Fix agent with corrected system_prompt injection

app.py

@@ -1,196 +1,153 @@
-import os
+import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
 
-# (Keep Constants as is)
-# --- Constants ---
-DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+from smolagents import (
+    CodeAgent,
+    DuckDuckGoSearchTool,
+    InferenceClientModel,
+    tool,
+)
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
-    def __init__(self):
-        print("BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-def run_and_submit_all( profile: gr.OAuthProfile | None):
+@tool
+def download_file_from_task(task_id: str) -> str:
     """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
+    Downloads a file associated with a GAIA task and returns its content as text.
+    Use this when a question references an attached file.
+    Args:
+        task_id: The task ID string of the GAIA question.
     """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
-
-    if profile:
-        username= f"{profile.username}"
-        print(f"User logged in: {username}")
-    else:
-        print("User not logged in.")
-        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"
+    url = f"{DEFAULT_API_URL}/files/{task_id}"
+    try:
+        response = requests.get(url, timeout=30)
+        response.raise_for_status()
+        try:
+            text = response.content.decode("utf-8")
+            if len(text) > 8000:
+                text = text[:8000] + "\n[... truncated ...]"
+            return text
+        except UnicodeDecodeError:
+            return f"Binary file. Size: {len(response.content)} bytes."
+    except Exception as e:
+        return f"Error downloading file: {e}"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+@tool
+def python_calculator(code: str) -> str:
+    """
+    Executes a Python expression and returns the result.
+    Use for arithmetic, unit conversions, date calculations.
+    Args:
+        code: A Python expression to evaluate (e.g. '2 ** 10')
+    """
+    import math, datetime
+    allowed = {"__builtins__": {}, "math": math, "datetime": datetime,
+               "abs": abs, "round": round, "int": int, "float": float,
+               "str": str, "len": len, "sum": sum, "min": min, "max": max,
+               "sorted": sorted, "range": range, "list": list, "dict": dict,
+               "set": set, "zip": zip, "enumerate": enumerate}
+    try:
+        return str(eval(code, allowed))
+    except Exception as e:
+        return f"Error: {e}"
+
+SYSTEM_PROMPT = """You are an expert research assistant answering GAIA benchmark questions.
+CRITICAL RULES:
+1. Your final answer must be EXACT and CONCISE. No explanations, no sentences.
+2. If the answer is a number, return ONLY the number.
+3. If the answer is a name, return ONLY the name.
+4. If the answer is a list, return items separated by commas.
+5. If a question references a file, use download_file_from_task with the task_id.
+6. Always search the web for factual questions.
+7. Never include FINAL ANSWER in your response.
+8. Match the exact format requested in the question.
+"""
+
+def build_agent():
+    model = InferenceClientModel(
+        model_id="Qwen/Qwen2.5-72B-Instruct",
+        max_tokens=2048,
+        temperature=0.1,
+    )
+    agent = CodeAgent(
+        model=model,
+        tools=[DuckDuckGoSearchTool(), download_file_from_task, python_calculator],
+        max_steps=8,
+        verbosity_level=1,
+        additional_authorized_imports=["math", "datetime", "re", "json", "csv", "io"],
+    )
+    agent.prompt_templates["system_prompt"] = SYSTEM_PROMPT + "\n\n" + agent.prompt_templates["system_prompt"]
+    return agent
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    space_id = os.getenv("SPACE_ID")
+    if not profile:
+        return "Please login to Hugging Face first.", None
+    username = profile.username
+    print(f"User logged in: {username}")
     try:
-        agent = BasicAgent()
+        agent = build_agent()
     except Exception as e:
-        print(f"Error instantiating agent: {e}")
         return f"Error initializing agent: {e}", None
-    # In the case of an app running as a hugging Face space, this link points toward your codebase ( usefull for others so please keep it public)
     agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=15)
+        response = requests.get(f"{DEFAULT_API_URL}/questions", timeout=15)
         response.raise_for_status()
         questions_data = response.json()
-        if not questions_data:
-             print("Fetched questions list is empty.")
-             return "Fetched questions list is empty or invalid format.", None
-        print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
-
-    # 3. Run your Agent
+        return f"Error fetching questions: {e}", None
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
     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:
-            print(f"Skipping item with missing task_id or question: {item}")
             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})
+            submitted_answer = str(agent.run(f"[task_id: {task_id}]\n\n{question_text}")).strip()
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
-
+            submitted_answer = f"AGENT ERROR: {e}"
+        answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
+        results_log.append({"Task ID": task_id, "Question": question_text[:120], "Submitted Answer": submitted_answer})
     if not answers_payload:
-        print("Agent did not produce any answers to submit.")
-        return "Agent did not produce any answers to submit.", pd.DataFrame(results_log)
-
-    # 4. Prepare Submission 
-    submission_data = {"username": username.strip(), "agent_code": agent_code, "answers": answers_payload}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+        return "Agent produced no answers.", pd.DataFrame(results_log)
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=60)
+        response = requests.post(f"{DEFAULT_API_URL}/submit",
+            json={"username": username.strip(), "agent_code": agent_code, "answers": answers_payload},
+            timeout=120)
         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.')}"
-        )
-        print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
-    except requests.exceptions.HTTPError as e:
-        error_detail = f"Server responded with status {e.response.status_code}."
-        try:
-            error_json = e.response.json()
-            error_detail += f" Detail: {error_json.get('detail', e.response.text)}"
-        except requests.exceptions.JSONDecodeError:
-            error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        r = response.json()
+        return (f"Submission Successful!\nUser: {r.get('username')}\n"
+                f"Score: {r.get('score')}% ({r.get('correct_count')}/{r.get('total_attempted')} correct)\n"
+                f"Message: {r.get('message')}"), pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-
+        return f"Submission Failed: {e}", pd.DataFrame(results_log)
 
-# --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
-    gr.Markdown(
-        """
-        **Instructions:**
-
-        1.  Please clone this space, then modify the code to define your agent's logic, the tools, the necessary packages, etc ...
-        2.  Log in to your Hugging Face account using the button below. This uses your HF username for submission.
-        3.  Click 'Run Evaluation & Submit All Answers' to fetch questions, run your agent, submit answers, and see the score.
-
-        ---
-        **Disclaimers:**
-        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.
-        """
-    )
-
+    gr.Markdown("# GAIA Agent - Unit 4 Final Assignment")
+    gr.Markdown("""
+    1. Log in with your Hugging Face account.
+    2. Click Run Evaluation to start the agent on all 20 GAIA questions.
+    3. Target: >= 30% to earn the certificate.
+    """)
     gr.LoginButton()
-
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
-
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
+    run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
+    status_output = gr.Textbox(label="Submission Result", lines=6, 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]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
     print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
-
+    space_id_startup = os.getenv("SPACE_ID")
     if space_host_startup:
-        print(f"✅ SPACE_HOST found: {space_host_startup}")
-        print(f"   Runtime URL should be: https://{space_host_startup}.hf.space")
-    else:
-        print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
-
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
-        print(f"✅ SPACE_ID found: {space_id_startup}")
-        print(f"   Repo URL: https://huggingface.co/spaces/{space_id_startup}")
-        print(f"   Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
-    else:
-        print("ℹ️  SPACE_ID environment variable not found (running locally?). Repo URL cannot be determined.")
-
-    print("-"*(60 + len(" App Starting ")) + "\n")
-
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
-    demo.launch(debug=True, share=False)
+        print(f"SPACE_HOST: {space_host_startup}")
+    if space_id_startup:
+        print(f"SPACE_ID: {space_id_startup}")
+        print(f"Repo URL: https://huggingface.co/spaces/{space_id_startup}")
+        print(f"Repo Tree URL: https://huggingface.co/spaces/{space_id_startup}/tree/main")
+    print("-"*74 + "\n")
+    print("Launching Gradio Interface...")
+    demo.launch(debug=True, share=False)