Update app.py

app.py

@@ -1,34 +1,262 @@
 import os
 import gradio as gr
 import requests
-import inspect
 import pandas as pd
+import anthropic
+import re
+from duckduckgo_search import DDGS
 
-# (Keep Constants as is)
 # --- Constants ---
 DEFAULT_API_URL = "https://agents-course-unit4-scoring.hf.space"
 
-# --- Basic Agent Definition ---
-# ----- THIS IS WERE YOU CAN BUILD WHAT YOU WANT ------
-class BasicAgent:
+# --- Tool Implementations ---
+
+def web_search(query: str) -> str:
+    """Search the web using DuckDuckGo."""
+    try:
+        with DDGS() as ddgs:
+            results = list(ddgs.text(query, max_results=5))
+        if not results:
+            return "No results found."
+        output = []
+        for r in results:
+            output.append(f"Title: {r.get('title', '')}\nURL: {r.get('href', '')}\nSnippet: {r.get('body', '')}\n")
+        return "\n---\n".join(output)
+    except Exception as e:
+        return f"Search error: {e}"
+
+
+def fetch_page(url: str) -> str:
+    """Fetch content from a URL."""
+    try:
+        headers = {"User-Agent": "Mozilla/5.0"}
+        response = requests.get(url, headers=headers, timeout=10)
+        response.raise_for_status()
+        # Basic text extraction
+        text = response.text
+        # Remove HTML tags crudely
+        text = re.sub(r'<[^>]+>', ' ', text)
+        text = re.sub(r'\s+', ' ', text).strip()
+        return text[:3000]
+    except Exception as e:
+        return f"Error fetching page: {e}"
+
+
+def run_python(code: str) -> str:
+    """Execute Python code and return the output."""
+    import sys
+    from io import StringIO
+    old_stdout = sys.stdout
+    sys.stdout = StringIO()
+    try:
+        exec_globals = {}
+        exec(code, exec_globals)
+        output = sys.stdout.getvalue()
+        return output if output else "Code executed successfully (no output)."
+    except Exception as e:
+        return f"Error executing code: {e}"
+    finally:
+        sys.stdout = old_stdout
+
+
+def wikipedia_search(query: str) -> str:
+    """Search Wikipedia for a topic."""
+    try:
+        search_url = "https://en.wikipedia.org/w/api.php"
+        params = {
+            "action": "query",
+            "list": "search",
+            "srsearch": query,
+            "format": "json",
+            "srlimit": 3,
+        }
+        response = requests.get(search_url, params=params, timeout=10)
+        data = response.json()
+        results = data.get("query", {}).get("search", [])
+        if not results:
+            return "No Wikipedia results found."
+        
+        # Fetch first result's summary
+        title = results[0]["title"]
+        summary_params = {
+            "action": "query",
+            "titles": title,
+            "prop": "extracts",
+            "exintro": True,
+            "explaintext": True,
+            "format": "json",
+        }
+        summary_response = requests.get(search_url, params=summary_params, timeout=10)
+        summary_data = summary_response.json()
+        pages = summary_data.get("query", {}).get("pages", {})
+        for page_id, page in pages.items():
+            extract = page.get("extract", "No content available.")
+            return f"Wikipedia: {title}\n\n{extract[:2000]}"
+        return "No content found."
+    except Exception as e:
+        return f"Wikipedia error: {e}"
+
+
+# --- Tool Definitions for Claude API ---
+TOOLS = [
+    {
+        "name": "web_search",
+        "description": "Search the web for current information. Use this for facts, recent events, or anything that requires looking up.",
+        "input_schema": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "The search query"
+                }
+            },
+            "required": ["query"]
+        }
+    },
+    {
+        "name": "wikipedia_search",
+        "description": "Search Wikipedia for factual information about people, places, events, concepts, etc.",
+        "input_schema": {
+            "type": "object",
+            "properties": {
+                "query": {
+                    "type": "string",
+                    "description": "The topic to search on Wikipedia"
+                }
+            },
+            "required": ["query"]
+        }
+    },
+    {
+        "name": "fetch_page",
+        "description": "Fetch and read the content of a specific URL/webpage.",
+        "input_schema": {
+            "type": "object",
+            "properties": {
+                "url": {
+                    "type": "string",
+                    "description": "The URL to fetch"
+                }
+            },
+            "required": ["url"]
+        }
+    },
+    {
+        "name": "run_python",
+        "description": "Execute Python code for calculations, data processing, or logic. Returns stdout output.",
+        "input_schema": {
+            "type": "object",
+            "properties": {
+                "code": {
+                    "type": "string",
+                    "description": "Python code to execute"
+                }
+            },
+            "required": ["code"]
+        }
+    }
+]
+
+TOOL_FUNCTIONS = {
+    "web_search": web_search,
+    "wikipedia_search": wikipedia_search,
+    "fetch_page": fetch_page,
+    "run_python": run_python,
+}
+
+SYSTEM_PROMPT = """You are a general AI assistant solving benchmark questions. 
+
+For each question:
+1. Think carefully about what information you need
+2. Use tools to search for facts, do calculations, or fetch web pages
+3. Reason step by step
+4. Give ONLY the final answer - no explanation, no "FINAL ANSWER:" prefix
+
+Your answer should be:
+- A number (no units unless specified, no commas in numbers)
+- A short phrase (no articles like "the" or "a", no abbreviations for proper nouns)  
+- A comma-separated list of numbers/strings
+
+Be precise. The answer is checked by exact match."""
+
+
+class SmartAgent:
     def __init__(self):
-        print("BasicAgent initialized.")
+        api_key = os.getenv("ANTHROPIC_API_KEY")
+        if not api_key:
+            raise ValueError("ANTHROPIC_API_KEY environment variable not set!")
+        self.client = anthropic.Anthropic(api_key=api_key)
+        self.model = "claude-opus-4-5"
+        print("SmartAgent (Claude-powered) initialized.")
+
     def __call__(self, question: str) -> str:
-        print(f"Agent received question (first 50 chars): {question[:50]}...")
-        fixed_answer = "This is a default answer."
-        print(f"Agent returning fixed answer: {fixed_answer}")
-        return fixed_answer
-
-def run_and_submit_all( profile: gr.OAuthProfile | None):
-    """
-    Fetches all questions, runs the BasicAgent on them, submits all answers,
-    and displays the results.
-    """
-    # --- Determine HF Space Runtime URL and Repo URL ---
-    space_id = os.getenv("SPACE_ID") # Get the SPACE_ID for sending link to the code
+        print(f"\nQuestion: {question[:100]}...")
+        messages = [{"role": "user", "content": question}]
+        
+        max_iterations = 10
+        for iteration in range(max_iterations):
+            response = self.client.messages.create(
+                model=self.model,
+                max_tokens=4096,
+                system=SYSTEM_PROMPT,
+                tools=TOOLS,
+                messages=messages,
+            )
+            
+            # Check if we're done
+            if response.stop_reason == "end_turn":
+                # Extract text answer
+                for block in response.content:
+                    if hasattr(block, "text"):
+                        answer = block.text.strip()
+                        # Clean up any "FINAL ANSWER:" prefix if model adds it
+                        answer = re.sub(r'^FINAL ANSWER:\s*', '', answer, flags=re.IGNORECASE).strip()
+                        print(f"Answer: {answer}")
+                        return answer
+                return "No answer"
+            
+            # Process tool calls
+            if response.stop_reason == "tool_use":
+                # Add assistant's response to messages
+                messages.append({"role": "assistant", "content": response.content})
+                
+                # Execute all tool calls
+                tool_results = []
+                for block in response.content:
+                    if block.type == "tool_use":
+                        tool_name = block.name
+                        tool_input = block.input
+                        print(f"  Tool: {tool_name}({list(tool_input.values())[0] if tool_input else ''})")
+                        
+                        try:
+                            func = TOOL_FUNCTIONS.get(tool_name)
+                            if func:
+                                result = func(**tool_input)
+                            else:
+                                result = f"Unknown tool: {tool_name}"
+                        except Exception as e:
+                            result = f"Tool error: {e}"
+                        
+                        tool_results.append({
+                            "type": "tool_result",
+                            "tool_use_id": block.id,
+                            "content": str(result)[:5000],
+                        })
+                
+                messages.append({"role": "user", "content": tool_results})
+            else:
+                # Unexpected stop reason
+                break
+        
+        return "Unable to determine answer"
+
+
+def run_and_submit_all(profile: gr.OAuthProfile | None):
+    """Fetches all questions, runs the SmartAgent, submits answers, and displays results."""
+    space_id = os.getenv("SPACE_ID")
 
     if profile:
-        username= f"{profile.username}"
+        username = f"{profile.username}"
         print(f"User logged in: {username}")
     else:
         print("User not logged in.")
@@ -38,13 +266,13 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
     questions_url = f"{api_url}/questions"
     submit_url = f"{api_url}/submit"
 
-    # 1. Instantiate Agent ( modify this part to create your agent)
+    # 1. Instantiate Agent
     try:
-        agent = BasicAgent()
+        agent = SmartAgent()
     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)
 
@@ -55,21 +283,12 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
         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
+            return "Fetched questions list is empty or invalid format.", None
         print(f"Fetched {len(questions_data)} questions.")
-    except requests.exceptions.RequestException as e:
-        print(f"Error fetching questions: {e}")
-        return f"Error fetching questions: {e}", None
-    except requests.exceptions.JSONDecodeError as e:
-         print(f"Error decoding JSON response from questions endpoint: {e}")
-         print(f"Response text: {response.text[:500]}")
-         return f"Error decoding server response for questions: {e}", None
     except Exception as e:
-        print(f"An unexpected error occurred fetching questions: {e}")
-        return f"An unexpected error occurred fetching questions: {e}", None
+        return f"Error fetching questions: {e}", None
 
-    # 3. Run your Agent
+    # 3. Run Agent on all questions
     results_log = []
     answers_payload = []
     print(f"Running agent on {len(questions_data)} questions...")
@@ -84,22 +303,17 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             answers_payload.append({"task_id": task_id, "submitted_answer": submitted_answer})
             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": submitted_answer})
         except Exception as e:
-             print(f"Error running agent on task {task_id}: {e}")
-             results_log.append({"Task ID": task_id, "Question": question_text, "Submitted Answer": f"AGENT ERROR: {e}"})
+            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 
+    # 4. Submit
     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 = requests.post(submit_url, json=submission_data, timeout=120)
         response.raise_for_status()
         result_data = response.json()
         final_status = (
@@ -110,60 +324,40 @@ def run_and_submit_all( profile: gr.OAuthProfile | None):
             f"Message: {result_data.get('message', 'No message received.')}"
         )
         print("Submission successful.")
-        results_df = pd.DataFrame(results_log)
-        return final_status, results_df
+        return final_status, pd.DataFrame(results_log)
     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:
+        except Exception:
             error_detail += f" Response: {e.response.text[:500]}"
-        status_message = f"Submission Failed: {error_detail}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.Timeout:
-        status_message = "Submission Failed: The request timed out."
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
-    except requests.exceptions.RequestException as e:
-        status_message = f"Submission Failed: Network error - {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"Submission Failed: {error_detail}", pd.DataFrame(results_log)
     except Exception as e:
-        status_message = f"An unexpected error occurred during submission: {e}"
-        print(status_message)
-        results_df = pd.DataFrame(results_log)
-        return status_message, results_df
+        return f"An unexpected error occurred during submission: {e}", pd.DataFrame(results_log)
 
 
-# --- Build Gradio Interface using Blocks ---
+# --- Gradio Interface ---
 with gr.Blocks() as demo:
-    gr.Markdown("# Basic Agent Evaluation Runner")
+    gr.Markdown("# 🤖 Smart Agent — GAIA Benchmark Runner")
     gr.Markdown(
         """
+        **Powered by Claude with Web Search, Wikipedia, and Python tools**
+        
         **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.
+        1. Make sure `ANTHROPIC_API_KEY` is set in your Space secrets
+        2. Log in with your Hugging Face account below
+        3. Click **Run Evaluation & Submit All Answers**
+        
+        The agent will fetch all 20 GAIA questions, reason through each one using tools, and submit your answers.
         """
     )
 
     gr.LoginButton()
 
-    run_button = gr.Button("Run Evaluation & Submit All Answers")
+    run_button = gr.Button("🚀 Run Evaluation & Submit All Answers", variant="primary")
 
     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(
@@ -172,25 +366,20 @@ with gr.Blocks() as demo:
     )
 
 if __name__ == "__main__":
-    print("\n" + "-"*30 + " App Starting " + "-"*30)
-    # Check for SPACE_HOST and SPACE_ID at startup for information
+    print("\n" + "-" * 30 + " App Starting " + "-" * 30)
     space_host_startup = os.getenv("SPACE_HOST")
-    space_id_startup = os.getenv("SPACE_ID") # Get SPACE_ID at startup
+    space_id_startup = os.getenv("SPACE_ID")
 
     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?).")
+        print("ℹ️ SPACE_HOST not found (running locally?)")
 
-    if space_id_startup: # Print repo URLs if SPACE_ID is found
+    if space_id_startup:
         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("ℹ️ SPACE_ID not found (running locally?)")
 
-    print("Launching Gradio Interface for Basic Agent Evaluation...")
+    print("-" * 74 + "\n")
+    print("Launching Gradio Interface...")
     demo.launch(debug=True, share=False)