fix: pass stream parameter from Agent to LLM

The Agent class was not passing the stream parameter to the LLM's get_response() method, causing the LLM to always use its default stream=True behavior regardless of the Agent's configuration.

This fix ensures that when an Agent is created with stream=False or when chat() is called with stream=False, this preference is properly passed to the LLM.

Co-authored-by: Mervin Praison <[email protected]>

Author: claude[bot]

src/praisonai-agents/praisonaiagents/agent/agent.py

@@ -1235,7 +1235,8 @@ def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pyd
                     agent_role=self.role,
                     agent_tools=[t.__name__ if hasattr(t, '__name__') else str(t) for t in (tools if tools is not None else self.tools)],
                     execute_tool_fn=self.execute_tool,  # Pass tool execution function
-                    reasoning_steps=reasoning_steps
+                    reasoning_steps=reasoning_steps,
+                    stream=stream  # Pass the stream parameter from chat method
                     )
 
                     self.chat_history.append({"role": "assistant", "content": response_text})