Added the Responses API

app/MindWork AI Studio/Provider/AlibabaCloud/ProviderAlibabaCloud.cs

@@ -77,7 +77,7 @@ public sealed class ProviderAlibabaCloud(ILogger logger) : BaseProvider("https:/
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("AlibabaCloud", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("AlibabaCloud", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Anthropic/ProviderAnthropic.cs

@@ -72,7 +72,7 @@ public sealed class ProviderAnthropic(ILogger logger) : BaseProvider("https://ap
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine>("Anthropic", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine, NoChatCompletionAnnotationStreamLine>("Anthropic", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Anthropic/ResponseStreamLine.cs

@@ -14,6 +14,21 @@ public readonly record struct ResponseStreamLine(string Type, int Index, Delta D
 
     /// <inheritdoc />
     public ContentStreamChunk GetContent() => new(this.Delta.Text, []);
+
+    #region Implementation of IAnnotationStreamLine
+
+    //
+    // Please note: Anthropic's API does not currently support sources in their
+    // OpenAI-compatible response stream.
+    //
+
+    /// <inheritdoc />
+    public bool ContainsSources() => false;
+
+    /// <inheritdoc />
+    public IList<ISource> GetSources() => [];
+
+    #endregion
 }
 
 /// <summary>

app/MindWork AI Studio/Provider/BaseProvider.cs

@@ -3,6 +3,7 @@ using System.Runtime.CompilerServices;
 using System.Text.Json;
 
 using AIStudio.Chat;
+using AIStudio.Provider.OpenAI;
 using AIStudio.Settings;
 using AIStudio.Tools.PluginSystem;
 using AIStudio.Tools.Services;
@@ -39,6 +40,7 @@ public abstract class BaseProvider : IProvider, ISecretId
     protected static readonly JsonSerializerOptions JSON_SERIALIZER_OPTIONS = new()
     {
         PropertyNamingPolicy = JsonNamingPolicy.SnakeCaseLower,
+        Converters = { new AnnotationConverter() }
     };
 
     /// <summary>
@@ -196,8 +198,20 @@ public abstract class BaseProvider : IProvider, ISecretId
         return new HttpRateLimitedStreamResult(true, false, string.Empty, response);
     }
 
-    protected async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletionInternal<T>(string providerName, Func<Task<HttpRequestMessage>> requestBuilder, [EnumeratorCancellation] CancellationToken token = default) where T : struct, IResponseStreamLine
+    /// <summary>
+    /// Streams the chat completion from the provider using the Chat Completion API.
+    /// </summary>
+    /// <param name="providerName">The name of the provider.</param>
+    /// <param name="requestBuilder">A function that builds the request.</param>
+    /// <param name="token">The cancellation token to use.</param>
+    /// <typeparam name="TDelta">The type of the delta lines inside the stream.</typeparam>
+    /// <typeparam name="TAnnotation">The type of the annotation lines inside the stream.</typeparam>
+    /// <returns>The stream of content chunks.</returns>
+    protected async IAsyncEnumerable<ContentStreamChunk> StreamChatCompletionInternal<TDelta, TAnnotation>(string providerName, Func<Task<HttpRequestMessage>> requestBuilder, [EnumeratorCancellation] CancellationToken token = default) where TDelta : IResponseStreamLine where TAnnotation : IAnnotationStreamLine
     {
+        // Check if annotations are supported:
+        var annotationSupported = typeof(TAnnotation) != typeof(NoResponsesAnnotationStreamLine) && typeof(TAnnotation) != typeof(NoChatCompletionAnnotationStreamLine);
+        
         StreamReader? streamReader = null;
         try
         {
@@ -224,7 +238,9 @@ public abstract class BaseProvider : IProvider, ISecretId
         if (streamReader is null)
             yield break;
         
+        //
         // Read the stream, line by line:
+        //
         while (true)
         {
             try
@@ -247,7 +263,9 @@ public abstract class BaseProvider : IProvider, ISecretId
                 yield break;
             }
 
+            //
             // Read the next line:
+            //
             string? line;
             try
             {
@@ -273,28 +291,233 @@ public abstract class BaseProvider : IProvider, ISecretId
             if (line.StartsWith("data: [DONE]", StringComparison.InvariantCulture))
                 yield break;
 
-            T providerResponse;
+            //
+            // Process annotation lines:
+            //
+            if (annotationSupported && line.Contains("""
+                                                     "annotations":[
+                                                     """, StringComparison.InvariantCulture))
+            {
+                TAnnotation? providerResponse;
+                
+                try
+                {
+                    // We know that the line starts with "data: ". Hence, we can
+                    // skip the first 6 characters to get the JSON data after that.
+                    var jsonData = line[6..];
+
+                    // Deserialize the JSON data:
+                    providerResponse = JsonSerializer.Deserialize<TAnnotation>(jsonData, JSON_SERIALIZER_OPTIONS);
+
+                    if (providerResponse is null)
+                        continue;
+                }
+                catch
+                {
+                    // Skip invalid JSON data:
+                    continue;
+                }
+
+                // Skip empty responses:
+                if (!providerResponse.ContainsSources())
+                    continue;
+
+                // Yield the response:
+                yield return new(string.Empty, providerResponse.GetSources());
+            }
+            
+            //
+            // Process delta lines:
+            //
+            else
+            {
+                TDelta? providerResponse;
+                try
+                {
+                    // We know that the line starts with "data: ". Hence, we can
+                    // skip the first 6 characters to get the JSON data after that.
+                    var jsonData = line[6..];
+
+                    // Deserialize the JSON data:
+                    providerResponse = JsonSerializer.Deserialize<TDelta>(jsonData, JSON_SERIALIZER_OPTIONS);
+
+                    if (providerResponse is null)
+                        continue;
+                }
+                catch
+                {
+                    // Skip invalid JSON data:
+                    continue;
+                }
+
+                // Skip empty responses:
+                if (!providerResponse.ContainsContent())
+                    continue;
+
+                // Yield the response:
+                yield return providerResponse.GetContent();
+            }
+        }
+        
+        streamReader.Dispose();
+    }
+
+    /// <summary>
+    /// Streams the chat completion from the provider using the Responses API.
+    /// </summary>
+    /// <param name="providerName">The name of the provider.</param>
+    /// <param name="requestBuilder">A function that builds the request.</param>
+    /// <param name="token">The cancellation token to use.</param>
+    /// <typeparam name="TDelta">The type of the delta lines inside the stream.</typeparam>
+    /// <typeparam name="TAnnotation">The type of the annotation lines inside the stream.</typeparam>
+    /// <returns>The stream of content chunks.</returns>
+    protected async IAsyncEnumerable<ContentStreamChunk> StreamResponsesInternal<TDelta, TAnnotation>(string providerName, Func<Task<HttpRequestMessage>> requestBuilder, [EnumeratorCancellation] CancellationToken token = default) where TDelta : IResponseStreamLine where TAnnotation : IAnnotationStreamLine
+    {
+        // Check if annotations are supported:
+        var annotationSupported = typeof(TAnnotation) != typeof(NoResponsesAnnotationStreamLine) && typeof(TAnnotation) != typeof(NoChatCompletionAnnotationStreamLine);
+        
+        StreamReader? streamReader = null;
+        try
+        {
+            // Send the request using exponential backoff:
+            var responseData = await this.SendRequest(requestBuilder, token);
+            if(responseData.IsFailedAfterAllRetries)
+            {
+                this.logger.LogError($"The {providerName} responses call failed: {responseData.ErrorMessage}");
+                yield break;
+            }
+            
+            // Open the response stream:
+            var providerStream = await responseData.Response!.Content.ReadAsStreamAsync(token);
+
+            // Add a stream reader to read the stream, line by line:
+            streamReader = new StreamReader(providerStream);
+        }
+        catch(Exception e)
+        {
+            await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Stream, string.Format(TB("Tried to communicate with the LLM provider '{0}'. There were some problems with the request. The provider message is: '{1}'"), this.InstanceName, e.Message)));
+            this.logger.LogError($"Failed to stream responses from {providerName} '{this.InstanceName}': {e.Message}");
+        }
+
+        if (streamReader is null)
+            yield break;
+        
+        //
+        // Read the stream, line by line:
+        //
+        while (true)
+        {
             try
             {
-                // We know that the line starts with "data: ". Hence, we can
-                // skip the first 6 characters to get the JSON data after that.
-                var jsonData = line[6..];
-
-                // Deserialize the JSON data:
-                providerResponse = JsonSerializer.Deserialize<T>(jsonData, JSON_SERIALIZER_OPTIONS);
+                if(streamReader.EndOfStream)
+                    break;
             }
-            catch
+            catch (Exception e)
             {
-                // Skip invalid JSON data:
-                continue;
+                await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Stream, string.Format(TB("Tried to stream the LLM provider '{0}' answer. There were some problems with the stream. The message is: '{1}'"), this.InstanceName, e.Message)));
+                this.logger.LogWarning($"Failed to read the end-of-stream state from {providerName} '{this.InstanceName}': {e.Message}");
+                break;
+            }
+                
+            // Check if the token is canceled:
+            if (token.IsCancellationRequested)
+            {
+                this.logger.LogWarning($"The user canceled the responses for {providerName} '{this.InstanceName}'.");
+                streamReader.Close();
+                yield break;
             }
 
-            // Skip empty responses:
-            if (!providerResponse.ContainsContent())
-                continue;
+            //
+            // Read the next line:
+            //
+            string? line;
+            try
+            {
+                line = await streamReader.ReadLineAsync(token);
+            }
+            catch (Exception e)
+            {
+                await MessageBus.INSTANCE.SendError(new(Icons.Material.Filled.Stream, string.Format(TB("Tried to stream the LLM provider '{0}' answer. Was not able to read the stream. The message is: '{1}'"), this.InstanceName, e.Message)));
+                this.logger.LogError($"Failed to read the stream from {providerName} '{this.InstanceName}': {e.Message}");
+                break;
+            }
 
-            // Yield the response:
-            yield return providerResponse.GetContent();
+            // Skip empty lines:
+            if (string.IsNullOrWhiteSpace(line))
+                continue;
+            
+            // Check if the line is the end of the stream:
+            if (line.StartsWith("event: response.completed", StringComparison.InvariantCulture))
+                yield break;
+            
+            //
+            // Find delta lines:
+            //
+            if (line.StartsWith("""
+                                data: {"type":"response.output_text.delta"
+                                """, StringComparison.InvariantCulture))
+            {
+                TDelta? providerResponse;
+                try
+                {
+                    // We know that the line starts with "data: ". Hence, we can
+                    // skip the first 6 characters to get the JSON data after that.
+                    var jsonData = line[6..];
+
+                    // Deserialize the JSON data:
+                    providerResponse = JsonSerializer.Deserialize<TDelta>(jsonData, JSON_SERIALIZER_OPTIONS);
+
+                    if (providerResponse is null)
+                        continue;
+                }
+                catch
+                {
+                    // Skip invalid JSON data:
+                    continue;
+                }
+
+                // Skip empty responses:
+                if (!providerResponse.ContainsContent())
+                    continue;
+
+                // Yield the response:
+                yield return providerResponse.GetContent();
+            }
+            
+            //
+            // Find annotation added lines:
+            //
+            else if (annotationSupported && line.StartsWith(
+                         """
+                         data: {"type":"response.output_text.annotation.added"
+                         """, StringComparison.InvariantCulture))
+            {
+                TAnnotation? providerResponse;
+                try
+                {
+                    // We know that the line starts with "data: ". Hence, we can
+                    // skip the first 6 characters to get the JSON data after that.
+                    var jsonData = line[6..];
+
+                    // Deserialize the JSON data:
+                    providerResponse = JsonSerializer.Deserialize<TAnnotation>(jsonData, JSON_SERIALIZER_OPTIONS);
+
+                    if (providerResponse is null)
+                        continue;
+                }
+                catch
+                {
+                    // Skip invalid JSON data:
+                    continue;
+                }
+
+                // Skip empty responses:
+                if (!providerResponse.ContainsSources())
+                    continue;
+
+                // Yield the response:
+                yield return new(string.Empty, providerResponse.GetSources());
+            }
         }
         
         streamReader.Dispose();

app/MindWork AI Studio/Provider/DeepSeek/ProviderDeepSeek.cs

@@ -76,7 +76,7 @@ public sealed class ProviderDeepSeek(ILogger logger) : BaseProvider("https://api
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("DeepSeek", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("DeepSeek", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Fireworks/ProviderFireworks.cs

@@ -4,6 +4,7 @@ using System.Text;
 using System.Text.Json;
 
 using AIStudio.Chat;
+using AIStudio.Provider.OpenAI;
 using AIStudio.Settings;
 
 namespace AIStudio.Provider.Fireworks;
@@ -77,7 +78,7 @@ public class ProviderFireworks(ILogger logger) : BaseProvider("https://api.firew
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine>("Fireworks", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine, ChatCompletionAnnotationStreamLine>("Fireworks", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Fireworks/ResponseStreamLine.cs

@@ -15,6 +15,20 @@ public readonly record struct ResponseStreamLine(string Id, string Object, uint
 
     /// <inheritdoc />
     public ContentStreamChunk GetContent() => new(this.Choices[0].Delta.Content, []);
+
+    #region Implementation of IAnnotationStreamLine
+
+    //
+    // Currently, Fireworks does not provide source citations in their response stream.
+    //
+    
+    /// <inheritdoc />
+    public bool ContainsSources() => false;
+
+    /// <inheritdoc />
+    public IList<ISource> GetSources() => [];
+
+    #endregion
 }
 
 /// <summary>

app/MindWork AI Studio/Provider/GWDG/ProviderGWDG.cs

@@ -76,7 +76,7 @@ public sealed class ProviderGWDG(ILogger logger) : BaseProvider("https://chat-ai
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("GWDG", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("GWDG", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Google/ProviderGoogle.cs

@@ -78,7 +78,7 @@ public class ProviderGoogle(ILogger logger) : BaseProvider("https://generativela
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("Google", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("Google", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Groq/ProviderGroq.cs

@@ -78,7 +78,7 @@ public class ProviderGroq(ILogger logger) : BaseProvider("https://api.groq.com/o
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("Groq", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("Groq", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/Helmholtz/ProviderHelmholtz.cs

@@ -76,7 +76,7 @@ public sealed class ProviderHelmholtz(ILogger logger) : BaseProvider("https://ap
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("Helmholtz", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("Helmholtz", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/HuggingFace/ProviderHuggingFace.cs

@@ -81,7 +81,7 @@ public sealed class ProviderHuggingFace : BaseProvider
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("HuggingFace", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("HuggingFace", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/IAnnotationStreamLine.cs

@@ -0,0 +1,19 @@
+namespace AIStudio.Provider;
+
+/// <summary>
+/// A contract for a line in a response stream that can provide annotations such as sources.
+/// </summary>
+public interface IAnnotationStreamLine
+{
+    /// <summary>
+    /// Checks if the response line contains any sources.
+    /// </summary>
+    /// <returns>True when the response line contains sources, false otherwise.</returns>
+    public bool ContainsSources();
+
+    /// <summary>
+    /// Gets the sources of the response line.
+    /// </summary>
+    /// <returns>The sources of the response line.</returns>
+    public IList<ISource> GetSources();
+}

app/MindWork AI Studio/Provider/IResponseStreamLine.cs

@@ -1,6 +1,9 @@
 namespace AIStudio.Provider;
 
-public interface IResponseStreamLine
+/// <summary>
+/// A contract for a streamed response line that may contain content and annotations.
+/// </summary>
+public interface IResponseStreamLine : IAnnotationStreamLine
 {
     /// <summary>
     /// Checks if the response line contains any content.
@@ -13,16 +16,4 @@ public interface IResponseStreamLine
     /// </summary>
     /// <returns>The content of the response line.</returns>
     public ContentStreamChunk GetContent();
-    
-    /// <summary>
-    /// Checks if the response line contains any sources.
-    /// </summary>
-    /// <returns>True when the response line contains sources, false otherwise.</returns>
-    public bool ContainsSources() => false;
-    
-    /// <summary>
-    /// Gets the sources of the response line.
-    /// </summary>
-    /// <returns>The sources of the response line.</returns>
-    public IList<ISource> GetSources() => [];
 }

app/MindWork AI Studio/Provider/Mistral/ProviderMistral.cs

@@ -77,7 +77,7 @@ public sealed class ProviderMistral(ILogger logger) : BaseProvider("https://api.
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("Mistral", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("Mistral", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/NoChatCompletionAnnotationStreamLine.cs

@@ -0,0 +1,15 @@
+namespace AIStudio.Provider;
+
+/// <summary>
+/// A marker record indicating that no chat completion annotation line is expected in that stream.
+/// </summary>
+public sealed record NoChatCompletionAnnotationStreamLine : IAnnotationStreamLine
+{
+    #region Implementation of IAnnotationStreamLine
+
+    public bool ContainsSources() => false;
+
+    public IList<ISource> GetSources() => [];
+
+    #endregion
+}

app/MindWork AI Studio/Provider/NoResponsesAnnotationStreamLine.cs

@@ -0,0 +1,15 @@
+namespace AIStudio.Provider;
+
+/// <summary>
+/// A marker record indicating that no annotation line is expected in that Responses API stream.
+/// </summary>
+public sealed record NoResponsesAnnotationStreamLine : IAnnotationStreamLine
+{
+    #region Implementation of IAnnotationStreamLine
+
+    public bool ContainsSources() => false;
+
+    public IList<ISource> GetSources() => [];
+
+    #endregion
+}

app/MindWork AI Studio/Provider/OpenAI/AnnotatingUnknown.cs

@@ -0,0 +1,7 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Represents an unknown annotation type.
+/// </summary>
+/// <param name="Type">The type of the unknown annotation.</param>
+public sealed record AnnotatingUnknown(string Type) : Annotation(Type);

app/MindWork AI Studio/Provider/OpenAI/Annotation.cs

@@ -0,0 +1,10 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Base class for different types of annotations.
+/// </summary>
+/// <remarks>
+/// We use this base class to represent various annotation types for all types of LLM providers.
+/// </remarks>
+/// <param name="Type">The type of the annotation.</param>
+public abstract record Annotation(string Type);

app/MindWork AI Studio/Provider/OpenAI/AnnotationConverter.cs

@@ -0,0 +1,62 @@
+using System.Text.Json;
+using System.Text.Json.Serialization;
+
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Custom JSON converter for the annotation class to handle polymorphic deserialization.
+/// </summary>
+/// <remarks>
+/// We use this converter for chat completion API and responses API annotation deserialization.
+/// </remarks>
+public sealed class AnnotationConverter : JsonConverter<Annotation>
+{
+    public override Annotation? Read(ref Utf8JsonReader reader, Type typeToConvert, JsonSerializerOptions options)
+    {
+        using var doc = JsonDocument.ParseValue(ref reader);
+        var root = doc.RootElement;
+        
+        if (!root.TryGetProperty("type", out var typeElement))
+            return null;
+        
+        var type = typeElement.GetString();
+        var rawText = root.GetRawText();
+        
+        Annotation? annotation;
+        switch (type)
+        {
+            case "url_citation":
+                
+                // Let's check the responses API data type first:
+                var responsesAnnotation = JsonSerializer.Deserialize<ResponsesAnnotatingUrlCitationData>(rawText, options);
+                
+                // If it fails, let's try the chat completion API data type:
+                if(responsesAnnotation is null || string.IsNullOrWhiteSpace(responsesAnnotation.Title) || string.IsNullOrWhiteSpace(responsesAnnotation.URL))
+                {
+                    // Try chat completion API data type:
+                    var chatCompletionAnnotation = JsonSerializer.Deserialize<ChatCompletionAnnotatingURL>(rawText, options);
+                    
+                    // If both fail, we return the unknown type:
+                    if(chatCompletionAnnotation is null)
+                        annotation = new AnnotatingUnknown(type);
+                    else
+                        annotation = chatCompletionAnnotation;
+                }
+                else
+                    annotation = responsesAnnotation;
+                
+                break;
+            
+            default:
+                annotation = new AnnotatingUnknown(type ?? "unknown");
+                break;
+        }
+
+        return annotation;
+    }
+
+    public override void Write(Utf8JsonWriter writer, Annotation value, JsonSerializerOptions options)
+    {
+        JsonSerializer.Serialize(writer, value, value.GetType(), options);
+    }
+}

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionAnnotatingURL.cs

@@ -0,0 +1,16 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data structure for URL annotation in chat completions.
+/// </summary>
+/// <remarks>
+/// Although this class is not directly intended for the Responses API, it is
+/// used there as a fallback solution. One day, one of the open source LLM
+/// drivers may use this data structure for their responses API.
+/// </remarks>
+/// <param name="Type">The type of annotation, typically "url_citation".</param>
+/// <param name="UrlCitation">The URL citation details.</param>
+public sealed record ChatCompletionAnnotatingURL(
+    string Type,
+    ChatCompletionUrlCitationData UrlCitation
+) : Annotation(Type);

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionAnnotationChoice.cs

@@ -0,0 +1,8 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data structure representing a choice in a chat completion annotation response.
+/// </summary>
+/// <param name="Index">The index of the choice.</param>
+/// <param name="Delta">The delta information for the choice.</param>
+public record ChatCompletionAnnotationChoice(int Index, ChatCompletionAnnotationDelta Delta);

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionAnnotationDelta.cs

@@ -0,0 +1,7 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data structure representing annotation deltas in chat completions.
+/// </summary>
+/// <param name="Annotations">The list of annotations, which can be null.</param>
+public record ChatCompletionAnnotationDelta(IList<Annotation>? Annotations);

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionAnnotationStreamLine.cs

@@ -0,0 +1,57 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Represents a line of a chat completion annotation stream.
+/// </summary>
+/// <param name="Id">The unique identifier of the chat completion.</param>
+/// <param name="Object">The type of object returned, typically "chat.completion".</param>
+/// <param name="Created">The creation timestamp of the chat completion in Unix epoch format.</param>
+/// <param name="Model">The model used for the chat completion.</param>
+/// <param name="SystemFingerprint">The system fingerprint associated with the chat completion.</param>
+/// <param name="Choices">The list of choices returned in the chat completion.</param>
+public record ChatCompletionAnnotationStreamLine(string Id, string Object, uint Created, string Model, string SystemFingerprint, IList<ChatCompletionAnnotationChoice> Choices) : IAnnotationStreamLine
+{
+    #region Implementation of IAnnotationStreamLine
+
+    /// <inheritdoc />
+    public bool ContainsSources() => this.Choices.Any(choice => choice.Delta.Annotations is not null && choice.Delta.Annotations.Any(annotation => annotation is not AnnotatingUnknown));
+
+    /// <inheritdoc />
+    public IList<ISource> GetSources()
+    {
+        var sources = new List<ISource>();
+        foreach (var choice in this.Choices)
+        {
+            if (choice.Delta.Annotations is null)
+                continue;
+
+            // Iterate through all annotations:
+            foreach (var annotation in choice.Delta.Annotations)
+            {
+                // Check if the annotation is of the expected type and extract the source information:
+                if (annotation is ChatCompletionAnnotatingURL urlAnnotation)
+                    sources.Add(new Source(urlAnnotation.UrlCitation.Title, urlAnnotation.UrlCitation.URL));
+
+                //
+                // Check for the unexpected annotation type of the Responses API.
+                //
+                // This seems weird at first. But there are two possibilities why this could happen:
+                // - Anyone of the open source providers such as ollama, LM Studio, etc. could
+                //   implement & use the Responses API data structures for annotations in their
+                //   chat completion endpoint.
+                //
+                // - Our custom JSON converter checks for the Responses API data type first. If it
+                //   fails, it checks for the chat completion API data type. So, when the Responses
+                //   API data type is valid, it will be deserialized into that type, even though
+                //   we are calling the chat completion endpoint.
+                //
+                if (annotation is ResponsesAnnotatingUrlCitationData citationData)
+                    sources.Add(new Source(citationData.Title, citationData.URL));
+            }
+        }
+
+        return sources;
+    }
+
+    #endregion
+}

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionDeltaStreamLine.cs

@@ -0,0 +1,45 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data model for a delta line in the chat completion response stream.
+/// </summary>
+/// <param name="Id">The id of the response.</param>
+/// <param name="Object">The object describing the response.</param>
+/// <param name="Created">The timestamp of the response.</param>
+/// <param name="Model">The model used for the response.</param>
+/// <param name="SystemFingerprint">The system fingerprint; together with the seed, this allows you to reproduce the response.</param>
+/// <param name="Choices">The choices made by the AI.</param>
+public record ChatCompletionDeltaStreamLine(string Id, string Object, uint Created, string Model, string SystemFingerprint, IList<ChatCompletionChoice> Choices) : IResponseStreamLine
+{
+    public ChatCompletionDeltaStreamLine() : this(string.Empty, string.Empty, 0, string.Empty, string.Empty, [])
+    {
+    }
+    
+    /// <inheritdoc />
+    public bool ContainsContent() => this.Choices.Count > 0;
+
+    /// <inheritdoc />
+    public ContentStreamChunk GetContent() => new(this.Choices[0].Delta.Content, []);
+
+    #region Implementation of IAnnotationStreamLine
+
+    //
+    // Please note that there are multiple options where LLM providers might stream sources:
+    //
+    // - As part of the delta content while streaming. That would be part of this class.
+    // - By using a dedicated stream event and data structure. That would be another class implementing IResponseStreamLine.
+    //
+    // Right now, OpenAI uses the latter approach, so we don't have any sources here. And
+    // because no other provider does it yet, we don't have any implementation here either.
+    //
+    // One example where sources are part of the delta content is the Perplexity provider.
+    //
+    
+    /// <inheritdoc />
+    public bool ContainsSources() => false;
+
+    /// <inheritdoc />
+    public IList<ISource> GetSources() => [];
+
+    #endregion
+}

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionResponseStreamLine.cs

@@ -1,33 +0,0 @@
-namespace AIStudio.Provider.OpenAI;
-
-/// <summary>
-/// Data model for a line in the response stream, for streaming chat completions.
-/// </summary>
-/// <param name="Id">The id of the response.</param>
-/// <param name="Object">The object describing the response.</param>
-/// <param name="Created">The timestamp of the response.</param>
-/// <param name="Model">The model used for the response.</param>
-/// <param name="SystemFingerprint">The system fingerprint; together with the seed, this allows you to reproduce the response.</param>
-/// <param name="Choices">The choices made by the AI.</param>
-public record ChatCompletionResponseStreamLine(string Id, string Object, uint Created, string Model, string SystemFingerprint, IList<ChatCompletionChoice> Choices) : IResponseStreamLine
-{
-    public ChatCompletionResponseStreamLine() : this(string.Empty, string.Empty, 0, string.Empty, string.Empty, [])
-    {
-    }
-    
-    /// <inheritdoc />
-    public bool ContainsContent() => this.Choices.Count > 0;
-
-    /// <inheritdoc />
-    public ContentStreamChunk GetContent() => new(this.Choices[0].Delta.Content, []);
-
-    #region Implementation of IAnnotationStreamLine
-
-    /// <inheritdoc />
-    public bool ContainsSources() => false;
-
-    /// <inheritdoc />
-    public IList<ISource> GetSources() => [];
-
-    #endregion
-}

app/MindWork AI Studio/Provider/OpenAI/ChatCompletionUrlCitationData.cs

@@ -0,0 +1,14 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Represents citation data for a URL in a chat completion response.
+/// </summary>
+/// <param name="EndIndex">The end index of the citation in the response text.</param>
+/// <param name="StartIndex">The start index of the citation in the response text.</param>
+/// <param name="Title">The title of the cited source.</param>
+/// <param name="URL">The URL of the cited source.</param>
+public sealed record ChatCompletionUrlCitationData(
+    int EndIndex,
+    int StartIndex,
+    string Title,
+    string URL);

app/MindWork AI Studio/Provider/OpenAI/ProviderOpenAI.cs

@@ -55,51 +55,113 @@ public sealed class ProviderOpenAI(ILogger logger) : BaseProvider("https://api.o
             
             _ => systemPromptRole,
         };
-        
-        this.logger.LogInformation($"Using the system prompt role '{systemPromptRole}' for model '{chatModel.Id}'.");
 
+        // Read the model capabilities:
+        var modelCapabilities = this.GetModelCapabilities(chatModel);
+        
+        // Check if we are using the Responses API or the Chat Completion API:
+        var usingResponsesAPI = modelCapabilities.Contains(Capability.RESPONSES_API);
+        
+        // Prepare the request path based on the API we are using:
+        var requestPath = usingResponsesAPI ? "responses" : "chat/completions";
+        
+        this.logger.LogInformation("Using the system prompt role '{SystemPromptRole}' and the '{RequestPath}' API for model '{ChatModelId}'.", systemPromptRole, requestPath, chatModel.Id);
+        
         // Prepare the system prompt:
         var systemPrompt = new Message
         {
             Role = systemPromptRole,
             Content = chatThread.PrepareSystemPrompt(settingsManager, chatThread, this.logger),
         };
-        
-        // Prepare the OpenAI HTTP chat request:
-        var openAIChatRequest = JsonSerializer.Serialize(new ChatCompletionAPIRequest
+
+        //
+        // Prepare the tools we want to use:
+        //
+        IList<Tool> tools = modelCapabilities.Contains(Capability.WEB_SEARCH) switch
         {
-            Model = chatModel.Id,
-            
-            // Build the messages:
-            // - First of all the system prompt
-            // - Then none-empty user and AI messages
-            Messages = [systemPrompt, ..chatThread.Blocks.Where(n => n.ContentType is ContentType.TEXT && !string.IsNullOrWhiteSpace((n.Content as ContentText)?.Text)).Select(n => new Message
+            true => [ Tools.WEB_SEARCH ],
+            _ => []
+        };
+        
+        //
+        // Create the request: either for the Responses API or the Chat Completion API
+        //
+        var openAIChatRequest = usingResponsesAPI switch
+        {
+            // Chat Completion API request:
+            false => JsonSerializer.Serialize(new ChatCompletionAPIRequest
             {
-                Role = n.Role switch
-                {
-                    ChatRole.USER => "user",
-                    ChatRole.AI => "assistant",
-                    ChatRole.AGENT => "assistant",
-                    ChatRole.SYSTEM => systemPromptRole,
-
-                    _ => "user",
-                },
-
-                Content = n.Content switch
-                {
-                    ContentText text => text.Text,
-                    _ => string.Empty,
-                }
-            }).ToList()],
+                Model = chatModel.Id,
             
-            // Right now, we only support streaming completions:
-            Stream = true,
-        }, JSON_SERIALIZER_OPTIONS);
+                // Build the messages:
+                // - First of all the system prompt
+                // - Then none-empty user and AI messages
+                Messages = [systemPrompt, ..chatThread.Blocks.Where(n => n.ContentType is ContentType.TEXT && !string.IsNullOrWhiteSpace((n.Content as ContentText)?.Text)).Select(n => new Message
+                {
+                    Role = n.Role switch
+                    {
+                        ChatRole.USER => "user",
+                        ChatRole.AI => "assistant",
+                        ChatRole.AGENT => "assistant",
+                        ChatRole.SYSTEM => systemPromptRole,
+
+                        _ => "user",
+                    },
+
+                    Content = n.Content switch
+                    {
+                        ContentText text => text.Text,
+                        _ => string.Empty,
+                    }
+                }).ToList()],
+            
+                // Right now, we only support streaming completions:
+                Stream = true,
+            }, JSON_SERIALIZER_OPTIONS),
+            
+            // Responses API request:
+            true => JsonSerializer.Serialize(new ResponsesAPIRequest
+            {
+                Model = chatModel.Id,
+            
+                // Build the messages:
+                // - First of all the system prompt
+                // - Then none-empty user and AI messages
+                Input = [systemPrompt, ..chatThread.Blocks.Where(n => n.ContentType is ContentType.TEXT && !string.IsNullOrWhiteSpace((n.Content as ContentText)?.Text)).Select(n => new Message
+                {
+                    Role = n.Role switch
+                    {
+                        ChatRole.USER => "user",
+                        ChatRole.AI => "assistant",
+                        ChatRole.AGENT => "assistant",
+                        ChatRole.SYSTEM => systemPromptRole,
+
+                        _ => "user",
+                    },
+
+                    Content = n.Content switch
+                    {
+                        ContentText text => text.Text,
+                        _ => string.Empty,
+                    }
+                }).ToList()],
+            
+                // Right now, we only support streaming completions:
+                Stream = true,
+                
+                // We do not want to store any data on OpenAI's servers:
+                Store = false,
+                
+                // Tools we want to use:
+                Tools = tools,
+                
+            }, JSON_SERIALIZER_OPTIONS),
+        };
 
         async Task<HttpRequestMessage> RequestBuilder()
         {
             // Build the HTTP post request:
-            var request = new HttpRequestMessage(HttpMethod.Post, "chat/completions");
+            var request = new HttpRequestMessage(HttpMethod.Post, requestPath);
 
             // Set the authorization header:
             request.Headers.Authorization = new AuthenticationHeaderValue("Bearer", await requestedSecret.Secret.Decrypt(ENCRYPTION));
@@ -108,18 +170,24 @@ public sealed class ProviderOpenAI(ILogger logger) : BaseProvider("https://api.o
             request.Content = new StringContent(openAIChatRequest, Encoding.UTF8, "application/json");
             return request;
         }
+
+        if (usingResponsesAPI)
+            await foreach (var content in this.StreamResponsesInternal<ResponsesDeltaStreamLine, ResponsesAnnotationStreamLine>("OpenAI", RequestBuilder, token))
+                yield return content;
         
-        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine>("OpenAI", RequestBuilder, token))
-            yield return content;
-            await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("OpenAI", RequestBuilder, token))
+        else
+            await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("OpenAI", RequestBuilder, token))
+                yield return content;
     }
 
     #pragma warning disable CS1998 // Async method lacks 'await' operators and will run synchronously
+    
     /// <inheritdoc />
     public override async IAsyncEnumerable<ImageURL> StreamImageCompletion(Model imageModel, string promptPositive, string promptNegative = FilterOperator.String.Empty, ImageURL referenceImageURL = default, [EnumeratorCancellation] CancellationToken token = default)
     {
         yield break;
     }
+    
     #pragma warning restore CS1998 // Async method lacks 'await' operators and will run synchronously
 
     /// <inheritdoc />
@@ -213,7 +281,7 @@ public sealed class ProviderOpenAI(ILogger logger) : BaseProvider("https://api.o
                     Capability.RESPONSES_API,
                 ];
         
-        if (modelName.StartsWith("o4-mini") || modelName.StartsWith("o1") || modelName.StartsWith("o3"))
+        if (modelName.StartsWith("o4-mini") || modelName.StartsWith("o3"))
             return
                 [
                     Capability.TEXT_INPUT, Capability.MULTIPLE_IMAGE_INPUT,
@@ -224,6 +292,16 @@ public sealed class ProviderOpenAI(ILogger logger) : BaseProvider("https://api.o
                     Capability.RESPONSES_API,
                 ];
         
+        if (modelName.StartsWith("o1"))
+            return
+            [
+                Capability.TEXT_INPUT, Capability.MULTIPLE_IMAGE_INPUT,
+                Capability.TEXT_OUTPUT,
+                    
+                Capability.ALWAYS_REASONING, Capability.FUNCTION_CALLING,
+                Capability.RESPONSES_API,
+            ];
+        
         if(modelName.StartsWith("gpt-4-turbo"))
             return
                 [
@@ -242,6 +320,16 @@ public sealed class ProviderOpenAI(ILogger logger) : BaseProvider("https://api.o
                     Capability.RESPONSES_API,
                 ];
         
+        if(modelName.StartsWith("gpt-5-nano"))
+            return
+            [
+                Capability.TEXT_INPUT, Capability.MULTIPLE_IMAGE_INPUT,
+                Capability.TEXT_OUTPUT,
+                
+                Capability.FUNCTION_CALLING, Capability.ALWAYS_REASONING,
+                Capability.RESPONSES_API,
+            ];
+        
         if(modelName is "gpt-5" || modelName.StartsWith("gpt-5-"))
             return
             [

app/MindWork AI Studio/Provider/OpenAI/ResponsesAPIRequest.cs

@@ -0,0 +1,21 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// The request body for the Responses API.
+/// </summary>
+/// <param name="Model">Which model to use.</param>
+/// <param name="Input">The chat messages.</param>
+/// <param name="Stream">Whether to stream the response.</param>
+/// <param name="Store">Whether to store the response on the server (usually OpenAI's infrastructure).</param>
+/// <param name="Tools">The tools to use for the request.</param>
+public record ResponsesAPIRequest(
+    string Model,
+    IList<Message> Input,
+    bool Stream,
+    bool Store,
+    IList<Tool> Tools)
+{
+    public ResponsesAPIRequest() : this(string.Empty, [], true, false, [])
+    {
+    }
+}

app/MindWork AI Studio/Provider/OpenAI/ResponsesAnnotatingURL.cs

@@ -0,0 +1,16 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data structure for URL citation annotations in the OpenAI Responses API.
+/// </summary>
+/// <param name="Type">The type of annotation, typically "url_citation".</param>
+/// <param name="EndIndex">The end index of the annotated text in the response.</param>
+/// <param name="StartIndex">The start index of the annotated text in the response.</param>
+/// <param name="Title">The title of the cited URL.</param>
+/// <param name="URL">The URL being cited.</param>
+public sealed record ResponsesAnnotatingUrlCitationData(
+    string Type,
+    int EndIndex,
+    int StartIndex,
+    string Title,
+    string URL) : Annotation(Type);

app/MindWork AI Studio/Provider/OpenAI/ResponsesAnnotationStreamLine.cs

@@ -0,0 +1,45 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data structure for a line in the response stream of the Responses API, containing an annotation.
+/// </summary>
+/// <param name="Type">The type of the annotation.</param>
+/// <param name="AnnotationIndex">The continuous index of the annotation in the response.</param>
+/// <param name="Annotation">The annotation details.</param>
+public sealed record ResponsesAnnotationStreamLine(string Type, int AnnotationIndex, Annotation Annotation) : IAnnotationStreamLine
+{
+    #region Implementation of IAnnotationStreamLine
+
+    /// <inheritdoc />
+    public bool ContainsSources()
+    {
+        return this.Annotation is not AnnotatingUnknown;
+    }
+
+    /// <inheritdoc />
+    public IList<ISource> GetSources()
+    {
+        //
+        // Check for the unexpected annotation type of the chat completion API.
+        //
+        // This seems weird at first. But there are two possibilities why this could happen:
+        // - Anyone of the open source providers such as ollama, LM Studio, etc. could
+        //   implement and use the chat completion API data structures for annotations in their
+        //   Responses API endpoint.
+        //
+        // - Our custom JSON converter checks for all possible annotation data types. So,
+        //   when the streamed data is valid for any annotation type, it will be deserialized
+        //   into that type, even though we are calling the Responses API endpoint.
+        //
+        if (this.Annotation is ChatCompletionAnnotatingURL urlAnnotation)
+            return [new Source(urlAnnotation.UrlCitation.Title, urlAnnotation.UrlCitation.URL)];
+        
+        // Check for the expected annotation type of the Responses API:
+        if (this.Annotation is ResponsesAnnotatingUrlCitationData urlCitationData)
+            return [new Source(urlCitationData.Title, urlCitationData.URL)];
+
+        return [];
+    }
+
+    #endregion
+}

app/MindWork AI Studio/Provider/OpenAI/ResponsesDeltaStreamLine.cs

@@ -0,0 +1,39 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Data model for a delta line in the Response API chat completion stream.
+/// </summary>
+/// <param name="Type">The type of the response.</param>
+/// <param name="Delta">The delta content of the response.</param>
+public record ResponsesDeltaStreamLine(
+    string Type,
+    string Delta) : IResponseStreamLine
+{
+    #region Implementation of IResponseStreamLine
+
+    /// <inheritdoc />
+    public bool ContainsContent() => !string.IsNullOrWhiteSpace(this.Delta);
+
+    /// <inheritdoc />
+    public ContentStreamChunk GetContent() => new(this.Delta, this.GetSources());
+
+    //
+    // Please note that there are multiple options where LLM providers might stream sources:
+    //
+    // - As part of the delta content while streaming. That would be part of this class.
+    // - By using a dedicated stream event and data structure. That would be another class implementing IResponseStreamLine.
+    //
+    // Right now, OpenAI uses the latter approach, so we don't have any sources here. And
+    // because no other provider does it yet, we don't have any implementation here either.
+    //
+    // One example where sources are part of the delta content is the Perplexity provider.
+    //
+    
+    /// <inheritdoc />
+    public bool ContainsSources() => false;
+
+    /// <inheritdoc />
+    public IList<ISource> GetSources() => [];
+
+    #endregion
+}

app/MindWork AI Studio/Provider/OpenAI/Tool.cs

@@ -0,0 +1,12 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Represents a tool used by the AI model.
+/// </summary>
+/// <remarks>
+/// Right now, only our OpenAI provider is using tools. Thus, this class is located in the
+/// OpenAI namespace. In the future, when other providers also support tools, this class can
+/// be moved into the provider namespace.
+/// </remarks>
+/// <param name="Type">The type of the tool.</param>
+public record Tool(string Type);

app/MindWork AI Studio/Provider/OpenAI/Tools.cs

@@ -0,0 +1,14 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// Known tools for LLM providers.
+/// </summary>
+/// <remarks>
+/// Right now, only our OpenAI provider is using tools. Thus, this class is located in the
+/// OpenAI namespace. In the future, when other providers also support tools, this class can
+/// be moved into the provider namespace.
+/// </remarks>
+public static class Tools
+{
+    public static readonly Tool WEB_SEARCH = new("web_search");
+}

app/MindWork AI Studio/Provider/Perplexity/ProviderPerplexity.cs

@@ -85,7 +85,7 @@ public sealed class ProviderPerplexity(ILogger logger) : BaseProvider("https://a
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine>("Perplexity", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ResponseStreamLine, NoChatCompletionAnnotationStreamLine>("Perplexity", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/SelfHosted/ProviderSelfHosted.cs

@@ -75,7 +75,7 @@ public sealed class ProviderSelfHosted(ILogger logger, Host host, string hostnam
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("self-hosted provider", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, ChatCompletionAnnotationStreamLine>("self-hosted provider", RequestBuilder, token))
             yield return content;
     }
 

app/MindWork AI Studio/Provider/X/ProviderX.cs

@@ -78,7 +78,7 @@ public sealed class ProviderX(ILogger logger) : BaseProvider("https://api.x.ai/v
             return request;
         }
         
-        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionResponseStreamLine>("xAI", RequestBuilder, token))
+        await foreach (var content in this.StreamChatCompletionInternal<ChatCompletionDeltaStreamLine, NoChatCompletionAnnotationStreamLine>("xAI", RequestBuilder, token))
             yield return content;
     }