improving pasring of responses for new ReAct agent

langgraphagent.py

@@ -21,7 +21,7 @@ from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint
 
 from custom_tools import get_custom_tools_list
 from system_prompt import SYSTEM_PROMPT
-from utils import cleanup_answer
+from utils import cleanup_answer, extract_text_from_content
 import config
 
 # Suppress BeautifulSoup GuessedAtParserWarning
@@ -252,36 +252,14 @@ class LangGraphAgent:
             print(f"{'='*60}\n")
 
             answer = response.get("answer")
-            if answer is None:
+            if not answer or answer is None:
                 print("[WARNING] Agent completed but returned None as answer")
                 return "Error: No answer generated"
 
-            # Final safety check: ensure answer is plain text string
-            if isinstance(answer, dict):
-                # If it's a dict, try to extract text field
-                if 'text' in answer:
-                    answer = answer['text']
-                else:
-                    answer = str(answer)
-                print(f"[WARNING] Answer was dict, extracted: {answer[:100]}")
-            elif isinstance(answer, list):
-                # If it's a list, extract text from each item
-                text_parts = []
-                for item in answer:
-                    if isinstance(item, dict) and 'text' in item:
-                        text_parts.append(item['text'])
-                    else:
-                        text_parts.append(str(item))
-                answer = " ".join(text_parts)
-                print(f"[WARNING] Answer was list, extracted: {answer[:100]}")
-            elif not isinstance(answer, str):
-                # Convert to string if it's any other type
-                answer = str(answer)
-                print(f"[WARNING] Answer was {type(answer)}, converted to string")
-
-            answer = answer.strip()
+            # Use utility function to extract text from various content formats
+            answer = extract_text_from_content(answer)
 
-            # Clean up the answer using utility function
+            # Clean up the answer using utility function (includes stripping)
             answer = cleanup_answer(answer)
 
             print(f"[FINAL ANSWER] {answer}")

reactlanggraphagent.py

@@ -15,7 +15,7 @@ from langchain_core.messages import HumanMessage
 
 from custom_tools import get_custom_tools_list
 from system_prompt import SYSTEM_PROMPT
-from utils import cleanup_answer
+from utils import cleanup_answer, extract_text_from_content
 import config
 
 # Suppress BeautifulSoup GuessedAtParserWarning
@@ -63,7 +63,7 @@ class ReActLangGraphAgent:
         agent_graph = create_react_agent(
             model=self.llm,
             tools=self.tools,
-            state_modifier=SYSTEM_PROMPT  # System prompt is added as state modifier
+            prompt=SYSTEM_PROMPT  # System prompt is added via the prompt parameter
         )
 
         return agent_graph
@@ -140,9 +140,17 @@ class ReActLangGraphAgent:
 
             # Get the last message (the agent's final response)
             last_message = messages[-1]
-            answer = last_message.content if hasattr(last_message, 'content') else str(last_message)
 
-            if answer is None:
+            # Extract content from the message
+            if hasattr(last_message, 'content'):
+                content = last_message.content
+            else:
+                content = str(last_message)
+
+            # Use utility function to extract text from various content formats
+            answer = extract_text_from_content(content)
+
+            if not answer or answer is None:
                 print("[WARNING] Agent completed but returned None as answer")
                 return "Error: No answer generated"
 

utils.py

@@ -48,6 +48,61 @@ def retry_with_backoff(
     return decorator
 
 
+def extract_text_from_content(content: Any) -> str:
+    """
+    Extract plain text from various content formats returned by LLM agents.
+
+    This function handles multiple content formats:
+    - String: Returns as-is
+    - Dict with 'text' field: Extracts the text value
+    - List of content blocks: Extracts text from all blocks with type='text'
+    - Other types: Converts to string
+
+    Args:
+        content: The content object from an LLM response (can be str, dict, list, etc.)
+
+    Returns:
+        str: Extracted plain text content
+    """
+    # Handle dict format (e.g., {'text': 'answer'})
+    if isinstance(content, dict):
+        if 'text' in content:
+            return str(content['text'])
+        else:
+            print(f"[WARNING] Content was dict without 'text' field, converting to string")
+            return str(content)
+
+    # Handle list format (e.g., [{'type': 'text', 'text': 'answer'}])
+    elif isinstance(content, list):
+        text_parts = []
+        for item in content:
+            if isinstance(item, dict):
+                # Look for items with type='text' and extract the 'text' field
+                if item.get('type') == 'text':
+                    text_parts.append(str(item.get('text', '')))
+                # Fallback: if there's a 'text' field but no type, use it
+                elif 'text' in item:
+                    text_parts.append(str(item['text']))
+            elif isinstance(item, str):
+                text_parts.append(item)
+            else:
+                text_parts.append(str(item))
+
+        result = ' '.join(text_parts)
+        if len(content) > 1 or (len(content) == 1 and isinstance(content[0], dict)):
+            print(f"[INFO] Extracted text from list with {len(content)} item(s)")
+        return result
+
+    # Handle string format (already plain text)
+    elif isinstance(content, str):
+        return content
+
+    # Fallback for other types
+    else:
+        print(f"[WARNING] Content was {type(content)}, converting to string")
+        return str(content)
+
+
 def cleanup_answer(answer: Any) -> str:
     """
     Clean up the agent answer to ensure it's in plain text format.