feat: Updated OpenAPI spec (#242)

Co-authored-by: github-actions[bot] <bot@openai.com>

Author: HavenDV

src/libs/Cohere/Generated/Cohere..JsonSerializerContext.g.cs

@@ -123,6 +123,8 @@ namespace Cohere
             typeof(global::Cohere.JsonConverters.StreamedChatResponseDiscriminatorEventTypeNullableJsonConverter),
             typeof(global::Cohere.JsonConverters.StreamedChatResponseV2DiscriminatorTypeJsonConverter),
             typeof(global::Cohere.JsonConverters.StreamedChatResponseV2DiscriminatorTypeNullableJsonConverter),
+            typeof(global::Cohere.JsonConverters.ThinkingTypeJsonConverter),
+            typeof(global::Cohere.JsonConverters.ThinkingTypeNullableJsonConverter),
             typeof(global::Cohere.JsonConverters.ToolV2TypeJsonConverter),
             typeof(global::Cohere.JsonConverters.ToolV2TypeNullableJsonConverter),
             typeof(global::Cohere.JsonConverters.UpdateClusterJobRequestStatusJsonConverter),

src/libs/Cohere/Generated/Cohere.CohereClient.Chat.g.cs

@@ -740,6 +740,11 @@ partial void ProcessChatResponseContent(
         ///  - AUTO: Cohere Platform Only<br/>
         ///  - AUTO_PRESERVE_ORDER: Azure, AWS Sagemaker/Bedrock, Private Deployments
         /// </param>
+        /// <param name="rawPrompting">
+        /// When enabled, the user's prompt will be sent to the model without<br/>
+        /// any pre-processing.<br/>
+        /// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+        /// </param>
         /// <param name="responseFormat">
         /// Configuration for forcing the model output to adhere to the specified format. Supported on [Command R 03-2024](https://docs.cohere.com/docs/command-r), [Command R+ 04-2024](https://docs.cohere.com/docs/command-r-plus) and newer models.<br/>
         /// The model can be forced into outputting JSON objects (with up to 5 levels of nesting) by setting `{ "type": "json_object" }`.<br/>
@@ -834,6 +839,7 @@ partial void ProcessChatResponseContent(
             string? model = default,
             string? preamble = default,
             global::Cohere.ChatRequestPromptTruncation? promptTruncation = default,
+            bool? rawPrompting = default,
             global::Cohere.ResponseFormat? responseFormat = default,
             global::Cohere.ChatRequestSafetyMode? safetyMode = default,
             bool? searchQueriesOnly = default,
@@ -862,6 +868,7 @@ partial void ProcessChatResponseContent(
                 Preamble = preamble,
                 PresencePenalty = presencePenalty,
                 PromptTruncation = promptTruncation,
+                RawPrompting = rawPrompting,
                 ResponseFormat = responseFormat,
                 SafetyMode = safetyMode,
                 SearchQueriesOnly = searchQueriesOnly,

src/libs/Cohere/Generated/Cohere.CohereClient.Chatv2.g.cs

@@ -648,8 +648,9 @@ partial void ProcessChatv2ResponseContent(
         /// Defaults to `false`. When set to `true`, the log probabilities of the generated tokens will be included in the response.
         /// </param>
         /// <param name="maxTokens">
-        /// The maximum number of tokens the model will generate as part of the response.<br/>
-        /// **Note**: Setting a low value may result in incomplete generations.
+        /// The maximum number of output tokens the model will generate in the response. If not set, `max_tokens` defaults to the model's maximum output token limit. You can find the maximum output token limits for each model in the [model documentation](https://docs.cohere.com/docs/models).<br/>
+        /// **Note**: Setting a low value may result in incomplete generations. In such cases, the `finish_reason` field in the response will be set to `"MAX_TOKENS"`.<br/>
+        /// **Note**: If `max_tokens` is set higher than the model's maximum output token limit, the generation will be capped at that model-specific maximum limit.
         /// </param>
         /// <param name="messages">
         /// A list of chat messages in chronological order, representing a conversation between the user and the model.<br/>
@@ -667,6 +668,11 @@ partial void ProcessChatv2ResponseContent(
         /// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.<br/>
         /// Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.
         /// </param>
+        /// <param name="rawPrompting">
+        /// When enabled, the user's prompt will be sent to the model without<br/>
+        /// any pre-processing.<br/>
+        /// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+        /// </param>
         /// <param name="responseFormat">
         /// Configuration for forcing the model output to adhere to the specified format. Supported on [Command R](https://docs.cohere.com/v2/docs/command-r), [Command R+](https://docs.cohere.com/v2/docs/command-r-plus) and newer models.<br/>
         /// The model can be forced into outputting JSON objects by setting `{ "type": "json_object" }`.<br/>
@@ -705,6 +711,11 @@ partial void ProcessChatv2ResponseContent(
         /// A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations, and higher temperatures mean more random generations.<br/>
         /// Randomness can be further maximized by increasing the  value of the `p` parameter.
         /// </param>
+        /// <param name="thinking">
+        /// Thinking gives the model enhanced reasoning capabilities for complex tasks, while also providing transparency into its step-by-step thought process before it delivers its final answer.<br/>
+        /// When thinking is turned on, the model creates thinking content blocks where it outputs its internal reasoning. The model will incorporate insights from this reasoning before crafting a final response.<br/>
+        /// When thinking is used without tools, the API response will include both thinking and text content blocks. Meanwhile, when thinking is used alongside tools and the model makes tool calls, the API response will include the thinking content block and `tool_calls`.
+        /// </param>
         /// <param name="toolChoice">
         /// Used to control whether or not the model will be forced to use a tool when answering. When `REQUIRED` is specified, the model will be forced to use at least one of the user-defined tools, and the `tools` parameter must be passed in the request.<br/>
         /// When `NONE` is specified, the model will be forced **not** to use one of the specified tools, and give a direct response.<br/>
@@ -730,13 +741,15 @@ partial void ProcessChatv2ResponseContent(
             int? maxTokens = default,
             float? p = default,
             float? presencePenalty = default,
+            bool? rawPrompting = default,
             global::Cohere.ResponseFormatV2? responseFormat = default,
             global::Cohere.Chatv2RequestSafetyMode? safetyMode = default,
             int? seed = default,
             global::System.Collections.Generic.IList<string>? stopSequences = default,
             bool? stream = default,
             bool? strictTools = default,
             float? temperature = default,
+            global::Cohere.Thinking? thinking = default,
             global::Cohere.Chatv2RequestToolChoice? toolChoice = default,
             global::System.Collections.Generic.IList<global::Cohere.ToolV2>? tools = default,
             global::System.Threading.CancellationToken cancellationToken = default)
@@ -753,13 +766,15 @@ partial void ProcessChatv2ResponseContent(
                 Model = model,
                 P = p,
                 PresencePenalty = presencePenalty,
+                RawPrompting = rawPrompting,
                 ResponseFormat = responseFormat,
                 SafetyMode = safetyMode,
                 Seed = seed,
                 StopSequences = stopSequences,
                 Stream = stream,
                 StrictTools = strictTools,
                 Temperature = temperature,
+                Thinking = thinking,
                 ToolChoice = toolChoice,
                 Tools = tools,
             };

src/libs/Cohere/Generated/Cohere.ICohereClient.Chat.g.cs

@@ -127,6 +127,11 @@ public partial interface ICohereClient
         ///  - AUTO: Cohere Platform Only<br/>
         ///  - AUTO_PRESERVE_ORDER: Azure, AWS Sagemaker/Bedrock, Private Deployments
         /// </param>
+        /// <param name="rawPrompting">
+        /// When enabled, the user's prompt will be sent to the model without<br/>
+        /// any pre-processing.<br/>
+        /// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+        /// </param>
         /// <param name="responseFormat">
         /// Configuration for forcing the model output to adhere to the specified format. Supported on [Command R 03-2024](https://docs.cohere.com/docs/command-r), [Command R+ 04-2024](https://docs.cohere.com/docs/command-r-plus) and newer models.<br/>
         /// The model can be forced into outputting JSON objects (with up to 5 levels of nesting) by setting `{ "type": "json_object" }`.<br/>
@@ -221,6 +226,7 @@ public partial interface ICohereClient
             string? model = default,
             string? preamble = default,
             global::Cohere.ChatRequestPromptTruncation? promptTruncation = default,
+            bool? rawPrompting = default,
             global::Cohere.ResponseFormat? responseFormat = default,
             global::Cohere.ChatRequestSafetyMode? safetyMode = default,
             bool? searchQueriesOnly = default,

src/libs/Cohere/Generated/Cohere.ICohereClient.Chatv2.g.cs

@@ -43,8 +43,9 @@ public partial interface ICohereClient
         /// Defaults to `false`. When set to `true`, the log probabilities of the generated tokens will be included in the response.
         /// </param>
         /// <param name="maxTokens">
-        /// The maximum number of tokens the model will generate as part of the response.<br/>
-        /// **Note**: Setting a low value may result in incomplete generations.
+        /// The maximum number of output tokens the model will generate in the response. If not set, `max_tokens` defaults to the model's maximum output token limit. You can find the maximum output token limits for each model in the [model documentation](https://docs.cohere.com/docs/models).<br/>
+        /// **Note**: Setting a low value may result in incomplete generations. In such cases, the `finish_reason` field in the response will be set to `"MAX_TOKENS"`.<br/>
+        /// **Note**: If `max_tokens` is set higher than the model's maximum output token limit, the generation will be capped at that model-specific maximum limit.
         /// </param>
         /// <param name="messages">
         /// A list of chat messages in chronological order, representing a conversation between the user and the model.<br/>
@@ -62,6 +63,11 @@ public partial interface ICohereClient
         /// Defaults to `0.0`, min value of `0.0`, max value of `1.0`.<br/>
         /// Used to reduce repetitiveness of generated tokens. Similar to `frequency_penalty`, except that this penalty is applied equally to all tokens that have already appeared, regardless of their exact frequencies.
         /// </param>
+        /// <param name="rawPrompting">
+        /// When enabled, the user's prompt will be sent to the model without<br/>
+        /// any pre-processing.<br/>
+        /// Compatible Deployments: Cohere Platform, Azure, AWS Sagemaker/Bedrock, Private Deployments
+        /// </param>
         /// <param name="responseFormat">
         /// Configuration for forcing the model output to adhere to the specified format. Supported on [Command R](https://docs.cohere.com/v2/docs/command-r), [Command R+](https://docs.cohere.com/v2/docs/command-r-plus) and newer models.<br/>
         /// The model can be forced into outputting JSON objects by setting `{ "type": "json_object" }`.<br/>
@@ -100,6 +106,11 @@ public partial interface ICohereClient
         /// A non-negative float that tunes the degree of randomness in generation. Lower temperatures mean less random generations, and higher temperatures mean more random generations.<br/>
         /// Randomness can be further maximized by increasing the  value of the `p` parameter.
         /// </param>
+        /// <param name="thinking">
+        /// Thinking gives the model enhanced reasoning capabilities for complex tasks, while also providing transparency into its step-by-step thought process before it delivers its final answer.<br/>
+        /// When thinking is turned on, the model creates thinking content blocks where it outputs its internal reasoning. The model will incorporate insights from this reasoning before crafting a final response.<br/>
+        /// When thinking is used without tools, the API response will include both thinking and text content blocks. Meanwhile, when thinking is used alongside tools and the model makes tool calls, the API response will include the thinking content block and `tool_calls`.
+        /// </param>
         /// <param name="toolChoice">
         /// Used to control whether or not the model will be forced to use a tool when answering. When `REQUIRED` is specified, the model will be forced to use at least one of the user-defined tools, and the `tools` parameter must be passed in the request.<br/>
         /// When `NONE` is specified, the model will be forced **not** to use one of the specified tools, and give a direct response.<br/>
@@ -125,13 +136,15 @@ public partial interface ICohereClient
             int? maxTokens = default,
             float? p = default,
             float? presencePenalty = default,
+            bool? rawPrompting = default,
             global::Cohere.ResponseFormatV2? responseFormat = default,
             global::Cohere.Chatv2RequestSafetyMode? safetyMode = default,
             int? seed = default,
             global::System.Collections.Generic.IList<string>? stopSequences = default,
             bool? stream = default,
             bool? strictTools = default,
             float? temperature = default,
+            global::Cohere.Thinking? thinking = default,
             global::Cohere.Chatv2RequestToolChoice? toolChoice = default,
             global::System.Collections.Generic.IList<global::Cohere.ToolV2>? tools = default,
             global::System.Threading.CancellationToken cancellationToken = default);

src/libs/Cohere/Generated/Cohere.JsonConverters.ThinkingType.g.cs

@@ -0,0 +1,53 @@
+#nullable enable
+
+namespace Cohere.JsonConverters
+{
+    /// <inheritdoc />
+    public sealed class ThinkingTypeJsonConverter : global::System.Text.Json.Serialization.JsonConverter<global::Cohere.ThinkingType>
+    {
+        /// <inheritdoc />
+        public override global::Cohere.ThinkingType Read(
+            ref global::System.Text.Json.Utf8JsonReader reader,
+            global::System.Type typeToConvert,
+            global::System.Text.Json.JsonSerializerOptions options)
+        {
+            switch (reader.TokenType)
+            {
+                case global::System.Text.Json.JsonTokenType.String:
+                {
+                    var stringValue = reader.GetString();
+                    if (stringValue != null)
+                    {
+                        return global::Cohere.ThinkingTypeExtensions.ToEnum(stringValue) ?? default;
+                    }
+                    
+                    break;
+                }
+                case global::System.Text.Json.JsonTokenType.Number:
+                {
+                    var numValue = reader.GetInt32();
+                    return (global::Cohere.ThinkingType)numValue;
+                }
+                case global::System.Text.Json.JsonTokenType.Null:
+                {
+                    return default(global::Cohere.ThinkingType);
+                }
+                default:
+                    throw new global::System.ArgumentOutOfRangeException(nameof(reader));
+            }
+
+            return default;
+        }
+
+        /// <inheritdoc />
+        public override void Write(
+            global::System.Text.Json.Utf8JsonWriter writer,
+            global::Cohere.ThinkingType value,
+            global::System.Text.Json.JsonSerializerOptions options)
+        {
+            writer = writer ?? throw new global::System.ArgumentNullException(nameof(writer));
+
+            writer.WriteStringValue(global::Cohere.ThinkingTypeExtensions.ToValueString(value));
+        }
+    }
+}

src/libs/Cohere/Generated/Cohere.JsonConverters.ThinkingTypeNullable.g.cs

@@ -0,0 +1,60 @@
+#nullable enable
+
+namespace Cohere.JsonConverters
+{
+    /// <inheritdoc />
+    public sealed class ThinkingTypeNullableJsonConverter : global::System.Text.Json.Serialization.JsonConverter<global::Cohere.ThinkingType?>
+    {
+        /// <inheritdoc />
+        public override global::Cohere.ThinkingType? Read(
+            ref global::System.Text.Json.Utf8JsonReader reader,
+            global::System.Type typeToConvert,
+            global::System.Text.Json.JsonSerializerOptions options)
+        {
+            switch (reader.TokenType)
+            {
+                case global::System.Text.Json.JsonTokenType.String:
+                {
+                    var stringValue = reader.GetString();
+                    if (stringValue != null)
+                    {
+                        return global::Cohere.ThinkingTypeExtensions.ToEnum(stringValue);
+                    }
+                    
+                    break;
+                }
+                case global::System.Text.Json.JsonTokenType.Number:
+                {
+                    var numValue = reader.GetInt32();
+                    return (global::Cohere.ThinkingType)numValue;
+                }
+                case global::System.Text.Json.JsonTokenType.Null:
+                {
+                    return default(global::Cohere.ThinkingType?);
+                }
+                default:
+                    throw new global::System.ArgumentOutOfRangeException(nameof(reader));
+            }
+
+            return default;
+        }
+
+        /// <inheritdoc />
+        public override void Write(
+            global::System.Text.Json.Utf8JsonWriter writer,
+            global::Cohere.ThinkingType? value,
+            global::System.Text.Json.JsonSerializerOptions options)
+        {
+            writer = writer ?? throw new global::System.ArgumentNullException(nameof(writer));
+
+            if (value == null)
+            {
+                writer.WriteNullValue();
+            }
+            else
+            {
+                writer.WriteStringValue(global::Cohere.ThinkingTypeExtensions.ToValueString(value.Value));
+            }
+        }
+    }
+}