Support for max_completion_tokens in the o1 series

[aeras3637]

It has been resolved in #9749 , but I still get an error after updating to v1.37.0.

Am I missing some setting?

static async Task Main(string[] args)
{
    var kernel = Kernel.CreateBuilder()
        .AddAzureOpenAIChatCompletion(
            "deploy",
            "endpoint",
            "key"
        ).Build();

    KernelArguments arguments = new(new AzureOpenAIPromptExecutionSettings() { MaxTokens = 4096});
    Console.WriteLine(await kernel.InvokePromptAsync("What is the Semantic Kernel? Include citations to the relevant information where it is referenced in the response.", arguments));
}

Microsoft.SemanticKernel.HttpOperationException
HResult=0x80131500
Message=HTTP 400 (invalid_request_error: unsupported_parameter)
Parameter: max_tokens

Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.
Source=Microsoft.SemanticKernel.Connectors.OpenAI
スタック トレース:
場所 Microsoft.SemanticKernel.Connectors.OpenAI.ClientCore.d__731.MoveNext() 場所 Microsoft.SemanticKernel.Connectors.OpenAI.ClientCore.<GetChatMessageContentsAsync>d__16.MoveNext() 場所 Microsoft.SemanticKernel.KernelFunctionFromPrompt.<GetChatCompletionResultAsync>d__25.MoveNext() 場所 Microsoft.SemanticKernel.KernelFunctionFromPrompt.<InvokeCoreAsync>d__6.MoveNext() 場所 System.Threading.Tasks.ValueTask1.get_Result()
場所 Microsoft.SemanticKernel.KernelFunction.<>c__DisplayClass27_0.<b__0>d.MoveNext()
場所 Microsoft.SemanticKernel.Kernel.d__34.MoveNext()
場所 Microsoft.SemanticKernel.Kernel.d__33.MoveNext()
場所 Microsoft.SemanticKernel.KernelFunction.d__27.MoveNext()
場所 AOAI.Program.

d__0.MoveNext() (D:\sandbox\AOAI\Program.cs):行 34

この例外は、最初にこの呼び出し履歴
[外部コード] でスローされました

内部例外 1:
ClientResultException: HTTP 400 (invalid_request_error: unsupported_parameter)
Parameter: max_tokens

Unsupported parameter: 'max_tokens' is not supported with this model. Use 'max_completion_tokens' instead.

[moonbox3]

Tagging @RogerBarreto for visibility.

[RogerBarreto]

@aeras3637 Thanks for bringing the subject, I have identified and was able to replicate, we merged in a fix for that that will be available on the next release.

• .Net: Azure OpenAI Connector - Adding new max completion tokens override parameter #10533

After the fix, to use the next max_completion_tokens with Azure you need to update your code to something like:

var result = await service.GetChatMessageContentAsync("my prompt", new AzureOpenAIPromptExecutionSettings
{
    SetNewMaxCompletionTokensEnabled = true,
    MaxTokens = 1000,
});