Skip to content

A programming framework for agentic AI

TEST/change gpt4, gpt4o serise to gpt4.1nano (#6375)

EeSa283d268dfc1
diff --git a/python/packages/autogen-agentchat/tests/test_group_chat.py b/python/packages/autogen-agentchat/tests/test_group_chat.py
index 971dec1ce..37763e866 100644
--- a/python/packages/autogen-agentchat/tests/test_group_chat.py
+++ b/python/packages/autogen-agentchat/tests/test_group_chat.py
@@ -455,7 +455,7 @@ async def test_round_robin_group_chat_with_tools(runtime: AgentRuntime | None) -
"TERMINATE",
],
model_info={
- "family": "gpt-4o",
+ "family": "gpt-4.1-nano",
"function_calling": True,
"json_output": True,
"vision": True,
@@ -1272,7 +1272,7 @@ async def test_swarm_handoff_using_tool_calls(runtime: AgentRuntime | None) -> N
"TERMINATE",
],
model_info={
- "family": "gpt-4o",
+ "family": "gpt-4.1-nano",
"function_calling": True,
"json_output": True,
"vision": True,
@@ -1372,7 +1372,7 @@ async def test_swarm_with_parallel_tool_calls(runtime: AgentRuntime | None) -> N
"TERMINATE",
],
model_info={
- "family": "gpt-4o",
+ "family": "gpt-4.1-nano",
"function_calling": True,
"json_output": True,
"vision": True,
@@ -1562,12 +1562,14 @@ async def test_declarative_groupchats_with_config(runtime: AgentRuntime | None)
# Create basic agents and components for testing
agent1 = AssistantAgent(
"agent_1",
- model_client=OpenAIChatCompletionClient(model="gpt-4o-2024-05-13", api_key=""),
+ model_client=OpenAIChatCompletionClient(model="gpt-4.1-nano-2025-04-14", api_key=""),
handoffs=["agent_2"],
)
- agent2 = AssistantAgent("agent_2", model_client=OpenAIChatCompletionClient(model="gpt-4o-2024-05-13", api_key=""))
+ agent2 = AssistantAgent(
+ "agent_2", model_client=OpenAIChatCompletionClient(model="gpt-4.1-nano-2025-04-14", api_key="")
+ )
termination = MaxMessageTermination(4)
- model_client = OpenAIChatCompletionClient(model="gpt-4o-2024-05-13", api_key="")
+ model_client = OpenAIChatCompletionClient(model="gpt-4.1-nano-2025-04-14", api_key="")
# Test round robin - verify config is preserved
round_robin = RoundRobinGroupChat(participants=[agent1, agent2], termination_condition=termination, max_turns=5)
diff --git a/python/packages/autogen-agentchat/tests/test_group_chat_endpoint.py b/python/packages/autogen-agentchat/tests/test_group_chat_endpoint.py
index d9081b161..142df2729 100644
--- a/python/packages/autogen-agentchat/tests/test_group_chat_endpoint.py
+++ b/python/packages/autogen-agentchat/tests/test_group_chat_endpoint.py
@@ -98,7 +98,7 @@ async def test_selector_group_chat_openai() -> None:
pytest.skip("OPENAI_API_KEY not set in environment variables.")
model_client = OpenAIChatCompletionClient(
- model="gpt-4o-mini",
+ model="gpt-4.1-nano",
api_key=api_key,
)
await _test_selector_group_chat(model_client)
diff --git a/python/packages/autogen-core/tests/test_model_context.py b/python/packages/autogen-core/tests/test_model_context.py
index fbb984090..7a37c30a2 100644
--- a/python/packages/autogen-core/tests/test_model_context.py
+++ b/python/packages/autogen-core/tests/test_model_context.py
@@ -119,7 +119,7 @@ async def test_unbounded_model_context() -> None:
@pytest.mark.parametrize(
"model_client,token_limit",
[
- (OpenAIChatCompletionClient(model="gpt-4o", temperature=0.0, api_key="test"), 30),
+ (OpenAIChatCompletionClient(model="gpt-4.1-nano", temperature=0.0, api_key="test"), 30),
(OllamaChatCompletionClient(model="llama3.3"), 20),
],
ids=["openai", "ollama"],
@@ -159,7 +159,7 @@ async def test_token_limited_model_context_with_token_limit(
@pytest.mark.parametrize(
"model_client",
[
- OpenAIChatCompletionClient(model="gpt-4o", temperature=0.0, api_key="test_key"),
+ OpenAIChatCompletionClient(model="gpt-4.1-nano", temperature=0.0, api_key="test_key"),
OllamaChatCompletionClient(model="llama3.3"),
],
ids=["openai", "ollama"],
@@ -182,7 +182,7 @@ async def test_token_limited_model_context_without_token_limit(model_client: Cha
@pytest.mark.parametrize(
"model_client,token_limit",
[
- (OpenAIChatCompletionClient(model="gpt-4o", temperature=0.0, api_key="test"), 60),
+ (OpenAIChatCompletionClient(model="gpt-4.1-nano", temperature=0.0, api_key="test"), 60),
(OllamaChatCompletionClient(model="llama3.3"), 50),
],
ids=["openai", "ollama"],
diff --git a/python/packages/autogen-ext/tests/models/test_openai_model_client.py b/python/packages/autogen-ext/tests/models/test_openai_model_client.py
index 263f57887..3e4d6dccf 100644
--- a/python/packages/autogen-ext/tests/models/test_openai_model_client.py
+++ b/python/packages/autogen-ext/tests/models/test_openai_model_client.py
@@ -95,7 +95,7 @@ class MockChunkEvent(BaseModel):
async def _mock_create_stream(*args: Any, **kwargs: Any) -> AsyncGenerator[ChatCompletionChunk, None]:
- model = resolve_model(kwargs.get("model", "gpt-4o"))
+ model = resolve_model(kwargs.get("model", "gpt-4.1-nano"))
mock_chunks_content = ["Hello", " Another Hello", " Yet Another Hello"]
# The openai api implementations (OpenAI and Litellm) stream chunks of tokens
@@ -167,7 +167,7 @@ async def _mock_create_stream(*args: Any, **kwargs: Any) -> AsyncGenerator[ChatC
async def _mock_create(*args: Any, **kwargs: Any) -> ChatCompletion | AsyncGenerator[ChatCompletionChunk, None]:
stream = kwargs.get("stream", False)
- model = resolve_model(kwargs.get("model", "gpt-4o"))
+ model = resolve_model(kwargs.get("model", "gpt-4.1-nano"))
if not stream:
await asyncio.sleep(0.1)
return ChatCompletion(
@@ -186,7 +186,7 @@ async def _mock_create(*args: Any, **kwargs: Any) -> ChatCompletion | AsyncGener
@pytest.mark.asyncio
async def test_openai_chat_completion_client() -> None:
- client = OpenAIChatCompletionClient(model="gpt-4o", api_key="api_key")
+ client = OpenAIChatCompletionClient(model="gpt-4.1-nano", api_key="api_key")
assert client
@@ -198,7 +198,7 @@ async def test_openai_chat_completion_client_with_gemini_model() -> None:
@pytest.mark.asyncio
async def test_openai_chat_completion_client_serialization() -> None:
- client = OpenAIChatCompletionClient(model="gpt-4o", api_key="sk-password")
+ client = OpenAIChatCompletionClient(model="gpt-4.1-nano", api_key="sk-password")
assert client
config = client.dump_component()
assert config
@@ -467,7 +467,7 @@ def test_convert_tools_accepts_both_tool_and_schema() -> None:
@pytest.mark.asyncio
async def test_json_mode(monkeypatch: pytest.MonkeyPatch) -> None:
- model = "gpt-4o-2024-11-20"
+ model = "gpt-4.1-nano-2025-04-14"
called_args = {}
@@ -562,7 +562,7 @@ async def test_structured_output_using_response_format(monkeypatch: pytest.Monke
thoughts: str
response: Literal["happy", "sad", "neutral"]
- model = "gpt-4o-2024-11-20"
+ model = "gpt-4.1-nano-2025-04-14"
called_args = {}
@@ -654,7 +654,7 @@ async def test_structured_output(monkeypatch: pytest.MonkeyPatch) -> None:
thoughts: str
response: Literal["happy", "sad", "neutral"]
- model = "gpt-4o-2024-11-20"
+ model = "gpt-4.1-nano-2025-04-14"
async def _mock_parse(*args: Any, **kwargs: Any) -> ParsedChatCompletion[AgentResponse]:
return ParsedChatCompletion(
@@ -737,7 +737,7 @@ async def test_structured_output_with_tool_calls(monkeypatch: pytest.MonkeyPatch
thoughts: str
response: Literal["happy", "sad", "neutral"]
- model = "gpt-4o-2024-11-20"
+ model = "gpt-4.1-nano-2025-04-14"
async def _mock_parse(*args: Any, **kwargs: Any) -> ParsedChatCompletion[AgentResponse]:
return ParsedChatCompletion(
@@ -813,7 +813,7 @@ async def test_structured_output_with_streaming(monkeypatch: pytest.MonkeyPatch)
chunked_content = [raw_content[i : i + 5] for i in range(0, len(raw_content), 5)]
assert "".join(chunked_content) == raw_content
- model = "gpt-4o-2024-11-20"
+ model = "gpt-4.1-nano-2025-04-14"
mock_chunk_events = [
MockChunkEvent(
type="chunk",
@@ -886,7 +886,7 @@ async def test_structured_output_with_streaming_tool_calls(monkeypatch: pytest.M
chunked_content = [raw_content[i : i + 5] for i in range(0, len(raw_content), 5)]
assert "".join(chunked_content) == raw_content
- model = "gpt-4o-2024-11-20"
+ model = "gpt-4.1-nano-2025-04-14"
# generate the list of mock chunk content
mock_chunk_events = [
@@ -1265,7 +1265,7 @@ async def test_r1_think_field_not_present(monkeypatch: pytest.MonkeyPatch) -> No
@pytest.mark.asyncio
async def test_tool_calling(monkeypatch: pytest.MonkeyPatch) -> None:
- model = "gpt-4o-2024-05-13"
+ model = "gpt-4.1-nano-2025-04-14"
chat_completions = [
# Successful completion, single tool call
ChatCompletion(
@@ -1622,7 +1622,7 @@ def openai_client(request: pytest.FixtureRequest) -> OpenAIChatCompletionClient:
@pytest.mark.asyncio
@pytest.mark.parametrize(
"model",
- ["gpt-4o-mini", "gemini-1.5-flash", "claude-3-5-haiku-20241022"],
+ ["gpt-4.1-nano", "gemini-1.5-flash", "claude-3-5-haiku-20241022"],
)
async def test_model_client_basic_completion(model: str, openai_client: OpenAIChatCompletionClient) -> None:
# Test basic completion
@@ -1639,7 +1639,7 @@ async def test_model_client_basic_completion(model: str, openai_client: OpenAICh
@pytest.mark.asyncio
@pytest.mark.parametrize(
"model",
- ["gpt-4o-mini", "gemini-1.5-flash", "claude-3-5-haiku-20241022"],
+ ["gpt-4.1-nano", "gemini-1.5-flash", "claude-3-5-haiku-20241022"],
)
async def test_model_client_with_function_calling(model: str, openai_client: OpenAIChatCompletionClient) -> None:
# Test tool calling
@@ -1716,7 +1716,7 @@ async def test_model_client_with_function_calling(model: str, openai_client: Ope
@pytest.mark.asyncio
@pytest.mark.parametrize(
"model",
- ["gpt-4o-mini", "gemini-1.5-flash"],
+ ["gpt-4.1-nano", "gemini-1.5-flash"],
)
async def test_openai_structured_output_using_response_format(
model: str, openai_client: OpenAIChatCompletionClient
@@ -1749,7 +1749,7 @@ async def test_openai_structured_output_using_response_format(
@pytest.mark.asyncio
@pytest.mark.parametrize(
"model",
- ["gpt-4o-mini", "gemini-1.5-flash"],
+ ["gpt-4.1-nano", "gemini-1.5-flash"],
)
async def test_openai_structured_output(model: str, openai_client: OpenAIChatCompletionClient) -> None:
class AgentResponse(BaseModel):
@@ -1769,7 +1769,7 @@ async def test_openai_structured_output(model: str, openai_client: OpenAIChatCom
@pytest.mark.asyncio
@pytest.mark.parametrize(
"model",
- ["gpt-4o-mini", "gemini-1.5-flash"],
+ ["gpt-4.1-nano", "gemini-1.5-flash"],
)
async def test_openai_structured_output_with_streaming(model: str, openai_client: OpenAIChatCompletionClient) -> None:
class AgentResponse(BaseModel):
@@ -1795,7 +1795,7 @@ async def test_openai_structured_output_with_streaming(model: str, openai_client
@pytest.mark.parametrize(
"model",
[
- "gpt-4o-mini",
+ "gpt-4.1-nano",
# "gemini-1.5-flash", # Gemini models do not support structured output with tool calls from model client.
],
)
@@ -1853,7 +1853,7 @@ async def test_openai_structured_output_with_tool_calls(model: str, openai_clien
@pytest.mark.parametrize(
"model",
[
- "gpt-4o-mini",
+ "gpt-4.1-nano",
# "gemini-1.5-flash", # Gemini models do not support structured output with tool calls from model client.
],
)
@@ -2072,7 +2072,7 @@ async def test_add_name_prefixes(monkeypatch: pytest.MonkeyPatch) -> None:
@pytest.mark.parametrize(
"model",
[
- "gpt-4o-mini",
+ "gpt-4.1-nano",
"gemini-1.5-flash",
"claude-3-5-haiku-20241022",
],
@@ -2188,7 +2188,7 @@ async def test_system_message_not_merged_for_multiple_system_messages_true() ->
mock_client = MagicMock()
client = BaseOpenAIChatCompletionClient(
client=mock_client,
- create_args={"model": "gpt-4o"},
+ create_args={"model": "gpt-4.1-nano"},
model_info={
"vision": False,
"function_calling": False,
@@ -2355,7 +2355,7 @@ async def test_empty_assistant_content_with_gemini(model: str, openai_client: Op
@pytest.mark.parametrize(
"model",
[
- "gpt-4o-mini",
+ "gpt-4.1-nano",
"gemini-1.5-flash",
"claude-3-5-haiku-20241022",
],
@@ -2402,7 +2402,7 @@ def test_openai_model_registry_find_well() -> None:
@pytest.mark.parametrize(
"model",
[
- "gpt-4o-mini",
+ "gpt-4.1-nano",
],
)
async def test_openai_model_unknown_message_type(model: str, openai_client: OpenAIChatCompletionClient) -> None:
diff --git a/python/packages/autogen-ext/tests/test_filesurfer_agent.py b/python/packages/autogen-ext/tests/test_filesurfer_agent.py
index 04fc46365..ef7d58e71 100644
--- a/python/packages/autogen-ext/tests/test_filesurfer_agent.py
+++ b/python/packages/autogen-ext/tests/test_filesurfer_agent.py
@@ -74,7 +74,7 @@ async def test_run_filesurfer(monkeypatch: pytest.MonkeyPatch) -> None:
</html>""")
# Mock the API calls
- model = "gpt-4o-2024-05-13"
+ model = "gpt-4.1-nano-2025-04-14"
chat_completions = [
ChatCompletion(
id="id1",
@@ -153,7 +153,7 @@ async def test_run_filesurfer(monkeypatch: pytest.MonkeyPatch) -> None:
@pytest.mark.asyncio
async def test_file_surfer_serialization() -> None:
"""Test that FileSurfer can be serialized and deserialized properly."""
- model = "gpt-4o-2024-05-13"
+ model = "gpt-4.1-nano-2025-04-14"
agent = FileSurfer(
"FileSurfer",
model_client=OpenAIChatCompletionClient(model=model, api_key=""),
diff --git a/python/packages/autogen-ext/tests/test_openai_assistant_agent.py b/python/packages/autogen-ext/tests/test_openai_assistant_agent.py
index d170e6b7f..b76279c92 100644
--- a/python/packages/autogen-ext/tests/test_openai_assistant_agent.py
+++ b/python/packages/autogen-ext/tests/test_openai_assistant_agent.py
@@ -202,7 +202,7 @@ def agent(client: AsyncOpenAI) -> OpenAIAssistantAgent:
return OpenAIAssistantAgent(
name="assistant",
instructions="Help the user with their task.",
- model="gpt-4o-mini",
+ model="gpt-4.1-nano",
description="OpenAI Assistant Agent",
client=client,
tools=tools,
@@ -346,7 +346,7 @@ async def test_on_reset_behavior(client: AsyncOpenAI, cancellation_token: Cancel
agent = OpenAIAssistantAgent(
name="assistant",
instructions="Help the user with their task.",
- model="gpt-4o-mini",
+ model="gpt-4.1-nano",
description="OpenAI Assistant Agent",
client=client,
thread_id=thread.id,
diff --git a/python/packages/autogen-ext/tests/test_websurfer_agent.py b/python/packages/autogen-ext/tests/test_websurfer_agent.py
index 37423bfe6..e9fb222d7 100644
--- a/python/packages/autogen-ext/tests/test_websurfer_agent.py
+++ b/python/packages/autogen-ext/tests/test_websurfer_agent.py
@@ -61,7 +61,7 @@ logger.addHandler(FileLogHandler("test_websurfer_agent.log"))
@pytest.mark.asyncio
async def test_run_websurfer(monkeypatch: pytest.MonkeyPatch) -> None:
- model = "gpt-4o-2024-05-13"
+ model = "gpt-4.1-nano-2025-04-14"
chat_completions = [
ChatCompletion(
id="id2",
@@ -149,7 +149,7 @@ async def test_run_websurfer(monkeypatch: pytest.MonkeyPatch) -> None:
@pytest.mark.asyncio
async def test_run_websurfer_declarative(monkeypatch: pytest.MonkeyPatch) -> None:
- model = "gpt-4o-2024-05-13"
+ model = "gpt-4.1-nano-2025-04-14"
chat_completions = [
ChatCompletion(
id="id1",
diff --git a/python/packages/autogen-studio/tests/test_db_manager.py b/python/packages/autogen-studio/tests/test_db_manager.py
index 30227a064..c2912a7d5 100644
--- a/python/packages/autogen-studio/tests/test_db_manager.py
+++ b/python/packages/autogen-studio/tests/test_db_manager.py
@@ -37,7 +37,7 @@ def sample_team(test_user: str) -> Team:
agent = AssistantAgent(
name="weather_agent",
model_client=OpenAIChatCompletionClient(
- model="gpt-4",
+ model="gpt-4.1-nano",
),
)
@@ -187,4 +187,4 @@ class TestDatabaseOperations:
finally:
asyncio.run(db.close())
- db.reset_db()
\ No newline at end of file
+ db.reset_db()
diff --git a/python/packages/autogen-studio/tests/test_team_manager.py b/python/packages/autogen-studio/tests/test_team_manager.py
index 0f25317d1..cf58ac78c 100644
--- a/python/packages/autogen-studio/tests/test_team_manager.py
+++ b/python/packages/autogen-studio/tests/test_team_manager.py
@@ -21,7 +21,7 @@ def sample_config():
agent = AssistantAgent(
name="weather_agent",
model_client=OpenAIChatCompletionClient(
- model="gpt-4o-mini",
+ model="gpt-4.1-nano",
),
)
@@ -146,4 +146,4 @@ class TestTeamManager:
# Verify the last message is a TeamResult
assert isinstance(streamed_messages[-1], type(mock_messages[-1]))
-
\ No newline at end of file
+