Python: Streaming content for token usage

[TaoChenOSU]

Motivation and Context

OpenAI recently starts providing token usage information on their streaming chat completion API. This ADR opens the discussion on how we should consume that information within our StreamingChatMessageContent data structure.

Description

Contribution Checklist

• The code builds clean without any errors or warnings
• The PR follows the SK Contribution Guidelines and the pre-submission formatting script raises no violations
• All unit tests pass, and I have added new tests where possible
• I didn't break anyone 😄

[TaoChenOSU]

Proposal 3 and 4 came from an offline discussion. They do include a refactoring of the existing content classes, which is not necessary for handling streaming usage information from OAI. However, I do like those two proposals as they further clean up our code base. Out of the two, I think proposal 4 is cleaner.