diff --git a/llama_stack/apis/agents/agents.py b/llama_stack/apis/agents/agents.py
index c904fdbef..eb3399788 100644
--- a/llama_stack/apis/agents/agents.py
+++ b/llama_stack/apis/agents/agents.py
@@ -296,9 +296,6 @@ class AgentTurnCreateRequest(AgentConfigOverridablePerTurn):
     stream: Optional[bool] = False
     tool_config: Optional[ToolConfig] = None
 
-    # TODO (xiyan): temporary flag, will remove for 0.1.5
-    allow_turn_resume: Optional[bool] = False
-
 
 @json_schema_type
 class AgentTurnResumeRequest(BaseModel):
@@ -355,7 +352,6 @@ class Agents(Protocol):
         documents: Optional[List[Document]] = None,
         toolgroups: Optional[List[AgentToolGroup]] = None,
         tool_config: Optional[ToolConfig] = None,
-        allow_turn_resume: Optional[bool] = False,
     ) -> Union[Turn, AsyncIterator[AgentTurnResponseStreamChunk]]: ...
 
     @webmethod(
diff --git a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
index 7a6cc551b..25cf0990a 100644
--- a/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agent_instance.py
@@ -244,22 +244,13 @@ class ChatAgent(ShieldRunnerMixin):
             )
             await self.storage.add_turn_to_session(request.session_id, turn)
 
-            if output_message.tool_calls and request.allow_turn_resume:
-                chunk = AgentTurnResponseStreamChunk(
-                    event=AgentTurnResponseEvent(
-                        payload=AgentTurnResponseTurnAwaitingInputPayload(
-                            turn=turn,
-                        )
-                    )
-                )
-            else:
-                chunk = AgentTurnResponseStreamChunk(
-                    event=AgentTurnResponseEvent(
-                        payload=AgentTurnResponseTurnCompletePayload(
-                            turn=turn,
-                        )
+            chunk = AgentTurnResponseStreamChunk(
+                event=AgentTurnResponseEvent(
+                    payload=AgentTurnResponseTurnCompletePayload(
+                        turn=turn,
                     )
                 )
+            )
 
             yield chunk
 
@@ -686,10 +677,16 @@ class ChatAgent(ShieldRunnerMixin):
                             message.content = [message.content] + output_attachments
                     yield message
                 else:
-                    logcat.debug("agents", f"completion message with EOM (iter: {n_iter}): {str(message)}")
+                    logcat.debug(
+                        "agents",
+                        f"completion message with EOM (iter: {n_iter}): {str(message)}",
+                    )
                     input_messages = input_messages + [message]
             else:
-                logcat.debug("agents", f"completion message (iter: {n_iter}) from the model: {str(message)}")
+                logcat.debug(
+                    "agents",
+                    f"completion message (iter: {n_iter}) from the model: {str(message)}",
+                )
                 # 1. Start the tool execution step and progress
                 step_id = str(uuid.uuid4())
                 yield AgentTurnResponseStreamChunk(
@@ -810,7 +807,7 @@ class ChatAgent(ShieldRunnerMixin):
     ) -> Tuple[List[ToolDefinition], Dict[str, str]]:
         # Determine which tools to include
         agent_config_toolgroups = {
-            toolgroup.name if isinstance(toolgroup, AgentToolGroupWithArgs) else toolgroup
+            (toolgroup.name if isinstance(toolgroup, AgentToolGroupWithArgs) else toolgroup)
             for toolgroup in self.agent_config.toolgroups
         }
         toolgroups_for_turn_set = (
diff --git a/llama_stack/providers/inline/agents/meta_reference/agents.py b/llama_stack/providers/inline/agents/meta_reference/agents.py
index b5eb12c49..db33bca4a 100644
--- a/llama_stack/providers/inline/agents/meta_reference/agents.py
+++ b/llama_stack/providers/inline/agents/meta_reference/agents.py
@@ -140,7 +140,6 @@ class MetaReferenceAgentsImpl(Agents):
         documents: Optional[List[Document]] = None,
         stream: Optional[bool] = False,
         tool_config: Optional[ToolConfig] = None,
-        allow_turn_resume: Optional[bool] = False,
     ) -> AsyncGenerator:
         request = AgentTurnCreateRequest(
             agent_id=agent_id,
@@ -150,7 +149,6 @@ class MetaReferenceAgentsImpl(Agents):
             toolgroups=toolgroups,
             documents=documents,
             tool_config=tool_config,
-            allow_turn_resume=allow_turn_resume,
         )
         if stream:
             return self._create_agent_turn_streaming(request)