Update app.py

app.py

@@ -1,241 +1,369 @@
-""" Basic Agent Evaluation Runner"""
+# """ Basic Agent Evaluation Runner"""
+# import os
+# import re
+# import inspect
+# import gradio as gr
+# import requests
+# import pandas as pd
+# from langchain_core.messages import HumanMessage
+# from agent import build_graph
+
+
+
+# # (Keep Constants as is)
+# # --- Constants ---
+# DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+
+# # --- Basic Agent Definition ---
+# # ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+
+
+# class BasicAgent:
+#     """A langgraph agent with debug logging."""
+#     def __init__(self):
+#         print("BasicAgent initialized.")
+#         self.graph = build_graph()
+
+#     def __call__(self, question: str) -> str:
+#         print(f"\n📥 Question → {repr(question)}")
+#         messages = [HumanMessage(content=question)]
+#         response = self.graph.invoke({"messages": messages})
+
+#         raw_output = response["messages"][-1].content
+#         print("📦 Raw model output →", repr(raw_output))
+
+#         import re
+#         match = re.search(r"FINAL ANSWER:\s*(.+)", raw_output, re.IGNORECASE)
+#         if match:
+#             final_answer = match.group(1).strip()
+#         else:
+#             final_answer = raw_output.strip()
+#             print("⚠️ Output missing 'FINAL ANSWER:' prefix. Using fallback.")
+
+#         print("✅ Final parsed answer:", repr(final_answer))
+#         return final_answer
+
+
+
+
+
+# def run_and_submit_all( profile: gr.OAuthProfile | None):
+#     """
+#     Fetches all questions, runs the BasicAgent on them, submits all answers,
+#     and displays the results.
+#     """
+#     # --- Determine HF Space Runtime URL and Repo URL ---
+#     space_id = os.getenv("SPACE_ID", "").strip()
+#  # Get the SPACE_ID for sending link to the code
+
+#     if profile:
+#         username= f"{profile.username.strip()}"
+#         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"
+
+#     # 1. Instantiate Agent ( modify this part to create your agent)
+#     try:
+#         agent = BasicAgent()
+#     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"
+    
+#     agent_code = agent_code.strip()
+
+#     print(agent_code)
+
+#     # 2. Fetch Questions
+#     print(f"Fetching questions from: {questions_url}")
+#     try:
+#         response = requests.get(questions_url, 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
+#     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})
+#         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}"})
+
+#     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 
+#     print("Sanitized submission preview:")
+#     print("username ��", repr(username))
+#     print("agent_code →", repr(agent_code))
+#     for a in answers_payload[:3]:  # Show first few answers
+#         print("sample answer →", repr(a))
+
+
+#     submission_data = {
+#     "username": username.strip(),
+#     "agent_code": agent_code.strip(),  # <<< prevent newline issues here too
+#     "answers": answers_payload
+# }
+#     status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
+#     print(status_update)
+#     import json
+#     print("📤 SUBMISSION PAYLOAD →", json.dumps(submission_data, indent=2))
+
+#     # 5. Submit
+#     print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
+#     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.')}"
+#         )
+#         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
+#     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
+
+
+# # --- 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.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
+#     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__":
+#     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
+
+#     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)
+
 import os
-import re
-import inspect
 import gradio as gr
 import requests
 import pandas as pd
 from langchain_core.messages import HumanMessage
 from agent import build_graph
+import json
+import re
 
-
-
-# (Keep Constants as is)
-# --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-
 
 class BasicAgent:
-    """A langgraph agent with debug logging."""
+    """LangGraph agent with enhanced debug logging and answer sanitization."""
     def __init__(self):
-        print("BasicAgent initialized.")
+        print("🧠 Initializing BasicAgent...")
         self.graph = build_graph()
 
     def __call__(self, question: str) -> str:
-        print(f"\n📥 Question → {repr(question)}")
+        print(f"\n📥 Received question: {repr(question)}")
         messages = [HumanMessage(content=question)]
         response = self.graph.invoke({"messages": messages})
-
         raw_output = response["messages"][-1].content
-        print("📦 Raw model output →", repr(raw_output))
+        print("📦 Raw LLM output:", repr(raw_output))
 
-        import re
         match = re.search(r"FINAL ANSWER:\s*(.+)", raw_output, re.IGNORECASE)
         if match:
             final_answer = match.group(1).strip()
         else:
             final_answer = raw_output.strip()
-            print("⚠️ Output missing 'FINAL ANSWER:' prefix. Using fallback.")
-
-        print("✅ Final parsed answer:", repr(final_answer))
-        return final_answer
-
+            print("⚠️ 'FINAL ANSWER:' prefix missing. Using fallback.")
 
+        # Sanitize for newline bugs
+        clean_answer = final_answer.replace("\n", " ").replace("\r", " ").strip()
+        print("✅ Final cleaned answer:", repr(clean_answer))
+        return clean_answer
 
 
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
+def run_and_submit_all(profile: gr.OAuthProfile | None):
     space_id = os.getenv("SPACE_ID", "").strip()
- # Get the SPACE_ID for sending link to the code
 
     if profile:
-        username= f"{profile.username.strip()}"
-        print(f"User logged in: {username}")
+        username = f"{profile.username.strip()}"
+        print(f"🙋 User logged in: {username}")
     else:
-        print("User not logged in.")
-        return "Please Login to Hugging Face with the button.", None
+        return "⚠️ Please log in to Hugging Face first.", None
+
+    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main".strip()
+    print("🛰️ Submitting from agent_code →", repr(agent_code))
 
-    api_url = DEFAULT_API_URL
-    questions_url = f"{api_url}/questions"
-    submit_url = f"{api_url}/submit"
+    questions_url = f"{DEFAULT_API_URL}/questions"
+    submit_url = f"{DEFAULT_API_URL}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
     try:
         agent = BasicAgent()
     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)
-    
+        return f"🚫 Failed to initialize agent: {e}", None
 
-    agent_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
-    
-    agent_code = agent_code.strip()
-
-    print(agent_code)
-
-    # 2. Fetch Questions
-    print(f"Fetching questions from: {questions_url}")
+    print(f"📡 Fetching questions from → {questions_url}")
     try:
         response = requests.get(questions_url, 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
+        return f"❌ Failed to fetch questions: {e}", None
 
-    # 3. Run your Agent
     results_log = []
     answers_payload = []
-    print(f"Running agent on {len(questions_data)} questions...")
+    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}")
+        if not task_id or not question_text:
             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})
+            answer = agent(question_text)
+            # Check for newlines explicitly
+            if "\n" in answer:
+                print(f"⚠️ Found newline in answer [{task_id}] →", repr(answer))
+            answers_payload.append({"task_id": task_id.strip(), "submitted_answer": answer})
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": answer})
         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}"})
+            err_msg = f"AGENT ERROR: {e}"
+            results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": err_msg})
 
     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)
+        return "🚫 Agent produced no valid answers.", pd.DataFrame(results_log)
 
-    # 4. Prepare Submission 
-    print("Sanitized submission preview:")
-    print("username →", repr(username))
-    print("agent_code →", repr(agent_code))
-    for a in answers_payload[:3]:  # Show first few answers
-        print("sample answer →", repr(a))
+    submission_data = {
+        "username": username,
+        "agent_code": agent_code,
+        "answers": answers_payload
+    }
 
+    print("\n📤 SUBMISSION PAYLOAD:")
+    print(json.dumps(submission_data, indent=2))
 
-    submission_data = {
-    "username": username.strip(),
-    "agent_code": agent_code.strip(),  # <<< prevent newline issues here too
-    "answers": answers_payload
-}
-    status_update = f"Agent finished. Submitting {len(answers_payload)} answers for user '{username}'..."
-    print(status_update)
-    import json
-    print("📤 SUBMISSION PAYLOAD →", json.dumps(submission_data, indent=2))
-
-    # 5. Submit
-    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     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.')}"
+        result = response.json()
+        summary = (
+            f"✅ Submission Successful!\n"
+            f"User: {result.get('username')}\n"
+            f"Score: {result.get('score', 'N/A')}% "
+            f"({result.get('correct_count', '?')}/{result.get('total_attempted', '?')})\n"
+            f"Message: {result.get('message', 'No message returned.')}"
         )
-        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
+        return summary, 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 Evaluation Runner with Debug Mode")
+    gr.Markdown("Log in, run your agent, submit answers, and review results with logging enabled.")
     gr.LoginButton()
-
     run_button = gr.Button("Run Evaluation & Submit All Answers")
+    status_output = gr.Textbox(label="Status / Result", lines=4)
+    results_table = gr.DataFrame(label="QA Log")
 
-    status_output = gr.Textbox(label="Run Status / Submission Result", lines=5, interactive=False)
-    # Removed max_rows=10 from DataFrame constructor
-    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
-
-    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("🚀 Launching Gradio app...")
+    demo.launch(debug=True, share=False)