Added the exact token count where the provider reports it (#989)

Co-authored-by: Thorsten Sommer <SommerEngineering@users.noreply.github.com>

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

@@ -0,0 +1,18 @@
+namespace AIStudio.Provider.OpenAI;
+
+/// <summary>
+/// What a streamed chat completion should report beyond its content.
+/// </summary>
+/// <remarks>
+/// An OpenAI-compatible provider says nothing about what a streamed request cost unless it is asked
+/// to. Without this block, the stream simply ends and the only token number anybody ever sees is
+/// the one AI Studio estimated for itself.
+/// </remarks>
+/// <param name="IncludeUsage">Whether the stream should end with a line stating the token usage.</param>
+public sealed record ChatCompletionStreamOptions(bool IncludeUsage)
+{
+    /// <summary>
+    /// Asks for the usage line.
+    /// </summary>
+    public static readonly ChatCompletionStreamOptions INCLUDE_USAGE = new(true);
+}