Update app.py

app.py

@@ -1,147 +1,322 @@
 import os
 import gradio as gr
 import requests
+import inspect
 import pandas as pd
+import json
+from agent.agent import chat_with_agent
 
+# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-class BasicAgent:
+# --- Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
+class AdvancedAgent:
     def __init__(self):
-        print("✅ BasicAgent initialized.")
-    def __call__(self, question: str) -> str:
-        print(f"🧠 Agent received question: {question[:50]}...")
-        return "This is a default answer."
-
-def run_and_submit_all(profile: gr.OAuthProfile | None):
-    space_id = os.getenv("SPACE_ID")
-
-    if profile:
-        username = profile.username
-        print(f"👤 Logged in as: {username}")
-    else:
-        print("❌ User not logged in.")
-        return "Please Login 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_code = f"https://huggingface.co/spaces/{space_id}/tree/main"
+        print("AdvancedAgent initialized with tools and capabilities.")
+        
+    def __call__(self, question: str) -> dict:
+        """
+        Process a question and return a structured response with answer and reasoning.
+        Returns: {"model_answer": "answer", "reasoning_trace": "reasoning"}
+        """
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        
+        try:
+            # Get response from the agent
+            response = chat_with_agent(question)
+            
+            # Extract the final answer from the response
+            # The agent is configured to end with "FINAL ANSWER: [answer]"
+            if "FINAL ANSWER:" in response:
+                # Extract everything after "FINAL ANSWER:"
+                final_answer = response.split("FINAL ANSWER:")[-1].strip()
+                # Remove any extra formatting or newlines
+                final_answer = final_answer.replace('\n', ' ').strip()
+            else:
+                # If no FINAL ANSWER format, use the whole response
+                final_answer = response.strip()
+            
+            # Create the reasoning trace (the full response without the final answer)
+            reasoning_trace = response.strip()
+            
+            return {
+                "model_answer": final_answer,
+                "reasoning_trace": reasoning_trace
+            }
+            
+        except Exception as e:
+            print(f"Error in agent processing: {e}")
+            return {
+                "model_answer": f"Error: {str(e)}",
+                "reasoning_trace": f"Agent encountered an error while processing the question: {str(e)}"
+            }
 
+def run_and_submit_all( profile: gr.OAuthProfile | None):
+    """
+    Fetches all questions, runs the AdvancedAgent on them, submits all answers,
+    and displays the results.
+    """
     try:
-        print(f"📥 Fetching questions from: {questions_url}")
-        response = requests.get(questions_url, timeout=15)
-        response.raise_for_status()
-        questions_data = response.json()
-
-        if not questions_data:
-            return "❌ No questions received from API.", None
+        # --- Determine HF Space Runtime URL and Repo URL ---
+        space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
 
-        # ✅ Limit to first 20 for safer UI
-        questions_data = questions_data[:20]
+        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
 
-        print(f"✅ Fetched {len(questions_data)} questions.")
-    except Exception as e:
-        return f"❌ Failed to fetch questions: {e}", None
+        api_url = DEFAULT_API_URL
+        questions_url = f"{api_url}/questions"
+        submit_url = f"{api_url}/submit"
 
-    results_log = []
-    answers_payload = []
+        # 1. Instantiate Agent ( modify this part to create your agent)
+        try:
+            agent = AdvancedAgent()
+        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" if space_id else "https://huggingface.co/spaces/your-space-id/tree/main"
+        print(agent_code)
 
-    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
+        # 2. Fetch Questions
+        print(f"Fetching questions from: {questions_url}")
         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
-            })
+            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:
-            results_log.append({
-                "Task ID": task_id,
-                "Question": question_text,
-                "Submitted Answer": f"ERROR: {e}"
-            })
-
-    if not answers_payload:
-        return "❌ Agent did not answer any questions.", pd.DataFrame(results_log)
-
-    submission_data = {
-        "username": username.strip(),
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
+            print(f"An unexpected error occurred fetching questions: {e}")
+            return f"An unexpected error occurred fetching questions: {e}", None
 
-    try:
-        print("📤 Submitting answers...")
-        response = requests.post(submit_url, json=submission_data, timeout=60)
-        response.raise_for_status()
-        result_data = response.json()
-
-        # ✅ Minified message to prevent Content-Length errors
-        final_status = (
-            f"✅ Submission Successful\n"
-            f"User: {result_data.get('username')}\n"
-            f"Score: {result_data.get('score', 'N/A')}%\n"
-            f"Correct: {result_data.get('correct_count', '?')}/"
-            f"{result_data.get('total_attempted', '?')}"
-        )
+        # 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:
+                # Get structured response from agent
+                agent_response = agent(question_text)
+                
+                # Extract model_answer and reasoning_trace
+                model_answer = agent_response.get("model_answer", "")
+                reasoning_trace = agent_response.get("reasoning_trace", "")
+                
+                # Ensure the answer is a string and not too long
+                if not isinstance(model_answer, str):
+                    model_answer = str(model_answer)
+                if len(model_answer) > 10000:  # Limit answer length
+                    model_answer = model_answer[:10000] + "..."
+                
+                # Ensure reasoning_trace is a string and not too long
+                if not isinstance(reasoning_trace, str):
+                    reasoning_trace = str(reasoning_trace)
+                if len(reasoning_trace) > 50000:  # Limit reasoning length
+                    reasoning_trace = reasoning_trace[:50000] + "..."
+                
+                # Create JSON-line format entry
+                json_line_entry = {
+                    "task_id": task_id,
+                    "model_answer": model_answer,
+                    "reasoning_trace": reasoning_trace
+                }
+                
+                answers_payload.append(json_line_entry)
+                
+                # For display in the table, show truncated versions
+                display_question = question_text[:200] + "..." if len(question_text) > 200 else question_text
+                display_answer = model_answer[:200] + "..." if len(model_answer) > 200 else model_answer
+                display_reasoning = reasoning_trace[:200] + "..." if len(reasoning_trace) > 200 else reasoning_trace
+                
+                results_log.append({
+                    "Task ID": task_id, 
+                    "Question": display_question, 
+                    "Model Answer": display_answer,
+                    "Reasoning Trace": display_reasoning
+                })
+                
+            except Exception as e:
+                 print(f"Error running agent on task {task_id}: {e}")
+                 error_response = {
+                     "task_id": task_id,
+                     "model_answer": f"AGENT ERROR: {e}",
+                     "reasoning_trace": f"Agent encountered an error while processing the question: {str(e)}"
+                 }
+                 answers_payload.append(error_response)
+                 results_log.append({
+                     "Task ID": task_id, 
+                     "Question": question_text[:200] + "..." if question_text and len(question_text) > 200 else question_text, 
+                     "Model Answer": f"AGENT ERROR: {e}",
+                     "Reasoning Trace": f"Error occurred during processing"
+                 })
 
-        # ✅ Limit rows for Hugging Face display
-        results_df = pd.DataFrame(results_log).head(20)
-        return final_status, results_df
+        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)
 
-    except Exception as e:
-        return f"❌ Submission failed: {e}", 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)
 
-# --- Gradio Interface ---
-with gr.Blocks() as demo:
-    gr.Markdown("## 🧪 Basic Agent Evaluation Runner")
-    gr.Markdown("""
-**Instructions:**
+        # 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
+    except Exception as e:
+        error_msg = f"Critical error in run_and_submit_all: {str(e)}"
+        print(error_msg)
+        return error_msg, None
 
-1. Log in with your Hugging Face account below.
-2. Click the button to run your agent on 20 questions and auto-submit the results.
-3. Score and output will be displayed.
 
-_Note: This is optimized for Hugging Face Spaces and avoids large UI payloads._
-""")
+# --- Build Gradio Interface using Blocks ---
+with gr.Blocks(
+    title="Advanced Agent Evaluation Runner",
+    theme=gr.themes.Soft(),
+    css="""
+    .gradio-container {
+        max-width: 1200px !important;
+    }
+    """
+) as demo:
+    gr.Markdown("# Advanced 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")
+    with gr.Row():
+        login_button = gr.LoginButton(label="Login to Hugging Face")
+        run_button = gr.Button("Run Evaluation & Submit All Answers", variant="primary")
 
-    status_output = gr.TextArea(
-        label="Run Status / Submission Result",
-        lines=5,
-        max_lines=10,
-        interactive=False
-    )
+    with gr.Row():
+        status_output = gr.Textbox(
+            label="Run Status / Submission Result", 
+            lines=5, 
+            interactive=False,
+            max_lines=10
+        )
+    
+    with gr.Row():
+        results_table = gr.DataFrame(
+            label="Questions and Agent Answers", 
+            wrap=True,
+            max_rows=50,
+            height=400
+        )
 
-    results_table = gr.DataFrame(
-        label="Agent Answers (First 50)",
-        wrap=True
-    )
+    # Add error handling to the button click
+    def safe_run_and_submit(profile):
+        try:
+            return run_and_submit_all(profile)
+        except Exception as e:
+            error_msg = f"An error occurred: {str(e)}"
+            print(f"Error in safe_run_and_submit: {e}")
+            return error_msg, None
 
     run_button.click(
-        fn=run_and_submit_all,
+        fn=safe_run_and_submit,
+        inputs=[login_button],
         outputs=[status_output, results_table]
     )
 
-# --- Run the Gradio App ---
 if __name__ == "__main__":
-    print("🚀 Launching Gradio App for Hugging Face Agent Evaluation")
-    demo.launch(debug=True, share=False)
+    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 Advanced Agent Evaluation...")
+    # Fixed launch configuration to prevent HTTP protocol errors
+    demo.launch(
+        debug=False,  # Disable debug mode to prevent extra logging that can cause issues
+        share=False,
+        server_name="0.0.0.0",
+        server_port=7860,
+        show_error=True,
+        quiet=False,
+        # Disable features that can cause HTTP protocol issues
+        prevent_thread_lock=False,
+        show_tips=False
+    )