fix: remove default stream value for agent

Author: yugasun

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

@@ -713,7 +713,7 @@ def _chat_completion(self, messages, temperature=0.2, tools=None, stream=True, r
             display_error(f"Error in chat completion: {e}")
             return None
 
-    def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=True):
+    def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pydantic=None, reasoning_steps=False, stream=None):
         # Log all parameter values when in debug mode
         if logging.getLogger().getEffectiveLevel() == logging.DEBUG:
             param_info = {
@@ -949,7 +949,7 @@ def chat(self, prompt, temperature=0.2, tools=None, output_json=None, output_pyd
 
                         logging.debug(f"{self.name} reflection count {reflection_count + 1}, continuing reflection process")
                         messages.append({"role": "user", "content": "Now regenerate your response using the reflection you made"})
-                        response = self._chat_completion(messages, temperature=temperature, tools=None, stream=True)
+                        response = self._chat_completion(messages, temperature=temperature, tools=None, stream=stream)
                         response_text = response.choices[0].message.content.strip()
                         reflection_count += 1
                         continue  # Continue the loop for more reflections

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

@@ -45,7 +45,7 @@ def process_video(video_path: str, seconds_per_frame=2):
     return base64_frames
 
 class PraisonAIAgents:
-    def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_retries=5, process="sequential", manager_llm=None, memory=False, memory_config=None, embedder=None, user_id=None, max_iter=10, stream=True):
+    def __init__(self, agents, tasks=None, verbose=0, completion_checker=None, max_retries=5, process="sequential", manager_llm=None, memory=False, memory_config=None, embedder=None, user_id=None, max_iter=10, stream=None):
         # Add check at the start if memory is requested
         if memory:
             try: