updates

agent.py

@@ -76,71 +76,12 @@ def build_graph():
     # Bind tools to LLM
     llm_with_tools = llm.bind_tools(tools)
 
-    def clean_answer(answer: any) -> str:
-        """
-        Clean up the answer to remove common prefixes and formatting
-        that models often add but that can cause exact match failures.
-        
-        Args:
-            answer: The raw answer from the model
-            
-        Returns:
-            The cleaned answer as a string
-        """
-        # Convert non-string types to strings
-        if not isinstance(answer, str):
-            # Handle numeric types (float, int)
-            if isinstance(answer, float):
-                # Format floating point numbers properly
-                # Check if it's an integer value in float form (e.g., 12.0)
-                if answer.is_integer():
-                    formatted_answer = str(int(answer))
-                else:
-                    # For currency values that might need formatting
-                    if abs(answer) >= 1000:
-                        formatted_answer = f"${answer:,.2f}"
-                    else:
-                        formatted_answer = str(answer)
-                return formatted_answer
-            elif isinstance(answer, int):
-                return str(answer)
-            else:
-                # For any other type
-                return str(answer)
-        
-        # Now we know answer is a string, so we can safely use string methods
-        # Normalize whitespace
-        answer = answer.strip()
-        
-        # Remove common prefixes and formatting that models add
-        prefixes_to_remove = [
-            "The answer is ", 
-            "Answer: ",
-            "Final answer: ",
-            "The result is ",
-            "To answer this question: ",
-            "Based on the information provided, ",
-            "According to the information: ",
-        ]
-        
-        for prefix in prefixes_to_remove:
-            if answer.startswith(prefix):
-                answer = answer[len(prefix):].strip()
-        
-        # Remove quotes if they wrap the entire answer
-        if (answer.startswith('"') and answer.endswith('"')) or (answer.startswith("'") and answer.endswith("'")):
-            answer = answer[1:-1].strip()
-        
-        return answer
-    
+       
     def assistant(state: MessagesState):
         messages_with_system_prompt = [sys_msg] + state["messages"]
         llm_response = llm_with_tools.invoke(messages_with_system_prompt)
-        
-        # Clean the answer
-        clean_text = clean_answer(llm_response.content)
-        
-        return {"messages": [AIMessage(content=json.dumps(clean_text, ensure_ascii=False))]}
+                
+        return {"messages": [AIMessage(content=json.dumps(llm_response.content, ensure_ascii=False))]}
 
     # --- Graph Definition ---
     builder = StateGraph(MessagesState)

scrapbook.py

@@ -0,0 +1,62 @@
+ def clean_answer(answer: any) -> str:
+        """
+        Clean up the answer to remove common prefixes and formatting
+        that models often add but that can cause exact match failures.
+        
+        Args:
+            answer: The raw answer from the model
+            
+        Returns:
+            The cleaned answer as a string
+        """
+        # Convert non-string types to strings
+        if not isinstance(answer, str):
+            # Handle numeric types (float, int)
+            if isinstance(answer, float):
+                # Format floating point numbers properly
+                # Check if it's an integer value in float form (e.g., 12.0)
+                if answer.is_integer():
+                    formatted_answer = str(int(answer))
+                else:
+                    # For currency values that might need formatting
+                    if abs(answer) >= 1000:
+                        formatted_answer = f"${answer:,.2f}"
+                    else:
+                        formatted_answer = str(answer)
+                return formatted_answer
+            elif isinstance(answer, int):
+                return str(answer)
+            else:
+                # For any other type
+                return str(answer)
+        
+        # Now we know answer is a string, so we can safely use string methods
+        # Normalize whitespace
+        answer = answer.strip()
+        
+        # Remove common prefixes and formatting that models add
+        prefixes_to_remove = [
+            "The answer is ", 
+            "Answer: ",
+            "Final answer: ",
+            "The result is ",
+            "To answer this question: ",
+            "Based on the information provided, ",
+            "According to the information: ",
+        ]
+        
+        for prefix in prefixes_to_remove:
+            if answer.startswith(prefix):
+                answer = answer[len(prefix):].strip()
+        
+        # Remove quotes if they wrap the entire answer
+        if (answer.startswith('"') and answer.endswith('"')) or (answer.startswith("'") and answer.endswith("'")):
+            answer = answer[1:-1].strip()
+        
+        return answer
+
+
+
+# Clean the answer
+        clean_text = clean_answer(llm_response.content)
+