Python: Bug: Inconsistent behavior of function calling from agent class

[NirajC-Microsoft]

Describe the bug
I'm experiencing an issue where calling a new function from an agent class returns the output of a previously invoked function, leading to inconsistent agent responses.

Expected behavior
When a specific function is called from an agent class, the response should accurately reflect the output of that function, not a previously invoked function. Each function call should produce a fresh, contextually relevant response based on the current invocation

Screenshots
Correct Scenario:
Here assign_mentor gets called and giving correct response

Bug:
Here assign_mentor gets called but giving incorrect response, that response is from previous function called from same agent class.

[catalinaperalta]

Thanks for reaching out @NirajC-Microsoft! Can you please share which python sdk library you're using?

[NirajC-Microsoft]

Hi @catalinaperalta ,
Thanks for your response.

Here are the Azure SDK for Python libraries currently used in my project:

azure-ai-evaluation >=1.5.0

azure-ai-inference >=1.0.0b9

azure-ai-projects >=1.0.0b9

azure-cosmos >=4.9.0

azure-identity >=1.21.0

azure-monitor-events-extension >=0.1.0

azure-monitor-opentelemetry >=1.6.8

azure-search-documents >=11.5.2

Additionally, there are some libraries that are indirectly related to Azure:

semantic-kernel[azure] ==1.28.1

opentelemetry-*

openai

[jhakulin]

@NirajC-Microsoft Could you please share sample code that can be used to reproduce the issue?

[NirajC-Microsoft]

@jhakuli, I'm sharing the repository link below for your reference to help reproduce the issue:

Multi-Agent-Custom-Automation-Engine-Solution-Accelerator

[NirajC-Microsoft]

Hi @jhakulin , any update on this issue?

[NirajC-Microsoft]

Hi @jhakulin, any updates or do you require any input from me on this bug?

[jhakulin]

@NirajC-Microsoft apologies for the delay, will be looking into the issue this week.

[NirajC-Microsoft]

Hey @jhakulin , Thanks for your response.