Update app.py

app.py

@@ -25,7 +25,7 @@ def summarize_query(query: str) -> str:
 
 search_tool = DuckDuckGoSearchTool()
 
-# --- System Prompt for ReACT + Scratchpad + Auto-Retry ---
+# --- System Message for ReACT + Scratchpad + Auto-Retry ---
 
 system_message = """
 You are a ReACT agent with scratchpad memory and a retry mechanism.
@@ -50,26 +50,14 @@ Formatting Rules:
 - Numbers: plain (no commas unless list)
 - Strings: no articles unless inside proper names
 - Lists: comma-separated without extra punctuation
-
-Example scratchpad flow:
-Thought: Need fruits from painting.
-Action: DuckDuckGoSearchTool('fruits in Embroidery from Uzbekistan painting')
-Observation: (empty)
-Thought: Unclear result, retry.
-Action: summarize_query('fruits in Embroidery painting Uzbekistan')
-Observation: pomegranate, apple, grape
-Thought: Find breakfast fruits.
-Action: DuckDuckGoSearchTool('breakfast menu October 1949 SS Ile de France')
-Observation: grapes, apples, oranges
-Thought: Overlap is grapes and apples.
-FINAL ANSWER: grapes, apples
 """
 
 # --- Build the Smart Agent ---
 
 smart_agent = CodeAgent(
     tools=[search_tool, summarize_query],
-    model=HfApiModel(system_message=system_message)  # <-- key fix here
+    model=HfApiModel(),                 # no prompt here
+    system_message=system_message       # moved into CodeAgent
 )
 
 # --- Integrate into Gradio App ---
@@ -80,121 +68,71 @@ class BasicAgent:
 
     def __call__(self, question: str) -> str:
         print(f"Agent received question (first 50 chars): {question[:50]}...")
-        answer = smart_agent.run(question)
-        print(f"Agent returning answer: {answer}")
-        return answer
+        return smart_agent.run(question)
 
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID")
-
     if profile:
         username = profile.username
-        print(f"User logged in: {username}")
     else:
-        print("User not logged in.")
         return "Please log in to Hugging Face using the button above.", 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 = BasicAgent()
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
 
     # Fetch questions
     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.", None
+        resp = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
+        resp.raise_for_status()
+        questions = resp.json()
+        if not questions:
+            return "No questions fetched.", None
     except Exception as e:
         return f"Error fetching questions: {e}", None
 
-    # Run agent on each question
-    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:
+    # Run agent
+    logs, payload = [], []
+    for item in questions:
+        tid = item.get("task_id")
+        q = item.get("question")
+        if not tid or q is None:
             continue
         try:
-            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
-            })
+            ans = agent(q)
         except Exception as e:
-            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)
-
-    # Submit answers
-    submission_data = {
-        "username": username,
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
+            ans = f"AGENT ERROR: {e}"
+        logs.append({"Task ID": tid, "Question": q, "Submitted Answer": ans})
+        payload.append({"task_id": tid, "submitted_answer": ans})
+
+    if not payload:
+        return "Agent did not produce any answers to submit.", pd.DataFrame(logs)
+
+    # Submit
+    sub = {"username": username, "agent_code": agent_code, "answers": payload}
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-        final_status = (
+        r = requests.post(f"{DEFAULT_API_URL}/submit", json=sub, timeout=60)
+        r.raise_for_status()
+        res = r.json()
+        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', '?')}/"
-            f"{result_data.get('total_attempted', '?')} correct)\n"
-            f"Message: {result_data.get('message', '')}"
+            f"User: {res.get('username')}\n"
+            f"Score: {res.get('score', 'N/A')}% "
+            f"({res.get('correct_count', '?')}/{res.get('total_attempted', '?')})"
         )
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        return status, pd.DataFrame(logs)
     except Exception as e:
-        results_df = pd.DataFrame(results_log)
-        return f"Submission Failed: {e}", results_df
+        return f"Submission Failed: {e}", pd.DataFrame(logs)
 
-# --- Gradio Interface ---
+# --- Gradio UI ---
 
 with gr.Blocks() as demo:
     gr.Markdown("# SmolAgent GAIA Evaluation Runner 🚀")
-    gr.Markdown(
-        """
-        **Instructions:**
-        1. Clone this space and modify if needed.
-        2. Log in to Hugging Face.
-        3. Click 'Run Evaluation & Submit All Answers'.
-        **Note:** Evaluation can take a few minutes.
-        """
-    )
+    gr.Markdown("1. Clone this space  2. Log in  3. Click **Run Evaluation & Submit All Answers**")
     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]
-    )
+    btn = gr.Button("Run Evaluation & Submit All Answers")
+    out_status = gr.Textbox(label="Status", lines=5, interactive=False)
+    out_table  = gr.DataFrame(label="Results")
+    btn.click(fn=run_and_submit_all, outputs=[out_status, out_table])
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    space_host = os.getenv("SPACE_HOST")
-    space_id = os.getenv("SPACE_ID")
-    if space_host:
-        print(f"SPACE_HOST: {space_host}")
-    if space_id:
-        print(f"SPACE_ID: {space_id}")
-    print("Launching Gradio Interface...")
     demo.launch(debug=True, share=False)