Prepare 2.1.0-beta.2 release (Part 1)

[joseharriaga]

Features added

• Added a StoredOutputEnabled property to ChatCompletionOptions (store in the REST API).
  • Use this property to indicate whether or not to store the output of the chat completion for use in model distillation or evals.
• Added a Metadata property to ChatCompletionOptions (metadata in the REST API).
  • Use this property to add custom tags and values to the chat completions for filtering in the OpenAI dashboard.
• Added an InputTokenDetails property to ChatTokenUsage (usage.prompt_token_details in the REST API).
  • The property is of a new type called ChatInputTokenUsageDetails, which contains properties for AudioTokenCount and CachedTokenCount for usage with supported models.
• Added an AudioTokenCount property to ChatOutputTokenUsageDetails (usage.completion_token_details in the REST API). Audio support in chat completions is coming soon.
• Added Illicit and IllictViolent properties ModerationResult to represent these two new moderation categories.
• Made improvements to the experimental Realtime API. Please note this features area is currently under rapid development and not all changes may be reflected here.
  • Several types have been renamed for consistency and clarity.
  • ConversationRateLimitsUpdate (previously ConversationRateLimitsUpdatedUpdate) now includes named RequestDetails and TokenDetails properties, mapping to the corresponding named items in the underlying rate_limits command payload.

Other Changes

• Updated the System.ClientModel dependency to version 1.2.1.
  • This updates the System.Text.Json transitive dependency to version 6.0.10, which includes a security compliance fix for CVE-2024-43485. Please note that the OpenAI library was not impacted by this vulnerability since it does not use the [JsonExtensionData] feature.