fix: Update OpenAPI spec

Author: HavenDV

specs/openai.yaml

@@ -40,8 +40,8 @@ public static bool IsArray(
     {
         schema = schema ?? throw new ArgumentNullException(nameof(schema));
 
-        return schema.Type == "array" ||
-               schema.Type == null && schema.Items != null;
+        return schema.Type is "array" or null &&
+               schema.Items is not null;
     }
 
     public static bool IsEnum(

src/libs/AutoSDK/Extensions/OpenApiSchemaExtensions.cs

@@ -233,7 +233,9 @@ public static string GetCSharpType(SchemaContext context)
 
             (_, _) when context.Schema.IsArray() =>
                 $"{context.Children.FirstOrDefault(x => x.Hint == Hint.ArrayItem)?.TypeData.CSharpTypeWithoutNullability}".AsArray(),
-
+            // Fallback if `items` property is missing (openai specification)
+            ("array", _) => "byte[]",
+                
             (_, _) when context.IsNamedAnyOfLike => $"global::{context.Settings.Namespace}.{context.Id}",
             (_, _) when context.IsDerivedClass => $"global::{context.Settings.Namespace}.{context.Id}",
 

src/libs/AutoSDK/Models/TypeData.cs

@@ -0,0 +1,52 @@
+[
+  {
+    Location: /*
+        /// </summary>
+        public static implicit operator ModelIds(global::G.ModelIdsShared value) => new ModelIds(value);
+                                                                                        ^^^^^^^^
+
+*/
+ AutoSDK.SourceGenerators\AutoSDK.SourceGenerators.SdkGenerator\G.Models.ModelIds.g.cs: (31,88)-(31,96),
+    Message: The call is ambiguous between the following methods or properties: 'ModelIds.ModelIds(ModelIdsShared?)' and 'ModelIds.ModelIds(ModelIdsResponses?)',
+    Severity: Error,
+    Descriptor: {
+      Id: CS0121,
+      Title: ,
+      HelpLink: https://msdn.microsoft.com/query/roslyn.query?appId=roslyn&k=k(CS0121),
+      MessageFormat: The call is ambiguous between the following methods or properties: '{0}' and '{1}',
+      Category: Compiler,
+      DefaultSeverity: Error,
+      IsEnabledByDefault: true,
+      CustomTags: [
+        Compiler,
+        Telemetry,
+        NotConfigurable
+      ]
+    }
+  },
+  {
+    Location: /*
+        /// </summary>
+        public static implicit operator ModelIds(global::G.ModelIdsResponses value) => new ModelIds(value);
+                                                                                           ^^^^^^^^
+
+*/
+ AutoSDK.SourceGenerators\AutoSDK.SourceGenerators.SdkGenerator\G.Models.ModelIds.g.cs: (66,91)-(66,99),
+    Message: The call is ambiguous between the following methods or properties: 'ModelIds.ModelIds(ModelIdsShared?)' and 'ModelIds.ModelIds(ModelIdsResponses?)',
+    Severity: Error,
+    Descriptor: {
+      Id: CS0121,
+      Title: ,
+      HelpLink: https://msdn.microsoft.com/query/roslyn.query?appId=roslyn&k=k(CS0121),
+      MessageFormat: The call is ambiguous between the following methods or properties: '{0}' and '{1}',
+      Category: Compiler,
+      DefaultSeverity: Error,
+      IsEnabledByDefault: true,
+      CustomTags: [
+        Compiler,
+        Telemetry,
+        NotConfigurable
+      ]
+    }
+  }
+]

src/tests/AutoSDK.SnapshotTests/Snapshots/openai/NewtonsoftJson/Tests.SdkGenerator_Diagnostics.received.txt

@@ -161,13 +161,16 @@ partial void ProcessCreateSpeechResponseContent(
         /// Generates audio from the input text.
         /// </summary>
         /// <param name="model">
-        /// One of the available [TTS models](/docs/models#tts): `tts-1` or `tts-1-hd`
+        /// One of the available [TTS models](/docs/models#tts): `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
         /// </param>
         /// <param name="input">
         /// The text to generate audio for. The maximum length is 4096 characters.
         /// </param>
+        /// <param name="instructions">
+        /// Control the voice of your generated audio with additional instructions. Does not work with `tts-1` or `tts-1-hd`.
+        /// </param>
         /// <param name="voice">
-        /// The voice to use when generating the audio. Supported voices are `alloy`, `ash`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage` and `shimmer`. Previews of the voices are available in the [Text to speech guide](/docs/guides/text-to-speech#voice-options).
+        /// Example: ash
         /// </param>
         /// <param name="responseFormat">
         /// The format to audio in. Supported formats are `mp3`, `opus`, `aac`, `flac`, `wav`, and `pcm`.<br/>
@@ -182,7 +185,8 @@ partial void ProcessCreateSpeechResponseContent(
         public async global::System.Threading.Tasks.Task<byte[]> CreateSpeechAsync(
             global::G.AnyOf<string, global::G.CreateSpeechRequestModel?> model,
             string input,
-            global::G.CreateSpeechRequestVoice voice,
+            global::G.VoiceIdsShared voice,
+            string? instructions = default,
             global::G.CreateSpeechRequestResponseFormat? responseFormat = default,
             double? speed = default,
             global::System.Threading.CancellationToken cancellationToken = default)
@@ -191,6 +195,7 @@ partial void ProcessCreateSpeechResponseContent(
             {
                 Model = model,
                 Input = input,
+                Instructions = instructions,
                 Voice = voice,
                 ResponseFormat = responseFormat,
                 Speed = speed,

src/tests/AutoSDK.SnapshotTests/Snapshots/openai/NewtonsoftJson/_#G.AudioClient.CreateSpeech.g.verified.cs

@@ -99,11 +99,23 @@ partial void ProcessCreateTranscriptionResponseContent(
                     content: new global::System.Net.Http.StringContent($"{request.Temperature}"),
                     name: "temperature");
             } 
+            if (request.Include != default)
+            {
+                __httpRequestContent.Add(
+                    content: new global::System.Net.Http.StringContent($"[{string.Join(",", global::System.Linq.Enumerable.Select(request.Include, x => x.ToValueString()))}]"),
+                    name: "include[]");
+            } 
             if (request.TimestampGranularities != default)
             {
                 __httpRequestContent.Add(
                     content: new global::System.Net.Http.StringContent($"[{string.Join(",", global::System.Linq.Enumerable.Select(request.TimestampGranularities, x => x.ToValueString()))}]"),
                     name: "timestamp_granularities[]");
+            } 
+            if (request.Stream != default)
+            {
+                __httpRequestContent.Add(
+                    content: new global::System.Net.Http.StringContent($"{request.Stream}"),
+                    name: "stream");
             }
             __httpRequest.Content = __httpRequestContent;
 
@@ -209,8 +221,8 @@ partial void ProcessCreateTranscriptionResponseContent(
         /// The audio file object (not file name) to transcribe, in one of these formats: flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
         /// </param>
         /// <param name="model">
-        /// ID of the model to use. Only `whisper-1` (which is powered by our open source Whisper V2 model) is currently available.<br/>
-        /// Example: whisper-1
+        /// ID of the model to use. The options are `gpt-4o-transcribe`, `gpt-4o-mini-transcribe`, and `whisper-1` (which is powered by our open source Whisper V2 model).<br/>
+        /// Example: gpt-4o-transcribe
         /// </param>
         /// <param name="language">
         /// The language of the input audio. Supplying the input language in [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`) format will improve accuracy and latency.
@@ -219,17 +231,32 @@ partial void ProcessCreateTranscriptionResponseContent(
         /// An optional text to guide the model's style or continue a previous audio segment. The [prompt](/docs/guides/speech-to-text#prompting) should match the audio language.
         /// </param>
         /// <param name="responseFormat">
-        /// The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`.<br/>
+        /// The format of the output, in one of these options: `json`, `text`, `srt`, `verbose_json`, or `vtt`. For `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`, the only supported format is `json`.<br/>
         /// Default Value: json
         /// </param>
         /// <param name="temperature">
         /// The sampling temperature, between 0 and 1. Higher values like 0.8 will make the output more random, while lower values like 0.2 will make it more focused and deterministic. If set to 0, the model will use [log probability](https://en.wikipedia.org/wiki/Log_probability) to automatically increase the temperature until certain thresholds are hit.<br/>
         /// Default Value: 0
         /// </param>
+        /// <param name="include">
+        /// Additional information to include in the transcription response. <br/>
+        /// `logprobs` will return the log probabilities of the tokens in the <br/>
+        /// response to understand the model's confidence in the transcription. <br/>
+        /// `logprobs` only works with response_format set to `json` and only with <br/>
+        /// the models `gpt-4o-transcribe` and `gpt-4o-mini-transcribe`.
+        /// </param>
         /// <param name="timestampGranularities">
         /// The timestamp granularities to populate for this transcription. `response_format` must be set `verbose_json` to use timestamp granularities. Either or both of these options are supported: `word`, or `segment`. Note: There is no additional latency for segment timestamps, but generating word timestamps incurs additional latency.<br/>
         /// Default Value: [segment]
         /// </param>
+        /// <param name="stream">
+        /// If set to true, the model response data will be streamed to the client<br/>
+        /// as it is generated using [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format). <br/>
+        /// See the [Streaming section of the Speech-to-Text guide](/docs/guides/speech-to-text?lang=curl#streaming-transcriptions)<br/>
+        /// for more information.<br/>
+        /// Note: Streaming is not supported for the `whisper-1` model and will be ignored.<br/>
+        /// Default Value: false
+        /// </param>
         /// <param name="cancellationToken">The token to cancel the operation with</param>
         /// <exception cref="global::System.InvalidOperationException"></exception>
         public async global::System.Threading.Tasks.Task<global::G.OneOf<global::G.CreateTranscriptionResponseJson, global::G.CreateTranscriptionResponseVerboseJson>> CreateTranscriptionAsync(
@@ -240,7 +267,9 @@ partial void ProcessCreateTranscriptionResponseContent(
             string? prompt = default,
             global::G.AudioResponseFormat? responseFormat = default,
             double? temperature = default,
+            global::System.Collections.Generic.IList<global::G.TranscriptionInclude>? include = default,
             global::System.Collections.Generic.IList<global::G.CreateTranscriptionRequestTimestampGranularitie>? timestampGranularities = default,
+            bool? stream = default,
             global::System.Threading.CancellationToken cancellationToken = default)
         {
             var __request = new global::G.CreateTranscriptionRequest
@@ -252,7 +281,9 @@ partial void ProcessCreateTranscriptionResponseContent(
                 Prompt = prompt,
                 ResponseFormat = responseFormat,
                 Temperature = temperature,
+                Include = include,
                 TimestampGranularities = timestampGranularities,
+                Stream = stream,
             };
 
             return await CreateTranscriptionAsync(

src/tests/AutoSDK.SnapshotTests/Snapshots/openai/NewtonsoftJson/_#G.AudioClient.CreateTranscription.g.verified.cs

@@ -218,7 +218,7 @@ partial void ProcessCreateTranslationResponseContent(
             string filename,
             global::G.AnyOf<string, global::G.CreateTranslationRequestModel?> model,
             string? prompt = default,
-            global::G.AudioResponseFormat? responseFormat = default,
+            global::G.CreateTranslationRequestResponseFormat? responseFormat = default,
             double? temperature = default,
             global::System.Threading.CancellationToken cancellationToken = default)
         {

src/tests/AutoSDK.SnapshotTests/Snapshots/openai/NewtonsoftJson/_#G.AudioClient.CreateTranslation.g.verified.cs

@@ -175,7 +175,7 @@ partial void ProcessCreateBatchResponseContent(
         /// Your input file must be formatted as a [JSONL file](/docs/api-reference/batch/request-input), and must be uploaded with the purpose `batch`. The file can contain up to 50,000 requests, and can be up to 200 MB in size.
         /// </param>
         /// <param name="endpoint">
-        /// The endpoint to be used for all requests in the batch. Currently `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.
+        /// The endpoint to be used for all requests in the batch. Currently `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported. Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000 embedding inputs across all requests in the batch.
         /// </param>
         /// <param name="completionWindow">
         /// The time frame within which the batch should be processed. Currently only `24h` is supported.