Skip to content

.NET: Setting ReasoningEffort on an agent is cumbersome #1455

@rwjdk-test

Description

@rwjdk-test

When you need to create an agent that use reasoning effort (example: GPT-5) you need to do it in the following way

ChatClientAgent agent = chatClient.CreateAIAgent(
    options: new ChatClientAgentOptions
    {
        Instructions = "You are a nice AI",
        ChatOptions = new ChatOptions
        {
            RawRepresentationFactory = _ => new ChatCompletionOptions
            {
#pragma warning disable OPENAI001
                ReasoningEffortLevel = "minimal",
#pragma warning restore OPENAI001
            },
            Tools = [] //Tools goes here
        }
    });

While this works, it is quite a cumbersome approach for configuring such an important setting (since GPT-5 but default use 'medium' reasoning which in not suited for quick and cheap answers you very often need to lower the default)

I would be so nice if we could do something like this instead:

ChatClientAgent agent = chatClient.CreateAIAgent(
    instructions: "You are a nice AI",
    tools: [], //Tools goes here
    reasoningEffort = "minimal"
    );

I do understand that not every LLM out there understand reasoningEffort, but same could be said for tools

Is there any plans to expose Reasoning Effort in a less cumbersome manner?

Metadata

Metadata

Assignees

Labels

.NETagentsIssues related to single agents

Type

No type

Projects

Status

Done

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests

Issue actions