We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Gemini isn't working when there is agent with tool parameter like this:
additional_notes: Annotated[Optional[str], "Additional notes"] = None
Here is a test case which is failing:
@pytest.mark.gemini def test_gemini_with_tools_parameters_set_to_is_annotated_with_none_as_default_value( credentials_gemini_pro: Credentials, ) -> None: agent = ConversableAgent(name="agent", llm_config=credentials_gemini_pro.llm_config) user_proxy = UserProxyAgent( name="user_proxy_1", human_input_mode="NEVER", ) mock = MagicMock() @user_proxy.register_for_execution() @agent.register_for_llm(description="Login function") def login( additional_notes: Annotated[Optional[str], "Additional notes"] = None, ) -> str: return "Login successful." user_proxy.initiate_chat(agent, message="Please login", max_turns=2) mock.assert_called_once()
This test is already in the test/agentchat/test_conversable_agent.py but currently it is marked with @pytest.skip because it is failing
test/agentchat/test_conversable_agent.py
@pytest.skip
No response
The text was updated successfully, but these errors were encountered:
rjambrecic
No branches or pull requests
Describe the bug
Gemini isn't working when there is agent with tool parameter like this:
Here is a test case which is failing:
This test is already in the
test/agentchat/test_conversable_agent.py
but currently it is marked with@pytest.skip
because it is failingSteps to reproduce
No response
Model Used
No response
Expected Behavior
No response
Screenshots and logs
No response
Additional Information
No response
The text was updated successfully, but these errors were encountered: