Decided how/if to make data retention on provider side configurable in AI Bridge

OpenAI allows to configure if request will be stored or not on the provider side:
* responses (default true): https://platform.openai.com/docs/api-reference/responses/create#responses_create-store
* chat completions (default false): https://platform.openai.com/docs/api-reference/chat/create#chat_create-store

It is possible to retrieve both chat completions or responses though API
* responses: https://platform.openai.com/docs/api-reference/responses/get
* chat completions: https://platform.openai.com/docs/api-reference/chat/get

Example on configuring data retention from openAI docs: https://platform.openai.com/docs/guides/migrate-to-responses#4-decide-when-to-use-statefulness

AI Bridge could be configurable to set those storage options. Possible options
* reject requests that would result in data being stored in provider API
* override `store` field value for all requests + add ["reasoning.encrypted_content"] to the [include field](https://platform.openai.com/docs/api-reference/responses/create#responses_create-include))

It seems that Anthropic doesn't support configuring data retention in requests (https://privacy.claude.com/en/articles/7996866-how-long-do-you-store-my-organization-s-data https://platform.claude.com/docs/en/api/messages/create).
Zero data retention requires special agreement: https://privacy.claude.com/en/articles/8956058-i-have-a-zero-data-retention-agreement-with-anthropic-what-products-does-it-apply-to
Maybe more research is needed to about storing Anthropic messages.