Merge pull request #962 from MervinPraison/claude/issue-956-20250716-2316

fix: enable real-time streaming regardless of verbose setting

Author: MervinPraison

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

@@ -1128,11 +1128,6 @@ def _chat_completion(self, messages, temperature=0.2, tools=None, stream=True, r
                     )
             else:
                 # Use the standard OpenAI client approach with tool support
-                def custom_display_fn(text, start_time):
-                    if self.verbose:
-                        return display_generating(text, start_time)
-                    return ""
-                
                 # Note: openai_client expects tools in various formats and will format them internally
                 # But since we already have formatted_tools, we can pass them directly
                 if self._openai_client is None:
@@ -1145,8 +1140,8 @@ def custom_display_fn(text, start_time):
                     tools=formatted_tools,  # Already formatted for OpenAI
                     execute_tool_fn=self.execute_tool,
                     stream=stream,
-                    console=self.console if self.verbose else None,
-                    display_fn=display_generating if stream and self.verbose else None,
+                    console=self.console if (self.verbose or stream) else None,
+                    display_fn=display_generating if stream else None,
                     reasoning_steps=reasoning_steps,
                     verbose=self.verbose,
                     max_iterations=10

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

@@ -2468,18 +2468,14 @@ def response(
             )
 
             if stream:
-                if verbose:
-                    with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
-                        for chunk in litellm.completion(**completion_params):
-                            content = self._process_streaming_chunk(chunk)
-                            if content:
-                                response_text += content
-                                live.update(display_generating(response_text, start_time))
-                else:
+                with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
                     for chunk in litellm.completion(**completion_params):
                         content = self._process_streaming_chunk(chunk)
                         if content:
                             response_text += content
+                            live.update(display_generating(response_text, start_time))
+                        if content:
+                            response_text += content
             else:
                 response = litellm.completion(**completion_params)
                 response_text = response.choices[0].message.content.strip() if response.choices[0].message.content else ""
@@ -2568,18 +2564,14 @@ async def aresponse(
             )
 
             if stream:
-                if verbose:
-                    with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
-                        async for chunk in await litellm.acompletion(**completion_params):
-                            content = self._process_streaming_chunk(chunk)
-                            if content:
-                                response_text += content
-                                live.update(display_generating(response_text, start_time))
-                else:
+                with Live(display_generating("", start_time), console=console or self.console, refresh_per_second=4) as live:
                     async for chunk in await litellm.acompletion(**completion_params):
                         content = self._process_streaming_chunk(chunk)
                         if content:
                             response_text += content
+                            live.update(display_generating(response_text, start_time))
+                        if content:
+                            response_text += content
             else:
                 response = await litellm.acompletion(**completion_params)
                 response_text = response.choices[0].message.content.strip() if response.choices[0].message.content else ""