RealtimeSession: persist user/assistant transcripts; emit assistant_done

backend.tests/RealtimeSessionTranscriptTests.cs

@@ -0,0 +1,60 @@
+using System.Text.Json.Nodes;
+using backend.Conversations;
+using backend.Data;
+using backend.Realtime;
+using backend.Tools;
+using FluentAssertions;
+using Microsoft.EntityFrameworkCore;
+using Microsoft.Extensions.DependencyInjection;
+using Xunit;
+
+namespace backend.tests;
+
+public class RealtimeSessionTranscriptTests(ApiFactory factory) : IClassFixture<ApiFactory>
+{
+    private readonly ApiFactory _factory = factory;
+
+    [Fact]
+    public async Task User_and_assistant_transcripts_are_persisted_and_response_done_emits_assistant_done()
+    {
+        using var scope = _factory.Services.CreateScope();
+        var db = scope.ServiceProvider.GetRequiredService<AppDbContext>();
+        var log = scope.ServiceProvider.GetRequiredService<ConversationLog>();
+        var reg = new ToolRegistry(Array.Empty<ITool>());
+        var upstream = new ScriptedRealtimeUpstream();
+        var sink = new RecordingSink();
+        var cfg = new RealtimeSettings("m", "v", "p", 30, new HashSet<string>());
+        var session = new RealtimeSession(Guid.NewGuid(), upstream, sink, log, reg, cfg,
+            new FakeDeviceChannel(), NullLogger.Instance);
+
+        upstream.Push(new JsonObject { ["type"] = "session.updated" });
+        var cts = new CancellationTokenSource();
+        var run = session.RunAsync(cts.Token);
+        await sink.WaitForAsync("session_started", TimeSpan.FromSeconds(2));
+
+        upstream.Push(new JsonObject
+        {
+            ["type"] = "conversation.item.input_audio_transcription.completed",
+            ["transcript"] = "hello",
+        });
+        upstream.Push(new JsonObject
+        {
+            ["type"] = "response.audio_transcript.done",
+            ["transcript"] = "hi there",
+        });
+        upstream.Push(new JsonObject { ["type"] = "response.done" });
+
+        await sink.WaitForAsync("assistant_done", TimeSpan.FromSeconds(2));
+
+        var convoId = session.ConversationId!.Value;
+        var turns = await db.Turns
+            .Where(t => t.ConversationId == convoId)
+            .OrderBy(t => t.Index).ToListAsync();
+        turns.Select(t => t.Role).Should().Equal(TurnRole.User, TurnRole.Assistant);
+        turns[0].Text.Should().Be("hello");
+        turns[1].Text.Should().Be("hi there");
+
+        cts.Cancel();
+        await run;
+    }
+}

backend/Realtime/RealtimeSession.cs

@@ -121,6 +121,24 @@ public class RealtimeSession
                 case "response.audio.delta":
                     await ForwardAudioDeltaAsync(evt, ct);
                     break;
+                case "conversation.item.input_audio_transcription.completed":
+                {
+                    var text = (string?)evt["transcript"];
+                    if (_conversation is not null && !string.IsNullOrEmpty(text))
+                        await _log.AppendUserAsync(_conversation.Id, text!, ct);
+                    break;
+                }
+                case "response.audio_transcript.done":
+                {
+                    var text = (string?)evt["transcript"];
+                    if (_conversation is not null && !string.IsNullOrEmpty(text))
+                        await _log.AppendAssistantAsync(_conversation.Id, text!, ct);
+                    break;
+                }
+                case "response.done":
+                    await _output.WriteEnvelopeAsync(
+                        new JsonObject { ["type"] = "assistant_done" }, ct);
+                    break;
             }
         }
     }