Add parallel_tool_call to openai model client config (#6888)

Author: ekzhu

python/packages/autogen-agentchat/src/autogen_agentchat/tools/_agent.py

@@ -50,7 +50,7 @@ class AgentTool(TaskRunnerTool, Component[AgentToolConfig]):
 
 
             async def main() -> None:
-                model_client = OpenAIChatCompletionClient(model="gpt-4")
+                model_client = OpenAIChatCompletionClient(model="gpt-4.1")
                 writer = AssistantAgent(
                     name="writer",
                     description="A writer agent for generating text.",
@@ -60,7 +60,7 @@ async def main() -> None:
                 writer_tool = AgentTool(agent=writer)
 
                 # Create model client with parallel tool calls disabled for the main agent
-                main_model_client = OpenAIChatCompletionClient(model="gpt-4", parallel_tool_calls=False)
+                main_model_client = OpenAIChatCompletionClient(model="gpt-4.1", parallel_tool_calls=False)
                 assistant = AssistantAgent(
                     name="assistant",
                     model_client=main_model_client,

python/packages/autogen-agentchat/src/autogen_agentchat/tools/_team.py

@@ -51,12 +51,12 @@ class TeamTool(TaskRunnerTool, Component[TeamToolConfig]):
             from autogen_agentchat.teams import RoundRobinGroupChat
             from autogen_agentchat.tools import TeamTool
             from autogen_agentchat.ui import Console
-            from autogen_ext.models.ollama import OllamaChatCompletionClient
+            from autogen_ext.models.openai import OpenAIChatCompletionClient
 
 
             async def main() -> None:
                 # Disable parallel tool calls when using TeamTool
-                model_client = OllamaChatCompletionClient(model="llama3.2")
+                model_client = OpenAIChatCompletionClient(model="gpt-4.1")
 
                 writer = AssistantAgent(name="writer", model_client=model_client, system_message="You are a helpful assistant.")
                 reviewer = AssistantAgent(
@@ -80,7 +80,7 @@ async def main() -> None:
                 )
 
                 # Create model client with parallel tool calls disabled for the main agent
-                main_model_client = OllamaChatCompletionClient(model="llama3.2", parallel_tool_calls=False)
+                main_model_client = OpenAIChatCompletionClient(model="gpt-4.1", parallel_tool_calls=False)
                 main_agent = AssistantAgent(
                     name="main_agent",
                     model_client=main_model_client,

python/packages/autogen-ext/src/autogen_ext/models/openai/_openai_client.py

@@ -1236,6 +1236,7 @@ class OpenAIChatCompletionClient(BaseOpenAIChatCompletionClient, Component[OpenA
         stop (optional, str | List[str]):
         temperature (optional, float):
         top_p (optional, float):
+        parallel_tool_calls (optional, bool): Whether to allow parallel tool calls. When not set, defaults to server behavior.
         user (optional, str):
         default_headers (optional, dict[str, str]):  Custom headers; useful for authentication or other custom requirements.
         add_name_prefixes (optional, bool): Whether to prepend the `source` value
@@ -1576,6 +1577,7 @@ class AzureOpenAIChatCompletionClient(
         stop (optional, str | List[str]):
         temperature (optional, float):
         top_p (optional, float):
+        parallel_tool_calls (optional, bool): Whether to allow parallel tool calls. When not set, defaults to server behavior.
         user (optional, str):
         default_headers (optional, dict[str, str]):  Custom headers; useful for authentication or other custom requirements.
         add_name_prefixes (optional, bool): Whether to prepend the `source` value

python/packages/autogen-ext/src/autogen_ext/models/openai/config/__init__.py

@@ -49,6 +49,7 @@ class CreateArguments(TypedDict, total=False):
     top_p: Optional[float]
     user: str
     stream_options: Optional[StreamOptions]
+    parallel_tool_calls: Optional[bool]
 
 
 AsyncAzureADTokenProvider = Callable[[], Union[str, Awaitable[str]]]
@@ -97,6 +98,7 @@ class CreateArgumentsConfigModel(BaseModel):
     top_p: float | None = None
     user: str | None = None
     stream_options: StreamOptions | None = None
+    parallel_tool_calls: bool | None = None
 
 
 class BaseOpenAIClientConfigurationConfigModel(CreateArgumentsConfigModel):