Update agent.py

agent.py

@@ -1,5 +1,5 @@
 """
-agent.py - Minimal Claude implementation for GAIA challenge
+agent.py - Claude implementation for GAIA challenge
 -----------------------------------------------------------
 A simplified implementation with direct litellm access to Anthropic's Claude
 """
@@ -114,12 +114,18 @@ All answers are graded by exact string match, so format carefully!"""
                 raise
 
 # --------------------------------------------------------------------------- #
-# Custom tool: fetch GAIA attachments
+# Tools section - All tools used by the agent
 # --------------------------------------------------------------------------- #
 @tool
 def gaia_file_reader(file_id: str) -> str:
     """
-    Download a GAIA attachment and return its contents
+    Download a GAIA attachment and return its contents.
+    
+    Args:
+        file_id: The identifier of the file to download from GAIA API.
+        
+    Returns:
+        The content of the file as a string (text files) or base64-encoded (binary files).
     """
     try:
         raw = _download_file(file_id)
@@ -130,12 +136,18 @@ def gaia_file_reader(file_id: str) -> str:
     except Exception as exc:
         return f"ERROR downloading {file_id}: {exc}"
 
-# --------------------------------------------------------------------------- #
-# Additional tools
-# --------------------------------------------------------------------------- #
 @tool
 def save_and_read_file(content: str, filename: Optional[str] = None) -> str:
-    """Save content to a file and return the path"""
+    """
+    Save content to a temporary file and return the path.
+    
+    Args:
+        content: The content to save to the file.
+        filename: Optional filename, will generate a random name if not provided.
+        
+    Returns:
+        Path to the saved file.
+    """
     temp_dir = tempfile.gettempdir()
     if filename is None:
         temp_file = tempfile.NamedTemporaryFile(delete=False)
@@ -150,7 +162,16 @@ def save_and_read_file(content: str, filename: Optional[str] = None) -> str:
 
 @tool
 def analyze_csv_file(file_path: str, query: str) -> str:
-    """Analyze a CSV file with pandas"""
+    """
+    Analyze a CSV file using pandas and answer questions about it.
+    
+    Args:
+        file_path: Path to the CSV file to analyze.
+        query: A question or instruction about what to analyze in the file.
+        
+    Returns:
+        Analysis results as text.
+    """
     try:
         import pandas as pd
         df = pd.read_csv(file_path)
@@ -168,7 +189,16 @@ def analyze_csv_file(file_path: str, query: str) -> str:
 
 @tool
 def analyze_excel_file(file_path: str, query: str) -> str:
-    """Analyze an Excel file with pandas"""
+    """
+    Analyze an Excel file using pandas and answer questions about it.
+    
+    Args:
+        file_path: Path to the Excel file to analyze.
+        query: A question or instruction about what to analyze in the file.
+        
+    Returns:
+        Analysis results as text.
+    """
     try:
         import pandas as pd
         df = pd.read_excel(file_path)
@@ -184,6 +214,73 @@ def analyze_excel_file(file_path: str, query: str) -> str:
     except Exception as e:
         return f"Error analyzing Excel file: {str(e)}"
 
+@tool
+def download_file_from_url(url: str, filename: Optional[str] = None) -> str:
+    """
+    Download a file from a URL and save it to a temporary location.
+    
+    Args:
+        url: The URL to download from.
+        filename: Optional filename, will generate one based on URL if not provided.
+        
+    Returns:
+        Path to the downloaded file.
+    """
+    try:
+        # Parse URL to get filename if not provided
+        if not filename:
+            path = urlparse(url).path
+            filename = os.path.basename(path)
+            if not filename:
+                # Generate a random name if we couldn't extract one
+                import uuid
+                filename = f"downloaded_{uuid.uuid4().hex[:8]}"
+        
+        # Create temporary file
+        temp_dir = tempfile.gettempdir()
+        filepath = os.path.join(temp_dir, filename)
+        
+        # Download the file
+        response = requests.get(url, stream=True)
+        response.raise_for_status()
+        
+        # Save the file
+        with open(filepath, 'wb') as f:
+            for chunk in response.iter_content(chunk_size=8192):
+                f.write(chunk)
+        
+        return f"File downloaded to {filepath}. You can now process this file."
+    except Exception as e:
+        return f"Error downloading file: {str(e)}"
+
+@tool
+def extract_text_from_image(image_path: str) -> str:
+    """
+    Extract text from an image using pytesseract (if available).
+    
+    Args:
+        image_path: Path to the image file to extract text from.
+        
+    Returns:
+        Extracted text from the image.
+    """
+    try:
+        # Try to import pytesseract
+        import pytesseract
+        from PIL import Image
+        
+        # Open the image
+        image = Image.open(image_path)
+        
+        # Extract text
+        text = pytesseract.image_to_string(image)
+        
+        return f"Extracted text from image:\n\n{text}"
+    except ImportError:
+        return "Error: pytesseract is not installed. Please install it with 'pip install pytesseract' and ensure Tesseract OCR is installed on your system."
+    except Exception as e:
+        return f"Error extracting text from image: {str(e)}"
+
 # --------------------------------------------------------------------------- #
 # ClaudeAgent - Main class for GAIA challenge
 # --------------------------------------------------------------------------- #
@@ -210,7 +307,9 @@ class ClaudeAgent:
                 save_and_read_file,
                 analyze_csv_file,
                 analyze_excel_file,
-                gaia_file_reader
+                gaia_file_reader,
+                download_file_from_url,
+                extract_text_from_image
             ]
             
             # Create the CodeAgent