Refactored the responses API as well

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

@@ -119,9 +119,7 @@ public sealed class ProviderOpenAI() : BaseProvider("https://api.openai.com/v1/"
             {
                 Model = chatModel.Id,
             
-                // Build the messages:
-                // - First of all the system prompt
-                // - Then none-empty user and AI messages
+                // All messages go into the messages field:
                 Messages = [systemPrompt, ..messages],
             
                 // Right now, we only support streaming completions:
@@ -134,27 +132,8 @@ public sealed class ProviderOpenAI() : BaseProvider("https://api.openai.com/v1/"
             {
                 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 TextMessage
-                {
-                    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()],
+                // All messages go into the input field:
+                Input = [systemPrompt, ..messages],
             
                 // Right now, we only support streaming completions:
                 Stream = true,

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

@@ -12,7 +12,7 @@ namespace AIStudio.Provider.OpenAI;
 /// <param name="Tools">The tools to use for the request.</param>
 public record ResponsesAPIRequest(
     string Model,
-    IList<TextMessage> Input,
+    IList<IMessageBase> Input,
     bool Stream,
     bool Store,
     IList<Tool> Tools)