_id")
+        question_text = item.get("question")
+        if not task_id or question_text is None:
+            continue
+        submitted_answer = agent(question_text)
+        answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+        results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
+
+    if not answers_payload:
+        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
+
+    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
+
+    try:
+        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response.raise_for_status()
+        result_data = response.json()
+        final_status = (
+            f"Submission Successful!\n"
+            f"User: {result_data.get('username')}\n"
+            f"Overall Score: {result_data.get('score', 'N/A')}% "
+            f"({result_data.get('correct_count', '?')}/{result_data.get('total_attempted', '?')} correct)\n"
+            f"Message: {result_data.get('message', 'No message received.')}"
+        )
+        return final_status, pd.DataFrame(results_log)
+    except Exception as e:
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
+
+
+with gr.Blocks() as demo:
+    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.LoginButton()
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
+    results_table = gr.DataFrame(label="Questions and Agent Answers", wrap=True)
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
+
+
+if __name__ == "__main__":
+    demo.launch(debug=True, share=False)
     
 
 def run_and_submit_all( profile: gr.OAuthProfile | None):