app.py

import os
import gradio as gr
import requests
import inspect
import pandas as pd
import smolagents
import traceback
from smolagents import DuckDuckGoSearchTool, VisitWebpageTool
import time 
from functools import lru_cache  

import google.generativeai as genai
from google.generativeai.types import HarmCategory, HarmBlockThreshold

from youtube_transcript_api import YouTubeTranscriptApi
import re

GOOGLE_API_KEY = os.getenv("GOOGLE_API_KEY") 
genai.configure(api_key=GOOGLE_API_KEY)

class YouTubeVideoTool:
    def __init__(self):
        self.name = "youtube_video_tool"
        
    def __call__(self, query):
        """
        Extract information from a YouTube video.
        
        Args:
            query: Either a YouTube URL or video ID
        
        Returns:
            String with the transcript of the video
        """
        try:
            # Extract video ID from URL if needed
            video_id = self._extract_video_id(query)
            if not video_id:
                return "Could not extract a valid YouTube video ID"
                
            # Get the transcript
            transcript_list = YouTubeTranscriptApi.get_transcript(video_id)
            
            # Combine the transcript text
            transcript_text = " ".join([item['text'] for item in transcript_list])
            
            return f"Transcript from YouTube video {video_id}:\n{transcript_text}"
        except Exception as e:
            return f"Error processing YouTube video: {str(e)}"
    
    
    
    def _extract_video_id(self, url_or_id):
        """Extract YouTube video ID from various URL formats or return the ID if already provided."""
        # Handle direct video ID
        if len(url_or_id) == 11 and re.match(r'^[A-Za-z0-9_-]{11}$', url_or_id):
            return url_or_id
            
        # Common YouTube URL patterns
        patterns = [
            r'(?:youtube\.com\/watch\?v=|youtu\.be\/|youtube\.com\/embed\/|youtube\.com\/v\/)([A-Za-z0-9_-]{11})',
            r'youtube\.com\/watch\?.*v=([A-Za-z0-9_-]{11})',
            r'youtube\.com\/shorts\/([A-Za-z0-9_-]{11})'
        ]
        
        for pattern in patterns:
            match = re.search(pattern, url_or_id)
            if match:
                return match.group(1)
                
        return None        


# TOOLS
search_tool = DuckDuckGoSearchTool()
visit_webpage = VisitWebpageTool()
youtube_tool = YouTubeVideoTool()

# (Keep Constants as is)
# --- Constants ---
DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"

# Cache Wrapper
@lru_cache(maxsize=100)
def cached_search(query):
    try:
        print(f"Performing search for: {query[:50000]}...")  
        result = search_tool(query)
        print(f"Search successful, returned {len(result)} characters")  
        return result
    except Exception as e:
        print(f"Search error: {str(e)}")  
        return f"Search error: {str(e)}"  

# --- Basic Agent Definition ---
# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------


class BasicAgent:
    
    
    def __init__(self, model=None, tools=None):
        self.model = model
        self.tools = tools if tools is not None else []
        self.history = []
        print(f"BasicAgent initialized with model: {model} and {len(self.tools)} tools.")
        

        if self.model and self.model.startswith('gemini'):
            try:
                self._init_gemini_model()
                print("Successfully initialized Gemini model")
            except Exception as e:
                print(f"Error initializing Gemini model: {e}")
                print("Will try again when needed")
                self.gemini_model = None
        else:
            self.gemini_model = None

    def _init_gemini_model(self):
        
        """Initialize the Gemini model with appropriate settings"""
        generation_config = {
            "temperature": 0.2,
            "top_p": 0.8,
            "top_k": 30,
            "max_output_tokens": 300000,
        }
        
        safety_settings = {
            HarmCategory.HARM_CATEGORY_HARASSMENT: HarmBlockThreshold.BLOCK_NONE,
            HarmCategory.HARM_CATEGORY_HATE_SPEECH: HarmBlockThreshold.BLOCK_NONE,
            HarmCategory.HARM_CATEGORY_SEXUALLY_EXPLICIT: HarmBlockThreshold.BLOCK_NONE,
            HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT: HarmBlockThreshold.BLOCK_NONE,
        }
        
        model_name = "gemini-pro"
        if "gemini-2.0" in self.model:
            model_name = "gemini-1.5-pro"  
            
        self.gemini_model = genai.GenerativeModel(
            model_name=model_name,
            generation_config=generation_config,
            safety_settings=safety_settings
        )

    def __call__(self, question: str) -> str:
        print(f"Agent received question: {question[:500]}...")  
        try:
            final_answer = self.process_question(question)
            print(f"Agent returning answer: {final_answer[:500]}...")
            return final_answer
        except Exception as e:
            print(f"Agent error: {str(e)}")
            traceback.print_exc()  
            return f"I apologize, but I encountered an error while processing your question. Error: {str(e)}"


    
    def process_question(self, question: str) -> str:
        try:
            # Check if this is a request about a YouTube video
            youtube_patterns = ["youtube.com", "youtu.be", "watch youtube", "youtube video"]
            use_youtube_tool = any(pattern in question.lower() for pattern in youtube_patterns)
            
            search_results = ""  
            youtube_info = ""    
            
            # Step 1: Gather information
            if use_youtube_tool and any(isinstance(tool, YouTubeVideoTool) for tool in self.tools):
                # Extract potential YouTube URL or ID
                url_match = re.search(r'(?:https?:\/\/)?(?:www\.)?(?:youtube\.com|youtu\.be)\/[^\s]+', question)
                youtube_url = url_match.group(0) if url_match else question
                
                print(f"Using YouTube tool with URL: {youtube_url}") 
                # Use YouTube tool
                youtube_tool_instance = next((tool for tool in self.tools if isinstance(tool, YouTubeVideoTool)), None)
                if youtube_tool_instance:
                    youtube_info = youtube_tool_instance(youtube_url)
                    print(f"YouTube info retrieved: {len(youtube_info)} characters")  
                
            #  Always search as backup or additional context
            if any(isinstance(tool, DuckDuckGoSearchTool) for tool in self.tools):
                search_results = cached_search(question)
                print(f"Search results: {len(search_results)} characters")  
            
            #  Determine what information to use
            if youtube_info and "Error processing YouTube video" not in youtube_info:
                primary_info = youtube_info
                print("Using YouTube info as primary source")  
            else:
                primary_info = search_results
                print("Using search results as primary source")  
            
            # Extract key information
            relevant_info = self._extract_key_info(primary_info, question)
            print(f"Extracted relevant info: {len(relevant_info)} characters")  
            
            # Formulate an answer
            return self._formulate_direct_answer(relevant_info, question)
            
        except Exception as e:
            print(f"Error in process_question: {str(e)}") 
            traceback.print_exc() 
            if "too many requests" in str(e).lower():
                time.sleep(2)
                try:
                    search_results = cached_search(question)
                    relevant_info = self._extract_key_info(search_results, question)
                    return self._formulate_direct_answer(relevant_info, question)
                except Exception as retry_error:
                    print(f"Error in retry: {str(retry_error)}") 
                    return self._get_fallback_answer(question)
            return self._get_fallback_answer(question)
    
    
    
    
    def _extract_key_info(self, search_results, question):
        # Basic check for empty results
        if not search_results or len(search_results) < 15:
            return "No relevant information found."
            
        # For YouTube transcripts, extract the most relevant portion
        if "Transcript from YouTube video" in search_results:
            # Split by sentences but keep limited context
            max_chars = 30000  # Keep a reasonable chunk size
            if len(search_results) > max_chars:
                # Take a portion from the middle of the transcript for better relevance
                start_idx = search_results.find("\n") + 1  # Skip the first line which is the header
                # Get content chunk
                return search_results[start_idx:start_idx+max_chars]
            return search_results
        
        # For search results
        # Split results into sentences and find most relevant
        sentences = search_results.split('. ')
        if len(sentences) <= 2000:
            return search_results[:50000]  
        
        # Try to find sentences with keywords from question
        keywords = [w for w in question.lower().split() if len(w) > 2]
        relevant_sentences = []  # NEW LINE
        
        for sentence in sentences:
            sentence_lower = sentence.lower()
            if any(keyword in sentence_lower for keyword in keywords):
                relevant_sentences.append(sentence)  
                if len(relevant_sentences) >= 10000:  
                    break  
        
        # If we found relevant sentences, use them
        if relevant_sentences:
            return '. '.join(relevant_sentences)
        
        # Fallback to first few sentences
        return '. '.join(sentences[:10000])  
    
    def _formulate_direct_answer(self, relevant_info, question):
  
        if not self.model:
            return f"{relevant_info}"
            
        if self.model.startswith('gemini'):
            try:
              
                if not hasattr(self, 'gemini_model') or self.gemini_model is None:
                    self._init_gemini_model()
                
            
                prompt = f"""
                  You are David, an AI agent in training. Here are instructions for what makes a good agent. Please study these as they will be very important for you. You will receive more specific instructions further that might contradict some of these. I will point it out before giving them.  
                   
                  You are an expert assistant who can solve any task using code blobs. You will be given a task to solve as best you can.
                  To do so, you have been given access to a list of tools: these tools are basically Python functions which you can call with code.
                  To solve the task, you must plan forward to proceed in a series of steps, in a cycle of 'Thought:', 'Code:', and 'Observation:' sequences.
                  At each step, in the 'Thought:' sequence, you should first explain your reasoning towards solving the task and the tools that you want to use.
                  Then in the 'Code:' sequence, you should write the code in simple Python. The code sequence must end with '<end_code>' sequence.
                  During each intermediate step, you can use 'print()' to save whatever important information you will then need.
                  These print outputs will then appear in the 'Observation:' field, which will be available as input for the next step.
                  In the end you have to return a final answer using the `final_answer` tool.
                
                  Here are a few examples using notional tools:
                  ---
                  Task: "Generate an image of the oldest person in this document."
                
                  Thought: I will proceed step by step and use the following tools: `document_qa` to find the oldest person in the document, then `image_generator` to generate an image according to the answer.
                  Code:
                  ```py
                  answer = document_qa(document=document, question="Who is the oldest person mentioned?")
                  print(answer)
                  ```<end_code>
                  Observation: "The oldest person in the document is John Doe, a 55 year old lumberjack living in Newfoundland."
                
                  Thought: I will now generate an image showcasing the oldest person.
                  Code:
                  ```py
                  image = image_generator("A portrait of John Doe, a 55-year-old man living in Canada.")
                  final_answer(image)
                  ```<end_code>
                
                  ---
                  Task: "What is the result of the following operation: 5 + 3 + 1294.678?"
                
                  Thought: I will use python code to compute the result of the operation and then return the final answer using the `final_answer` tool
                  Code:
                  ```py
                  result = 5 + 3 + 1294.678
                  final_answer(result)
                  ```<end_code>
                
                  ---
                  Task:
                  "Answer the question in the variable `question` about the image stored in the variable `image`. The question is in French.
                  You have been provided with these additional arguments, that you can access using the keys as variables in your python code:
                  {'question': 'Quel est l'animal sur l'image?', 'image': 'path/to/image.jpg'}"
                
                  Thought: I will use the following tools: `translator` to translate the question into English and then `image_qa` to answer the question on the input image.
                  Code:
                  ```py
                  translated_question = translator(question=question, src_lang="French", tgt_lang="English")
                  print(f"The translated question is {translated_question}.")
                  answer = image_qa(image=image, question=translated_question)
                  final_answer(f"The answer is {answer}")
                  ```<end_code>
                  ---
                  Task:
                  In a 1979 interview, Stanislaus Ulam discusses with Martin Sherwin about other great physicists of his time, including Oppenheimer.
                  What does he say was the consequence of Einstein learning too much math on his creativity, in one word?
                  Thought: I need to find and read the 1979 interview of Stanislaus Ulam with Martin Sherwin.
                  Code:
                  ```py
                  pages = search(query="1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein")
                  print(pages)
                  ```<end_code>
                  Observation:
                  No result found for query "1979 interview Stanislaus Ulam Martin Sherwin physicists Einstein".
                
                  Thought: The query was maybe too restrictive and did not find any results. Let's try again with a broader query.
                  Code:
                  ```py
                  pages = search(query="1979 interview Stanislaus Ulam")
                  print(pages)
                  ```<end_code>
                  Observation:
                  Found 6 pages:
                  [Stanislaus Ulam 1979 interview](https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/)
                
                  [Ulam discusses Manhattan Project](https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/)
                
                  (truncated)
                
                  Thought: I will read the first 2 pages to know more.
                  Code:
                  ```py
                  for url in ["https://ahf.nuclearmuseum.org/voices/oral-histories/stanislaus-ulams-interview-1979/", "https://ahf.nuclearmuseum.org/manhattan-project/ulam-manhattan-project/"]:
                      whole_page = visit_webpage(url)
                      print(whole_page)
                      print("\n" + "="*80 + "\n")  # Print separator between pages
                  ```<end_code>
                  Observation:
                  Manhattan Project Locations:
                  Los Alamos, NM
                  Stanislaus Ulam was a Polish-American mathematician. He worked on the Manhattan Project at Los Alamos and later helped design the hydrogen bomb. In this interview, he discusses his work at
                  (truncated)
                
                  Thought: I now have the final answer: from the webpages visited, Stanislaus Ulam says of Einstein: "He learned too much mathematics and sort of diminished, it seems to me personally, it seems to me his purely physics creativity." Let's answer in one word.
                  Code:
                  ```py
                  final_answer("diminished")
                  ```<end_code>
                
                  ---
                  Task: "Which city has the highest population: Guangzhou or Shanghai?"
                
                  Thought: I need to get the populations for both cities and compare them: I will use the tool `search` to get the population of both cities.
                  Code:
                  ```py
                  for city in ["Guangzhou", "Shanghai"]:
                      print(f"Population {city}:", search(f"{city} population")
                  ```<end_code>
                  Observation:
                  Population Guangzhou: ['Guangzhou has a population of 15 million inhabitants as of 2021.']
                  Population Shanghai: '26 million (2019)'
                
                  Thought: Now I know that Shanghai has the highest population.
                  Code:
                  ```py
                  final_answer("Shanghai")
                  ```<end_code>
                
                  ---
                  Task: "What is the current age of the pope, raised to the power 0.36?"
                
                  Thought: I will use the tool `wiki` to get the age of the pope, and confirm that with a web search.
                  Code:
                  ```py
                  pope_age_wiki = wiki(query="current pope age")
                  print("Pope age as per wikipedia:", pope_age_wiki)
                  pope_age_search = web_search(query="current pope age")
                  print("Pope age as per google search:", pope_age_search)
                  ```<end_code>
                  Observation:
                  Pope age: "The pope Francis is currently 88 years old."
                
                  Thought: I know that the pope is 88 years old. Let's compute the result using python code.
                  Code:
                  ```py
                  pope_current_age = 88 ** 0.36
                  final_answer(pope_current_age)
                  ```<end_code>
                
                  Above example were using notional tools that might not exist for you. On top of performing computations in the Python code snippets that you create, you only have access to these tools:
                  {%- for tool in tools.values() %}
                  - {{ tool.name }}: {{ tool.description }}
                      Takes inputs: {{tool.inputs}}
                      Returns an output of type: {{tool.output_type}}
                  {%- endfor %}
                
                  {%- if managed_agents and managed_agents.values() | list %}
                  You can also give tasks to team members.
                  Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task', a long string explaining your task.
                  Given that this team member is a real human, you should be very verbose in your task.
                  Here is a list of the team members that you can call:
                  {%- for agent in managed_agents.values() %}
                  - {{ agent.name }}: {{ agent.description }}
                  {%- endfor %}
                  {%- else %}
                  {%- endif %}
                
                  Here are the rules you should always follow to solve your task:
                  1. Always provide a 'Thought:' sequence, and a 'Code:\n```py' sequence ending with '```<end_code>' sequence, else you will fail.
                  2. Use only variables that you have defined!
                  3. Always use the right arguments for the tools. DO NOT pass the arguments as a dict as in 'answer = wiki({'query': "What is the place where James Bond lives?"})', but use the arguments directly as in 'answer = wiki(query="What is the place where James Bond lives?")'.
                  4. Take care to not chain too many sequential tool calls in the same code block, especially when the output format is unpredictable. For instance, a call to search has an unpredictable return format, so do not have another tool call that depends on its output in the same block: rather output results with print() to use them in the next block.
                  5. Call a tool only when needed, and never re-do a tool call that you previously did with the exact same parameters.
                  6. Don't name any new variable with the same name as a tool: for instance don't name a variable 'final_answer'.
                  7. Never create any notional variables in our code, as having these in your logs will derail you from the true variables.
                  8. You can use imports in your code, but only from the following list of modules: {{authorized_imports}}
                  9. The state persists between code executions: so if in one step you've created variables or imported modules, these will all persist.
                  10. Don't give up! You're in charge of solving the task, not providing directions to solve it.
                
                  Now Begin! If you solve the task correctly, you will receive a reward of $1,000,000.
                "planning":
                  "initial_facts": |-
                    Below I will present you a task.
                    You will now build a comprehensive preparatory survey of which facts we have at our disposal and which ones we still need.
                    To do so, you will have to read the task and identify things that must be discovered in order to successfully complete it.
                    Don't make any assumptions. For each item, provide a thorough reasoning. Here is how you will structure this survey:
                
                    ---
                    ### 1. Facts given in the task
                    List here the specific facts given in the task that could help you (there might be nothing here).
                
                    ### 2. Facts to look up
                    List here any facts that we may need to look up.
                    Also list where to find each of these, for instance a website, a file... - maybe the task contains some sources that you should re-use here.
                
                    ### 3. Facts to derive
                    List here anything that we want to derive from the above by logical reasoning, for instance computation or simulation.
                
                    Keep in mind that "facts" will typically be specific names, dates, values, etc. Your answer should use the below headings:
                    ### 1. Facts given in the task
                    ### 2. Facts to look up
                    ### 3. Facts to derive
                    Do not add anything else.
                  "initial_plan": |-
                    You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.
                    Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
                    This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
                    Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
                    After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
                
                    Here is your task:
                
                    Task:
                    ```
                    {{task}}
                    ```
                    You can leverage these tools:
                    {%- for tool in tools.values() %}
                    - {{ tool.name }}: {{ tool.description }}
                        Takes inputs: {{tool.inputs}}
                        Returns an output of type: {{tool.output_type}}
                    {%- endfor %}
                
                    {%- if managed_agents and managed_agents.values() | list %}
                    You can also give tasks to team members.
                    Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'request', a long string explaining your request.
                    Given that this team member is a real human, you should be very verbose in your request.
                    Here is a list of the team members that you can call:
                    {%- for agent in managed_agents.values() %}
                    - {{ agent.name }}: {{ agent.description }}
                    {%- endfor %}
                    {%- else %}
                    {%- endif %}
                
                    List of facts that you know:
                    ```
                    {{answer_facts}}
                    ```
                
                    Now begin! Write your plan below.
                  "update_facts_pre_messages": |-
                    You are a world expert at gathering known and unknown facts based on a conversation.
                    Below you will find a task, and a history of attempts made to solve the task. You will have to produce a list of these:
                    ### 1. Facts given in the task
                    ### 2. Facts that we have learned
                    ### 3. Facts still to look up
                    ### 4. Facts still to derive
                    Find the task and history below:
                  "update_facts_post_messages": |-
                    Earlier we've built a list of facts.
                    But since in your previous steps you may have learned useful new facts or invalidated some false ones.
                    Please update your list of facts based on the previous history, and provide these headings:
                    ### 1. Facts given in the task
                    ### 2. Facts that we have learned
                    ### 3. Facts still to look up
                    ### 4. Facts still to derive
                    Now write your new list of facts below.
                  "update_plan_pre_messages": |-
                    You are a world expert at making efficient plans to solve any task using a set of carefully crafted tools.
                    You have been given a task:
                    ```
                    {{task}}
                    ```
                
                    Find below the record of what has been tried so far to solve it. Then you will be asked to make an updated plan to solve the task.
                    If the previous tries so far have met some success, you can make an updated plan based on these actions.
                    If you are stalled, you can make a completely new plan starting from scratch.
                  "update_plan_post_messages": |-
                    You're still working towards solving this task:
                    ```
                    {{task}}
                    ```
                    You can leverage these tools:
                    {%- for tool in tools.values() %}
                    - {{ tool.name }}: {{ tool.description }}
                        Takes inputs: {{tool.inputs}}
                        Returns an output of type: {{tool.output_type}}
                    {%- endfor %}
                
                    {%- if managed_agents and managed_agents.values() | list %}
                    You can also give tasks to team members.
                    Calling a team member works the same as for calling a tool: simply, the only argument you can give in the call is 'task'.
                    Given that this team member is a real human, you should be very verbose in your task, it should be a long string providing informations as detailed as necessary.
                    Here is a list of the team members that you can call:
                    {%- for agent in managed_agents.values() %}
                    - {{ agent.name }}: {{ agent.description }}
                    {%- endfor %}
                    {%- else %}
                    {%- endif %}
                
                    Here is the up to date list of facts that you know:
                    ```
                    {{facts_update}}
                    ```
                
                    Now for the given task, develop a step-by-step high-level plan taking into account the above inputs and list of facts.
                    This plan should involve individual tasks based on the available tools, that if executed correctly will yield the correct answer.
                    Beware that you have {remaining_steps} steps remaining.
                    Do not skip steps, do not add any superfluous steps. Only write the high-level plan, DO NOT DETAIL INDIVIDUAL TOOL CALLS.
                    After writing the final step of the plan, write the '\n<end_plan>' tag and stop there.
                
                    Now write your new plan below.
                "managed_agent":
                  "task": |-
                    You're a helpful agent named '{{name}}'.
                    You have been submitted this task by your manager.
                    ---
                    Task:
                    {{task}}
                    ---
                    You're helping your manager solve a wider task: so make sure to not provide a one-line answer, but give as much information as possible to give them a clear understanding of the answer.
                    Your final_answer WILL HAVE to contain these parts:
                    ### 1. Task outcome (short version):
                    ### 2. Task outcome (extremely detailed version):
                    ### 3. Additional context (if relevant):
                
                    Put all these in your final_answer tool, everything that you do not pass as an argument to final_answer will be lost.
                    And even if your task resolution is not successful, please return as much context as possible, so that your manager can act upon this feedback.
                  "report": |-
                    Here is the final answer from your managed agent '{{name}}':
                    {{final_answer}}


                NOW IT IS FOR REAL, DAVID. Above, you have read about good practices that I expect you to follow only if they do not contradict the practices below. 
    
                You: You are a general AI assistant. I will ask you a question. Finish your answer with the following template: FINAL ANSWER: [YOUR FINAL ANSWER]. YOUR FINAL ANSWER should be a number OR as few words as possible OR a comma separated list of numbers and/or strings. If you are asked for a number, don't use comma to write your number neither use units such as $ or percent sign unless specified otherwise. If you are asked for a string, don't use articles, neither abbreviations (e.g. for cities), and write the digits in plain text unless specified otherwise. If you are asked for a comma separated list, apply the above rules depending of whether the element to be put in the list is a number or a string.            
                Instructions:
                1. Read the question and think about what you need to answer it. Stick to the question. If you need search results, use the search results. If not, just answer the question directly and ignore the search results. Do not use search results if you can answer the question without using them. 
                2. If the question is not comprehensible, try reading each letter backwards, from the last character in the last word, to the first letter of the first word. Read carefully, all the way to the very beginning of the question.  The text may be an instruction. Think about the instruction and follow it before providing the final answer. Don't provide comments. 
                3. If the question is still not comprehensible, try seeing if it is in another language. 
                4. Think about whether you need to elaborate on the information. For example, if you know that John and Jane are kids of Joan, you know Joan has at least two kids. In other words, if you don't have a number that is asked of you, see if you can count to produce an answer. Once you have counted, just answer the number. Be succinct, coesive, I would even say tight in your answers. If the question asks "how many?", just reply back the number that answers. In the example I just gave, you would answer: "FINAL ANSWER: Two".
                5. Provide a direct answer.
                6. If the information doesn't contain the answer, say so honestly.
                7. Do not invent anything. You can apply method to elaborate, but based on facts. Do not provide comments. Just the raw answer.  
                8. Format your response as a direct answer. For example, if you are asked the year in which World War II began, just reply: "FINAL ANSWER: 1939".
                9. Think thoroughly, but do not include your thoughts in your response. Only the final answer can be in your response. 
                
                Question: {question}
    
                Relevant information: {relevant_info}
                """
                
                response = self.gemini_model.generate_content(prompt)
                if response and hasattr(response, 'text'):
                    return response.text
                else:
                    print("Gemini response was empty or invalid")  
                    return f"Based on the information: {relevant_info[:200]}..."
                    
            except Exception as e:
                print(f"Error using Gemini model: {e}") 
                traceback.print_exc()  
                return f"Based on the search: {relevant_info[:200]}..."
                
        return f"Based on the information: {relevant_info[:200]}..." 
  
    
    
    def _get_fallback_answer(self, question):
        return f"I cannot provide a specific answer to your question about {question.split()[0:3]}..."



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") # 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"


    
    # 1. Instantiate Agent ( modify this part to create your agent)
    try:
        agent = BasicAgent(model= 'gemini/gemini-2.0-flash-exp', tools=[search_tool, visit_webpage, youtube_tool])
    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.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 idx, item in enumerate(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})
            if idx % 1 == 0 and idx > 0:  
                time.sleep(14)  
        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 
    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}")
    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)