Added a way to read what the AI received from your sources (#1100)

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

app/Tests/Tools/WordCountingTokenizer.cs

@@ -0,0 +1,23 @@
+using System.Net;
+using System.Net.Http.Json;
+using System.Text.Json;
+
+namespace AIStudio.Tests.Tools;
+
+/// <summary>
+/// Plays the tokenizer of the runtime for tests which cut texts into chunks: one token per word.
+/// </summary>
+/// <remarks>
+/// Counting words is all it takes to make a chunk full, so a test can say exactly where a chunk ends.
+/// </remarks>
+internal sealed class WordCountingTokenizer : HttpMessageHandler
+{
+    public static int Count(string text) => text.Split((char[]?)null, StringSplitOptions.RemoveEmptyEntries).Length;
+
+    protected override async Task<HttpResponseMessage> SendAsync(HttpRequestMessage request, CancellationToken cancellationToken)
+    {
+        using var body = JsonDocument.Parse(await request.Content!.ReadAsStringAsync(cancellationToken));
+        var text = body.RootElement.GetProperty("text").GetString() ?? string.Empty;
+        return new HttpResponseMessage(HttpStatusCode.OK) { Content = JsonContent.Create(new { success = true, token_count = Count(text), message = string.Empty }) };
+    }
+}