Update app.py

app.py

@@ -1,376 +1,188 @@
 import os
+
 import gradio as gr
-import requests
 import pandas as pd
-import re
-import json
-import math
-from typing import Dict, List, Any, Optional
-from datetime import datetime
-
-# --- Advanced Tool-Based Agent ---
-class ToolBasedAgent:
-    def __init__(self):
-        print("ToolBasedAgent initialized with multiple tools")
-        self.available_tools = {
-            "web_search": self.web_search_tool,
-            "calculator": self.calculator_tool,
-            "data_analyzer": self.data_analyzer_tool,
-            "text_processor": self.text_processor_tool,
-            "reasoning_engine": self.reasoning_engine_tool
-        }
-    
-    def web_search_tool(self, query: str) -> str:
-        """Simulated web search tool - in production would integrate with real APIs"""
-        # This would integrate with:
-        # - SerpAPI, Google Search API
-        # - Wikipedia API
-        # - DuckDuckGo API
-        return f"Based on search for '{query}', the information would be retrieved from reliable sources."
-
-    def calculator_tool(self, expression: str, context: str = "") -> str:
-        """Mathematical calculation tool"""
-        try:
-            # Safe evaluation of mathematical expressions
-            if re.search(r'\d+', expression):
-                # Simple arithmetic
-                if '+' in expression:
-                    numbers = [int(x) for x in re.findall(r'\d+', expression)]
-                    return str(sum(numbers))
-                elif 'sum' in expression.lower():
-                    numbers = [int(x) for x in re.findall(r'\d+', expression)]
-                    return str(sum(numbers))
-            return "Calculation requires specific numbers and operations"
-        except:
-            return "Unable to perform calculation with given information"
-
-    def data_analyzer_tool(self, data_description: str, question: str) -> str:
-        """Data analysis tool for structured data questions"""
-        if 'excel' in data_description.lower() or 'sales' in question.lower():
-            return "Data analysis would process the Excel file to calculate total food sales excluding drinks, formatted as USD with two decimals"
-        elif 'table' in data_description.lower() or 'data' in question.lower():
-            return "Would analyze the provided dataset to extract relevant information and perform required calculations"
-        return "Data analysis tool ready to process structured information"
+import requests
 
-    def text_processor_tool(self, text: str, operation: str) -> str:
-        """Text processing and analysis tool"""
-        if 'extract' in operation or 'find' in operation:
-            # Extract key entities
-            entities = re.findall(r'[A-Z][a-z]+(?:\s+[A-Z][a-z]+)*', text)
-            if entities:
-                return f"Key entities found: {', '.join(set(entities))}"
-        return "Text analysis completed"
+import smolagents
+from agent_for_unit4 import manager_agent, prepare_for_input
 
-    def reasoning_engine_tool(self, question: str, context: str = "") -> str:
-        """Advanced reasoning for complex questions"""
-        # Analyze question structure and type
-        question_lower = question.lower()
-        
-        # Historical/Research questions
-        if any(word in question_lower for word in ['olympics', 'athletes', 'ioc']):
-            return "Research strategy: Query Olympic databases for 1928 Summer Games participation data, find country with minimum athletes, handle ties alphabetically, return IOC code"
-        
-        # Sports/Player data questions
-        elif any(word in question_lower for word in ['pitchers', 'baseball', 'number before', 'number after']):
-            return "Research strategy: Access baseball databases to find Taishō Tamai's player number, identify adjacent players, extract and format last names in Roman characters"
-        
-        # Competition/Historical research
-        elif any(word in question_lower for word in ['malko competition', 'nationality', 'country no longer exists']):
-            return "Research strategy: Analyze Malko Competition records post-1977, identify recipients from now-defunct countries, extract first names"
-        
-        # Data analysis questions
-        elif any(word in question_lower for word in ['excel', 'sales', 'total', 'usd']):
-            return "Analysis strategy: Process the attached Excel file, separate food and drink items, sum food sales, format result in USD with two decimal places"
-        
-        return "Complex reasoning required: Break down question into subproblems, research relevant information, synthesize answer"
+# (Keep Constants as is)
+# --- Constants ---
+DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
+FILE_BASE_URL = "https://agents-course-unit4-scoring.hf.space/files/"
 
-    def analyze_question_structure(self, question: str) -> Dict[str, Any]:
-        """Analyze question to determine required tools and approach"""
-        analysis = {
-            "type": "unknown",
-            "required_tools": [],
-            "complexity": "medium",
-            "needs_research": False,
-            "needs_calculation": False,
-            "needs_data_analysis": False
-        }
-        
-        question_lower = question.lower()
-        
-        # Determine question type
-        if any(word in question_lower for word in ['calculate', 'sum', 'total', 'how many']):
-            analysis["type"] = "calculation"
-            analysis["required_tools"].append("calculator")
-            analysis["needs_calculation"] = True
-            
-        if any(word in question_lower for word in ['excel', 'data', 'table', 'sales']):
-            analysis["type"] = "data_analysis"
-            analysis["required_tools"].append("data_analyzer")
-            analysis["needs_data_analysis"] = True
-            
-        if any(word in question_lower for word in ['who', 'what country', 'which', 'name of']):
-            analysis["type"] = "research"
-            analysis["required_tools"].append("web_search")
-            analysis["required_tools"].append("reasoning_engine")
-            analysis["needs_research"] = True
-            
-        if any(word in question_lower for word in ['how', 'why', 'process', 'method']):
-            analysis["type"] = "explanation"
-            analysis["required_tools"].append("reasoning_engine")
-            analysis["complexity"] = "high"
-            
-        # Adjust complexity based on question length and structure
-        if len(question.split()) > 20:
-            analysis["complexity"] = "high"
-            
-        return analysis
+def fix_input_text(input_text: str) -> str:
+    if "You're helping your manager solve a wider task:" in input_text:
+        input_text = input_text.split("You're helping your manager solve a wider task:")[0]
+    return input_text.strip()
 
-    def __call__(self, question: str) -> str:
-        print(f"ToolBasedAgent processing: {question[:100]}...")
-        
-        # Analyze the question
-        analysis = self.analyze_question_structure(question)
-        print(f"Question analysis: {analysis}")
-        
-        # Use reasoning engine for complex questions
-        if analysis["complexity"] == "high" or analysis["needs_research"]:
-            reasoning_result = self.reasoning_engine_tool(question)
-            
-            # For very specific question patterns, provide targeted responses
-            if "IOC country code" in question and "1928 Summer Olympics" in question:
-                return "Research required: Access Olympic historical databases to find participating countries and athlete counts for 1928 Summer Olympics, identify country with fewest athletes, handle alphabetical tie-breaking, return 3-letter IOC code"
-            
-            elif "Taishō Tamai" in question and "pitchers" in question:
-                return "Research required: Query baseball reference databases to find Taishō Tamai's uniform number, locate players with adjacent numbers, extract and format last names in Roman characters as 'Pitcher Before, Pitcher After'"
-            
-            elif "Malko Competition" in question and "country no longer exists" in question:
-                return "Research required: Analyze Malko Competition archives for post-1977 recipients, identify those with nationalities from now-defunct countries (e.g., USSR, Yugoslavia, etc.), return first name of matching recipient"
-            
-            elif "Excel" in question and "sales" in question and "USD" in question:
-                return "Analysis required: Process the attached Excel file data, separate food items from drinks, calculate sum of food sales only, format result as USD currency with two decimal places (e.g., 1234.56)"
-            
-            return reasoning_result
-        
-        # Use calculator for mathematical questions
-        elif analysis["needs_calculation"]:
-            return self.calculator_tool(question, "Mathematical calculation required")
-        
-        # Use data analyzer for data-related questions
-        elif analysis["needs_data_analysis"]:
-            return self.data_analyzer_tool(question, "Data analysis required")
-        
-        # Default to web search for general questions
-        else:
-            return self.web_search_tool(question)
 
-# --- Enhanced execution function ---
 def run_and_submit_all(profile: gr.OAuthProfile | None):
     """
-    Enhanced execution with better progress tracking and error handling
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
+    and displays the results.
     """
-    space_id = os.getenv("SPACE_ID")
-    
-    if not profile:
-        return "Please log in to Hugging Face to submit your answers.", 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
+
+    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
 
-    username = profile.username
-    api_url = "https://agents-course-unit4-scoring.hf.space"
+    api_url = DEFAULT_API_URL
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # Initialize the tool-based agent
-    try:
-        agent = ToolBasedAgent()
-        print("ToolBasedAgent initialized successfully")
-    except Exception as e:
-        error_msg = f"Error initializing ToolBasedAgent: {str(e)}"
-        print(error_msg)
-        return error_msg, 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)
 
-    # Fetch questions with enhanced error handling
+    # 2. Fetch Questions
+    print(f"Fetching questions from: {questions_url}")
     try:
-        print(f"Fetching questions from {questions_url}")
-        response = requests.get(questions_url, timeout=45)
+        response = requests.get(questions_url, timeout=15)
         response.raise_for_status()
         questions_data = response.json()
-        
-        if not isinstance(questions_data, list):
-            return "Invalid response format: questions data is not a list", None
-            
-        print(f"Successfully fetched {len(questions_data)} questions")
-        
-    except requests.exceptions.Timeout:
-        return "Timeout while fetching questions. Please try again.", None
+        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:
-        return f"Network error while fetching questions: {str(e)}", None
+        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:
-        return f"Unexpected error fetching questions: {str(e)}", None
+        print(f"An unexpected error occurred fetching questions: {e}")
+        return f"An unexpected error occurred fetching questions: {e}", None
 
-    # Process each question with the agent
+    # 3. Run your Agent
+    print(f"smolagents version: {smolagents.__version__}")
     results_log = []
     answers_payload = []
-    
-    for index, item in enumerate(questions_data):
+    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", "").strip()
-        
-        if not task_id or not question_text:
-            print(f"Skipping invalid item at index {index}")
+        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
-            
-        print(f"Processing question {index + 1}/{len(questions_data)}")
-        print(f"Question: {question_text[:100]}...")
-        
         try:
-            # Use the tool-based agent to generate answer
-            submitted_answer = agent(question_text)
-            
-            # Ensure answer is reasonable length
-            if len(submitted_answer) > 1000:
-                submitted_answer = submitted_answer[:1000] + "... [truncated]"
-                
-            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
-            })
-            
-            print(f"Generated answer: {submitted_answer[:100]}...")
-            
+            # === RUN AGENT ===
+            input_text = prepare_for_input(item, FILE_BASE_URL)
+            print(f"input_text:\n{input_text}")
+            submitted_answer = manager_agent.run(input_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:
-            error_msg = f"Agent processing error: {str(e)}"
-            print(error_msg)
-            
-            answers_payload.append({
-                "task_id": task_id, 
-                "submitted_answer": error_msg
-            })
-            
-            results_log.append({
-                "Task ID": task_id, 
-                "Question": question_text, 
-                "Submitted Answer": error_msg
-            })
+            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}"})
 
-    # Submit answers if we have any
     if not answers_payload:
-        return "No answers were generated. Please check the agent implementation.", pd.DataFrame(results_log)
+        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)
 
-    print(f"Submitting {len(answers_payload)} answers for user: {username}")
-    
-    submission_data = {
-        "username": username.strip(),
-        "agent_code": agent_code,
-        "answers": answers_payload
-    }
-    
+    # 5. Submit
+    print(f"Submitting {len(answers_payload)} answers to: {submit_url}")
     try:
-        response = requests.post(submit_url, json=submission_data, timeout=120)
+        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', username)}\n"
-            f"📊 Overall Score: {result_data.get('score', 'N/A')}% "
+            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 additional message')}"
+            f"Message: {result_data.get('message', 'No message received.')}"
         )
-        
-        print("Submission completed successfully")
-        return final_status, pd.DataFrame(results_log)
-        
+        print("Submission successful.")
+        results_df = pd.DataFrame(results_log)
+        return final_status, results_df
     except requests.exceptions.HTTPError as e:
-        error_msg = f"HTTP Error {e.response.status_code}: {e.response.text[:200]}"
-        print(f"Submission failed: {error_msg}")
-        return f"Submission Failed: {error_msg}", pd.DataFrame(results_log)
-        
+        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:
-        error_msg = "Submission timeout. The server took too long to respond."
-        print(error_msg)
-        return error_msg, pd.DataFrame(results_log)
-        
+        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:
-        error_msg = f"Unexpected error during submission: {str(e)}"
-        print(error_msg)
-        return error_msg, pd.DataFrame(results_log)
-
-# --- Improved Gradio Interface ---
-with gr.Blocks(theme=gr.themes.Soft()) as demo:
-    gr.Markdown("""
-    # 🚀 Advanced Tool-Based Agent System
-    
-    **Next-generation agent capable of handling complex, diverse questions using specialized tools**
-    
-    ### 🔧 Available Tools:
-    - **Web Search**: Research and information retrieval
-    - **Calculator**: Mathematical computations  
-    - **Data Analyzer**: Excel and structured data processing
-    - **Text Processor**: Text analysis and entity extraction
-    - **Reasoning Engine**: Complex problem-solving strategies
-    
-    ### 📝 Instructions:
-    1. Log in with your Hugging Face account
-    2. Click "Run Evaluation & Submit Answers"
-    3. The agent will analyze each question and use appropriate tools
-    4. View results and score in the output sections
-    
-    *Note: Processing may take several minutes for complex questions*
-    """)
-    
-    with gr.Row():
-        with gr.Column(scale=1):
-            gr.LoginButton()
-            status_indicator = gr.HTML("<div style='padding: 10px; border-radius: 5px; background: #f0f0f0;'>Waiting for login...</div>")
-        
-        with gr.Column(scale=2):
-            run_button = gr.Button(
-                "🚀 Run Evaluation & Submit Answers", 
-                variant="primary",
-                size="lg"
-            )
+        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.
+        """
+    )
 
-    with gr.Row():
-        status_output = gr.Textbox(
-            label="📊 Submission Status",
-            lines=4,
-            interactive=False,
-            show_copy_button=True
-        )
-    
-    with gr.Row():
-        results_table = gr.DataFrame(
-            label="📋 Questions and Generated Answers",
-            wrap=True,
-            height=400
-        )
+    gr.LoginButton()
 
-    # Update login status
-    def update_login_status(profile):
-        if profile:
-            return f"<div style='padding: 10px; border-radius: 5px; background: #d4edda; color: #155724;'>✅ Logged in as: {profile.name}</div>"
-        else:
-            return "<div style='padding: 10px; border-radius: 5px; background: #f8d7da; color: #721c24;'>❌ Please log in to continue</div>"
+    run_button = gr.Button("Run Evaluation & Submit All Answers")
 
-    demo.load(
-        fn=update_login_status,
-        inputs=gr.OAuthProfile(),
-        outputs=status_indicator
-    )
+    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,
-        inputs=gr.OAuthProfile(),
-        outputs=[status_output, results_table]
-    )
+    run_button.click(fn=run_and_submit_all, outputs=[status_output, results_table])
 
 if __name__ == "__main__":
-    print("🚀 Starting Advanced Tool-Based Agent System...")
-    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 Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)