[FEATURE REQ] add ability to set prompt_cache_retention for requests

[danfaber]

Describe the feature or improvement you are requesting

the api docs mention that you can now set the prompt cache retention to 24 hours, instead of the standard 5-10 minutes
https://platform.openai.com/docs/guides/prompt-caching

{
"model": "gpt-5.1",
"input": "Your prompt goes here...",
"prompt_cache_retention": "24h"
}

it would be brilliant to be able to set it in the .net SDK too - both on the chat and responses clients.

could it be added to the following objects:
ResponseCreationOptions and ChatCompletionOptions

Many thanks.

Additional context

No response

[jsquire]

@danfaber: Thank you for the additional context. The prompt_cache_retention option is a more recent addition that is not yet represented in the REST API spec used for client generation. Once the spec is updated to include this area and a new version published, we'll include it in the client.

In the meantime, you can set it using the JSON Patch feature added in v2.6.0. For responses, this would look something like:

var client = new OpenAIResponseClient("gpt-5", "<< YOUR API KEY >>");

var responseOptions = new ResponseCreationOptions
{
    Instructions = "You are Terry Crews and have had 12 cans of Redbull this morning.  You are PUMPED to help any way possible."
};

// Set the prompt cache duration, following the platform docs for information on 
// the right path:  https://platform.openai.com/docs/api-reference/responses/create#responses_create-prompt_cache_retention 
options.Patch.Set("$.prompt_cache_retention"u8, "24h");

OpenAIResponse response = await client.CreateResponseAsync(
    [ResponseItem.CreateUserMessageItem("Tell me a story about cake.")],
    responseOptions);