updated based on changelog

Author: jamesrochabrun

Sources/OpenAI/Public/Parameters/Chat/ChatCompletionParameters.swift

@@ -29,6 +29,8 @@ public struct ChatCompletionParameters: Encodable {
    public var functions: [ChatFunction]?
    /// A list of tools the model may call. Currently, only functions are supported as a tool. Use this to provide a list of functions the model may generate JSON inputs for.
    public var tools: [Tool]?
+   /// Whether to enable parallel function calling during tool use. Defaults to true.
+   public var parallelToolCalls: Bool?
    /// Modify the likelihood of specified tokens appearing in the completion.
    /// Accepts a json object that maps tokens (specified by their token ID in the tokenizer) to an associated bias value from -100 to 100. Mathematically, the bias is added to the logits generated by the model prior to sampling. The exact effect will vary per model, but values between -1 and 1 should decrease or increase likelihood of selection; values like -100 or 100 should result in a ban or exclusive selection of the relevant token. Defaults to null.
    public var logitBias: [Int: Double]?
@@ -48,6 +50,11 @@ public struct ChatCompletionParameters: Encodable {
    /// Setting to `{ type: "json_object" }` enables `JSON` mode, which guarantees the message the model generates is valid JSON.
    ///Important: when using `JSON` mode you must still instruct the model to produce `JSON` yourself via some conversation message, for example via your system message. If you don't do this, the model may generate an unending stream of whitespace until the generation reaches the token limit, which may take a lot of time and give the appearance of a "stuck" request. Also note that the message content may be partial (i.e. cut off) if `finish_reason="length"`, which indicates the generation exceeded `max_tokens` or the conversation exceeded the max context length.
    public var responseFormat: ResponseFormat?
+   /// Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:
+   /// If set to 'auto', the system will utilize scale tier credits until they are exhausted.
+   /// If set to 'default', the request will be processed in the shared cluster.
+   /// When this parameter is set, the response body will include the service_tier utilized.
+   public var serviceTier: String?
    /// This feature is in `Beta`. If specified, our system will make a best effort to sample deterministically, such that repeated requests with the same `seed` and parameters should return the same result.
    /// Determinism is not guaranteed, and you should refer to the `system_fingerprint` response parameter to monitor changes in the backend.
    public var seed: Int?
@@ -418,6 +425,15 @@ public struct ChatCompletionParameters: Encodable {
       }
    }
 
+   public enum ServiceTier: String, Encodable {
+      /// Specifies the latency tier to use for processing the request. This parameter is relevant for customers subscribed to the scale tier service:
+      /// If set to 'auto', the system will utilize scale tier credits until they are exhausted.
+      /// If set to 'default', the request will be processed in the shared cluster.
+      /// When this parameter is set, the response body will include the service_tier utilized.
+      case auto
+      case `default`
+   }
+   
    public struct StreamOptions: Encodable {
       /// If set, an additional chunk will be streamed before the data: [DONE] message.
       /// The usage field on this chunk shows the token usage statistics for the entire request,
@@ -437,6 +453,7 @@ public struct ChatCompletionParameters: Encodable {
       case toolChoice = "tool_choice"
       case functionCall = "function_call"
       case tools
+      case parallelToolCalls = "parallel_tool_calls"
       case functions
       case logitBias = "logit_bias"
       case logprobs
@@ -446,6 +463,7 @@ public struct ChatCompletionParameters: Encodable {
       case responseFormat = "response_format"
       case presencePenalty = "presence_penalty"
       case seed
+      case serviceTier = "service_tier"
       case stop
       case stream
       case streamOptions = "stream_options"
@@ -462,13 +480,15 @@ public struct ChatCompletionParameters: Encodable {
       toolChoice: ToolChoice? = nil,
       functions: [ChatFunction]? = nil,
       tools: [Tool]? = nil,
+      parallelToolCalls: Bool? = nil,
       logitBias: [Int: Double]? = nil,
       logProbs: Bool? = nil,
       topLogprobs: Int? = nil,
       maxTokens: Int? = nil,
       n: Int? = nil,
       responseFormat: ResponseFormat? = nil,
       presencePenalty: Double? = nil,
+      serviceTier: ServiceTier? = nil,
       seed: Int? = nil,
       stop: [String]? = nil,
       temperature: Double? = nil,
@@ -482,13 +502,15 @@ public struct ChatCompletionParameters: Encodable {
       self.toolChoice = toolChoice
       self.functions = functions
       self.tools = tools
+      self.parallelToolCalls = parallelToolCalls
       self.logitBias = logitBias
       self.logprobs = logProbs
       self.topLogprobs = topLogprobs
       self.maxTokens = maxTokens
       self.n = n
       self.responseFormat = responseFormat
       self.presencePenalty = presencePenalty
+      self.serviceTier = serviceTier?.rawValue
       self.seed = seed
       self.stop = stop
       self.temperature = temperature