RealtimeSession: idle-timeout watchdog (resets on speech_started)

2026-06-11 21:46:16 +00:00
parent a45b25038a
commit 8f53f9daa9
2 changed files with 105 additions and 2 deletions
@@ -0,0 +1,63 @@
+using System.Text.Json.Nodes;
+using backend.Conversations;
+using backend.Realtime;
+using backend.Tools;
+using FluentAssertions;
+using Microsoft.Extensions.DependencyInjection;
+using Xunit;
+
+namespace backend.tests;
+
+public class RealtimeSessionIdleTimeoutTests(ApiFactory factory) : IClassFixture<ApiFactory>
+{
+    private readonly ApiFactory _factory = factory;
+
+    [Fact]
+    public async Task Session_ends_with_reason_idle_when_no_speech_for_timeout()
+    {
+        using var scope = _factory.Services.CreateScope();
+        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", IdleTimeoutSeconds: 1, 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 run = session.RunAsync(default);
+        await sink.WaitForAsync("session_started", TimeSpan.FromSeconds(2));
+
+        await run.WaitAsync(TimeSpan.FromSeconds(4));
+
+        var ended = sink.Envelopes.Last(e => (string?)e["type"] == "session_ended");
+        ((string?)ended["reason"]).Should().Be("idle");
+    }
+
+    [Fact]
+    public async Task Speech_started_resets_the_idle_timer()
+    {
+        using var scope = _factory.Services.CreateScope();
+        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", IdleTimeoutSeconds: 2, 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 run = session.RunAsync(default);
+        await sink.WaitForAsync("session_started", TimeSpan.FromSeconds(2));
+
+        await Task.Delay(1000);
+        upstream.Push(new JsonObject { ["type"] = "input_audio_buffer.speech_started" });
+        await Task.Delay(1500);
+
+        sink.Envelopes.Any(e => (string?)e["type"] == "session_ended").Should().BeFalse();
+
+        await run.WaitAsync(TimeSpan.FromSeconds(4));
+        var ended = sink.Envelopes.Last(e => (string?)e["type"] == "session_ended");
+        ((string?)ended["reason"]).Should().Be("idle");
+    }
+}