Update app.py

app.py

@@ -1,484 +1,88 @@
+""" Basic Agent Evaluation Runner"""
 import os
-import sys
-import subprocess
-import re
-
-# 检查并安装缺失的依赖
-required_packages = ["litellm", "duckduckgo-search", "gradio", "requests", "pandas"]
-for package in required_packages:
-    try:
-        __import__(package)
-    except ImportError:
-        print(f"Installing {package}...")
-        subprocess.check_call([sys.executable, "-m", "pip", "install", package])
-        print(f"{package} installed successfully!")
-
-# 现在导入所需模块
+import inspect
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
-import json
-import time
-from typing import List, Dict, Any, Optional
-from litellm import completion
-from duckduckgo_search import DDGS
-
-# 用於獲取並解析附件
-def fetch_and_summarize_attachment(task_id, question, files_api_url="https://agents-course-unit4-scoring.hf.space/files/"):
-    import pandas as pd, requests
-    q_lower = question.lower()
-    keywords = ["attached", "file", "excel", "csv", "spreadsheet", "audio", "mp3", "image", "picture", "python code", "code"]
-    if not any(k in q_lower for k in keywords):
-        return ""
-    try:
-        file_url = f"{files_api_url}{task_id}"
-        response = requests.get(file_url, timeout=10)
-        local_path = f"/tmp/{task_id}"
-        with open(local_path, "wb") as f:
-            f.write(response.content)
-        if local_path.endswith(".csv") or b"," in response.content[:512]:
-            df = pd.read_csv(local_path)
-            summary = df.head(10).to_string()
-            return f"[Attachment Detected: CSV Table]\nFirst 10 rows:\n{summary}\n"
-        elif local_path.endswith(".xls") or local_path.endswith(".xlsx"):
-            df = pd.read_excel(local_path)
-            summary = df.head(10).to_string()
-            return f"[Attachment Detected: Excel Table]\nFirst 10 rows:\n{summary}\n"
-        elif local_path.endswith(".txt") or b"\n" in response.content[:512]:
-            with open(local_path, "r", encoding="utf-8", errors="ignore") as f:
-                text = f.read(1000)
-            return f"[Attachment Detected: Text File]\n{text}\n"
-        elif local_path.endswith(".py"):
-            with open(local_path, "r", encoding="utf-8", errors="ignore") as f:
-                code = f.read(1000)
-            return f"[Attachment Detected: Python Code]\n{code}\n"
-        else:
-            return "[Attachment Detected, but file type not supported for summary]\n"
-    except Exception as e:
-        return f"[Attachment Error: {e}]\n"
-
+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"
-DEFAULT_USERNAME = "lethaq"  # 默认用户名，您可以修改为您的用户名
-
-# --- Tool Implementations ---
-class DuckDuckGoSearchTool:
-    def __init__(self):
-        self.name = "duckduckgo_search"
-        self.description = "Search the web using DuckDuckGo"
-        
-    def search(self, query: str, max_results: int = 8) -> List[Dict[str, str]]:
-        """
-        Search the web using DuckDuckGo and return results.
-        
-        Args:
-            query: The search query
-            max_results: Maximum number of results to return
-            
-        Returns:
-            List of dictionaries with search results
-        """
-        try:
-            with DDGS() as ddgs:
-                results = list(ddgs.text(query, max_results=max_results))
-            return results
-        except Exception as e:
-            print(f"DuckDuckGo search error: {e}")
-            return [{"title": f"Search error: {e}", "body": "", "href": ""}]
-
-
-
-            
-
-    
-    def __call__(self, query: str, max_results: int = 8) -> Dict[str, Any]:
-        """
-        Execute the search and return results in a structured format.
-        
-        Args:
-            query: The search query
-            max_results: Maximum number of results to return
-            
-        Returns:
-            Dictionary with search results and metadata
-        """
-        start_time = time.time()
-        results = self.search(query, max_results)
-        end_time = time.time()
-        
-        return {
-            "tool_name": self.name,
-            "query": query,
-            "results": results,
-            "result_count": len(results),
-            "time_taken": end_time - start_time
-        }
 
-# --- LiteLLM Model Wrapper ---
-class LiteLLMModel:
-    def __init__(self, model_id: str, api_key: str):
-        self.model_id = model_id
-        self.api_key = api_key
-        print(f"Initialized LiteLLM with model: {model_id}")
-        
-    def generate(self, prompt: str, system_prompt: str = None, temperature: float = 0.1) -> str:
-        """
-        Generate text using the LiteLLM model.
-        
-        Args:
-            prompt: The user prompt
-            system_prompt: Optional system prompt
-            temperature: Temperature for generation (lower = more deterministic)
-            
-        Returns:
-            Generated text response
-        """
-        try:
-            messages = []
-            if system_prompt:
-                messages.append({"role": "system", "content": system_prompt})
-            messages.append({"role": "user", "content": prompt})
-            
-            response = completion(
-                model=self.model_id,
-                messages=messages,
-                api_key=self.api_key,
-                temperature=temperature,
-                max_tokens=256
-            )
-            
-            return response.choices[0].message.content
-        except Exception as e:
-            print(f"LiteLLM generation error: {e}")
-            return f"Error generating response: {str(e)}"
+# --- Basic Agent Definition ---
+# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
 
-# --- Advanced Agent Implementation ---
-class CodeAgent:
-    def __init__(self, tools: List[Any], model: LiteLLMModel):
-        self.tools = tools
-        self.model = model
-        self.search_tool = next((tool for tool in tools if isinstance(tool, DuckDuckGoSearchTool)), None)
-        print(f"CodeAgent initialized with {len(tools)} tools and model {model.model_id}")
-        
-    def format_search_results(self, results: List[Dict[str, str]]) -> str:
-        """Format search results into a readable string"""
-        formatted = "Search Results:\n"
-        if not results:
-            return "No search results found.\n\n"
-        for i, result in enumerate(results, 1):
-            formatted += f"{i}. {result.get('title', 'No title')}\n"
-            formatted += f"   {result.get('body', 'No description')[:300]}...\n"
-            formatted += f"   URL: {result.get('href', 'No URL')}\n\n"
-        return formatted
-    
-    def create_system_prompt(self) -> str:
-        """Create a system prompt for the model"""
-        return (
-            "You are a specialized AI assistant for the GAIA benchmark test. Your sole purpose is to provide extremely concise, factual answers. "
-            "Follow these strict guidelines:\n\n"
-            "1. NEVER explain, justify, or add context to your answers\n"
-            "2. For numerical questions, respond ONLY with the number\n"
-            "3. For multiple choice questions, respond ONLY with the letter(s) of the correct option(s)\n"
-            "4. For list questions, provide comma-separated items without numbering\n"
-            "5. For yes/no questions, respond ONLY with 'yes' or 'no'\n"
-            "6. If you cannot determine the answer with high confidence, respond ONLY with 'Unknown'\n"
-            "7. NEVER include phrases like 'the answer is' or 'based on'\n"
-            "8. NEVER use bullet points or numbering in your answers\n"
-            "9. NEVER include explanations or reasoning\n\n"
-            "Examples:\n"
-            "- Question: What is the capital of France? Answer: Paris\n"
-            "- Question: How many planets are in our solar system? Answer: 8\n"
-            "- Question: Which options show prime numbers? a) 4 b) 7 c) 11 d) 15 Answer: b, c\n"
-            "- Question: List the Great Lakes. Answer: Superior, Michigan, Huron, Erie, Ontario\n"
-            "- Question: Is the sun a star? Answer: yes\n"
-            "- Question: What is written on the back of the image? Answer: Unknown"
-        )
 
-    def enhance_search_query(self, question: str) -> str:
-        """Enhance the search query based on question type"""
-        question_lower = question.lower()
-        
-        # 添加特定关键词以提高搜索质量
-        if "how many" in question_lower:
-            return question + " exact number statistics"
-        elif "when" in question_lower:
-            return question + " exact date"
-        elif "who" in question_lower:
-            return question + " person biography"
-        elif "where" in question_lower:
-            return question + " location"
-        elif "which" in question_lower and any(word in question_lower for word in ["option", "choice"]):
-            # 对于选择题，提取选项内容加入搜索
-            options = re.findall(r'[a-d]\)(.*?)(?=[a-d]\)|$)', question)
-            if options:
-                return question + " " + " ".join(options)
-        elif any(word in question_lower for word in ["list", "name all", "what are"]):
-            return question + " complete list"
-        elif "code" in question_lower or "python" in question_lower:
-            return question + " code example"
-            
-        return question
+class BasicAgent:
+    """A langgraph agent."""
+    def __init__(self):
+        print("BasicAgent initialized.")
+        self.graph = build_graph()
 
-    def create_prompt(self, question: str, search_results: Optional[List[Dict[str, str]]] = None) -> str:
-        """Create a prompt for the model with optional search results"""
-        # 检测问题类型
-        question_lower = question.lower()
-        is_multiple_choice = "option" in question_lower or re.search(r'[a-d]\)', question)
-        is_numerical = "how many" in question_lower or "number of" in question_lower
-        is_list_question = any(word in question_lower for word in ["list", "name all", "what are"])
-        is_date_question = "when" in question_lower or "what year" in question_lower or "date" in question_lower
-        is_yes_no = question_lower.startswith("is ") or question_lower.startswith("are ") or question_lower.startswith("does ") or question_lower.startswith("do ")
-        
-        prompt = [f"Question: {question}\n\n"]
-        
-        if search_results:
-            prompt.append("I found the following information:\n")
-            for i, result in enumerate(search_results, 1):
-                title = result.get('title', 'No title')
-                body = result.get('body', 'No description')[:300]
-                prompt.append(f"Source {i}: {title}\n{body}\n\n")
-        
-        prompt.append("Instructions:\n")
-        
-        # 添加针对特定问题类型的指导
-        if is_multiple_choice:
-            prompt.append("- This is a multiple choice question. Respond ONLY with the letter(s) of the correct option(s), like 'a' or 'b, c'.\n")
-        elif is_numerical:
-            prompt.append("- This is a numerical question. Respond ONLY with the number, without any units or explanation.\n")
-        elif is_list_question:
-            prompt.append("- This is a list question. Provide items as comma-separated values without numbering or bullet points.\n")
-        elif is_date_question:
-            prompt.append("- This is a date question. Provide only the specific date or year without explanation.\n")
-        elif is_yes_no:
-            prompt.append("- This is a yes/no question. Respond ONLY with 'yes' or 'no'.\n")
-        
-        prompt.append("- Your answer must be extremely concise - no explanations, no reasoning, no context.\n")
-        prompt.append("- If you cannot determine the answer with high confidence, respond ONLY with 'Unknown'.\n")
-        prompt.append("- NEVER include phrases like 'the answer is' or 'based on'.\n\n")
-        
-        # 添加针对特定问题的示例
-        if is_multiple_choice:
-            prompt.append("Example: If asked 'Which options show prime numbers? a) 4 b) 7 c) 11 d) 15', answer only 'b, c'\n\n")
-        elif is_numerical:
-            prompt.append("Example: If asked 'How many planets are in our solar system?', answer only '8'\n\n")
-        elif is_list_question:
-            prompt.append("Example: If asked 'List the Great Lakes', answer only 'Superior, Michigan, Huron, Erie, Ontario'\n\n")
-        
-        prompt.append("Answer: ")
-        
-        return "".join(prompt)
-        
-    def should_use_search(self, question: str) -> bool:
-        """Determine if search should be used for this question"""
-        question_lower = question.lower()
-        
-        # 不应该搜索的问题类型
-        no_search_patterns = [
-            "tfel", # 反向拼写问题
-            "chess position",
-            "image",
-            "write a",
-            "calculate",
-            "compute",
-            "solve this equation",
-            "what is the opposite of",
-            "what does .* mean in"
-        ]
-        
-        for pattern in no_search_patterns:
-            if pattern in question_lower:
-                return False
-        
-        # 特殊处理反向拼写问题
-        if '.remna eht sa "tfel" drow eht fo etisoppo eht etirw' in question_lower:
-            return False
-            
-        # 应该搜索的问题类型
-        search_triggers = [
-            "what", "who", "when", "where", "how", "which", 
-            "why", "list", "name", "find", "identify", "describe",
-            "explain", "tell me", "show", "give", "provide",
-            "capital of", "population of", "invented", "published",
-            "released", "founded", "created", "discovered",
-            "located", "born", "died", "year", "date"
-        ]
-        
-        # 如果包含搜索触发词，应该搜索
-        if any(trigger in question_lower for trigger in search_triggers):
-            return True
-            
-        # 如果是问句但不包含特定模式，也应该搜索
-        if "?" in question and len(question_lower.split()) > 3:
-            return True
-            
-        return False
-    
-    def clean_answer(self, answer: str, question: str) -> str:
-        """Clean up the model's answer based on question type"""
-        # 基本清理
-        answer = answer.strip()
-        
-        # 移除常见前缀
-        prefixes_to_remove = [
-            "Answer:", "The answer is:", "I believe", "I think",
-            "Based on", "According to", "The answer would be",
-            "The correct answer is", "My answer is", "From the information",
-            "From the search results", "The information suggests",
-            "The sources indicate", "It appears that", "It seems that"
-        ]
-        
-        for prefix in prefixes_to_remove:
-            if answer.lower().startswith(prefix.lower()):
-                answer = answer[len(prefix):].strip()
-        
-        # 移除引号
-        if (answer.startswith('"') and answer.endswith('"')) or \
-           (answer.startswith("'") and answer.endswith("'")):
-            answer = answer[1:-1].strip()
-        
-        # 移除末尾的标点符号
-        answer = answer.rstrip(".!,;:")
-        
-        # 检测问题类型
-        question_lower = question.lower()
-        
-        # 处理特殊问题类型
-        if "how many" in question_lower or "number of" in question_lower:
-            # 尝试提取数字
-            numbers = re.findall(r'\d+', answer)
-            if numbers:
-                return numbers[0]
-        
-        elif "which" in question_lower and ("option" in question_lower or re.search(r'[a-d]\)', question)):
-            # 尝试提取选项字母
-            options = re.findall(r'[a-dA-D]', answer)
-            if options:
-                return ", ".join(option.lower() for option in options)
-        
-        elif question_lower.startswith("is ") or question_lower.startswith("are ") or question_lower.startswith("does ") or question_lower.startswith("do "):
-            # 处理是/否问题
-            answer_lower = answer.lower()
-            if "yes" in answer_lower:
-                return "yes"
-            elif "no" in answer_lower:
-                return "no"
-        
-        # 处理反向拼写问题
-        if '.remna eht sa "tfel" drow eht fo etisoppo eht etirw' in question_lower:
-            return "right"
-            
-        # 处理列表问题，确保格式正确
-        if any(word in question_lower for word in ["list", "name all", "what are"]):
-            # 移除列表标记
-            answer = re.sub(r'^\s*[\-\*\d]+\.\s*', '', answer)
-            answer = re.sub(r'\n\s*[\-\*\d]+\.\s*', ', ', answer)
-            
-            # 确保列表项之间使用逗号分隔
-            if "\n" in answer:
-                answer = answer.replace("\n", ", ")
-                
-            # 修复多余的逗号和空格
-            answer = re.sub(r',\s*,', ',', answer)
-            answer = re.sub(r'\s+', ' ', answer)
-            
-        return answer
-    
     def __call__(self, question: str) -> str:
-        """
-        Process a question and return an answer.
-        
-        Args:
-            question: The question to answer
-            
-        Returns:
-            The answer to the question
-        """
-        print(f"Agent received question: {question[:100]}...")
-        
-        # 特殊问题处理
-        if '.remna eht sa "tfel" drow eht fo etisoppo eht etirw' in question.lower():
-            return "right"
-            
-        if "chess position" in question.lower() or "image" in question.lower():
-            return "Unknown"
-            
-        # 确定是否应该使用搜索
-        should_search = self.should_use_search(question)
-        
-        search_results = None
-        if should_search and self.search_tool:
-            print(f"Searching for information about: {question}")
-            # 使用增强的搜索查询
-            search_query = self.enhance_search_query(question)
-            search_response = self.search_tool(search_query, max_results=8)
-            search_results = search_response.get("results", [])
-            print(f"Found {len(search_results)} search results")
-        
-        # 创建提示词和生成回答
-        prompt = self.create_prompt(question, search_results)
-        system_prompt = self.create_system_prompt()
-        
-        print("Generating response with LLM...")
-        # 使用较低的温度以获得更确定性的回答
-        response = self.model.generate(prompt, system_prompt, temperature=0.1)
-        
-        # 清理回答
-        answer = self.clean_answer(response, question)
-        
-        print(f"Final answer: {answer[:100]}...")
-        return answer
+        print(f"Agent received question (first 50 chars): {question[:50]}...")
+        # Wrap the question in a HumanMessage from langchain_core
+        messages = [HumanMessage(content=question)]
+        messages = self.graph.invoke({"messages": messages})
+        answer = messages['messages'][-1].content
+        return answer[14:]
+
 
-# 简化版本，不使用OAuthProfile
-def run_and_submit_all():
+def run_and_submit_all( profile: gr.OAuthProfile | None):
     """
-    Fetches all questions, runs the Agent on them, submits all answers,
+    Fetches all questions, runs the BasicAgent on them, submits all answers,
     and displays the results.
     """
-    space_id = os.getenv("SPACE_ID")
+    # --- 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:
-        api_key = os.getenv("GEMINI_API_KEY")
-        if not api_key:
-            return "Error: GEMINI_API_KEY environment variable not found. Please set it in your Space settings.", None
-        
-        model = LiteLLMModel(model_id="gemini/gemini-2.0-flash-lite", api_key='AIzaSyAhmwogxZFBtt7_OUsKQGNeOYF7ced39bM')
-        agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)
+        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"
-    if not space_id:
-        agent_code = "https://huggingface.co/spaces/lethaq/Final_Assignment_Template/tree/main" 
-    print(f"Agent code URL: {agent_code}")
+    print(agent_code)
 
+    # 2. Fetch Questions
     print(f"Fetching questions from: {questions_url}")
     try:
-        response = requests.get(questions_url, timeout=20)
+        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("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
+         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...")
@@ -489,40 +93,34 @@ def run_and_submit_all():
             print(f"Skipping item with missing task_id or question: {item}")
             continue
         try:
-        # ① Attachment 摘要插入
-            attachment_context = fetch_and_summarize_attachment(task_id, question_text)
-        # ② 拼 prompt（根據你的 agent 用法）：
-        # （方案A）如果 agent 支援 attachment_context 參數
-        # submitted_answer = agent(question_text, attachment_context=attachment_context)
-        # （方案B）最直接：把 attachment 拼到問題開頭
-            full_question = (attachment_context + "\n" + question_text).strip()
-            submitted_answer = agent(full_question)
+            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})
-            print(f"Answer for task {task_id}: {submitted_answer[:50]}...")
         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}"})
-
+             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:
-        submission_dict = {
-            "username": DEFAULT_USERNAME,
-            "agent_code": agent_code,
-            "answers": answers_payload
-        }
-        response = requests.post(submit_url, json=submission_dict, timeout=60)
+        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"Score: {result_data.get('score', 'N/A')}% "
+            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)
@@ -557,62 +155,38 @@ def run_and_submit_all():
 
 # --- Build Gradio Interface using Blocks ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Gemini Agent for GAIA Benchmark")
+    gr.Markdown("# Basic Agent Evaluation Runner")
     gr.Markdown(
         """
         **Instructions:**
-        1. Make sure you have set the GEMINI_API_KEY environment variable in your Space settings.
-        2. Click 'Run Evaluation & Submit All Answers' to fetch questions, run the agent, and submit answers.
-        
-        This agent uses:
-        - Gemini 2.0 Flash Lite model for reasoning
-        - DuckDuckGo search for retrieving information
+        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)
 
-    # Add a single question test feature
-    gr.Markdown("## Test Single Question")
-    with gr.Row():
-        question_in = gr.Textbox(label="Question", lines=3)
-        answer_out = gr.Textbox(label="Answer", lines=3, interactive=False)
-    
-    test_btn = gr.Button("Test Question", variant="secondary")
-    
-    # Add a function to test a single question
-    def test_single_question(question):
-        try:
-            api_key = os.getenv("GEMINI_API_KEY")
-            if not api_key:
-                return "Error: GEMINI_API_KEY environment variable not found"
-            
-            model = LiteLLMModel(model_id="gemini/gemini-2.0-flash-lite", api_key=api_key)
-            agent = CodeAgent(tools=[DuckDuckGoSearchTool()], model=model)
-            answer = agent(question)
-            return answer
-        except Exception as e:
-            return f"Error: {str(e)}"
-
-    # 完全移除OAuthProfile相关代码
     run_button.click(
         fn=run_and_submit_all,
         outputs=[status_output, results_table]
     )
-    
-    test_btn.click(
-        fn=test_single_question,
-        inputs=[question_in],
-        outputs=[answer_out]
-    )
 
 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") 
+    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
 
     if space_host_startup:
         print(f"✅ SPACE_HOST found: {space_host_startup}")
@@ -620,7 +194,7 @@ if __name__ == "__main__":
     else:
         print("ℹ️  SPACE_HOST environment variable not found (running locally?).")
 
-    if space_id_startup: 
+    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")
@@ -629,5 +203,6 @@ if __name__ == "__main__":
 
     print("-"*(60 + len(" App Starting ")) + "\n")
 
-    print("Launching Gradio Interface for Gemini Agent Evaluation...")
-    demo.launch(debug=False, share=False)
+    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    demo.launch(debug=True, share=False)
+