RealtimeSession: execute server-side tools at response.done

This commit is contained in:
2026-06-11 21:38:31 +00:00
parent b078f9aa78
commit 7dada5fdb9
2 changed files with 131 additions and 0 deletions
+64
View File
@@ -25,6 +25,7 @@ public class RealtimeSession
private Conversation? _conversation;
private EndReason _endReason = EndReason.Unknown;
private bool _endRequested;
private readonly List<(string CallId, string Name, string ArgsJson)> _pendingCalls = new();
private readonly System.Threading.Channels.Channel<byte[]> _uplink =
System.Threading.Channels.Channel.CreateBounded<byte[]>(
@@ -135,14 +136,77 @@ public class RealtimeSession
await _log.AppendAssistantAsync(_conversation.Id, text!, ct);
break;
}
case "response.function_call_arguments.done":
{
var callId = (string?)evt["call_id"] ?? "";
var name = (string?)evt["name"] ?? "";
var args = (string?)evt["arguments"] ?? "{}";
_pendingCalls.Add((callId, name, args));
break;
}
case "response.done":
{
await _output.WriteEnvelopeAsync(
new JsonObject { ["type"] = "assistant_done" }, ct);
if (_pendingCalls.Count == 0) break;
var calls = _pendingCalls.ToList();
_pendingCalls.Clear();
if (calls.Any(c => c.Name == "end_session"))
{
_endReason = EndReason.Tool;
_endRequested = true;
break;
}
foreach (var c in calls)
{
await ExecuteToolAsync(c.CallId, c.Name, c.ArgsJson, ct);
}
break;
}
}
}
}
private async Task ExecuteToolAsync(string callId, string name, string argsJson, CancellationToken ct)
{
var tool = _registry.Get(name);
string outputJson;
if (tool is null)
{
outputJson = $$"""{"ok":false,"error":"unknown tool: {{name}}"}""";
}
else
{
try
{
using var argsDoc = System.Text.Json.JsonDocument.Parse(argsJson);
var ctx = new DeviceContext(_deviceId, _conversation!.Id, _channel);
var res = await tool.ExecuteAsync(
new ToolInvocation(callId, argsDoc.RootElement.Clone()), ctx, ct);
outputJson = res.Output.GetRawText();
}
catch (Exception ex)
{
outputJson = System.Text.Json.JsonSerializer.Serialize(new
{
ok = false,
error = ex.Message,
});
}
}
if (_conversation is not null)
{
await _log.AppendToolAsync(_conversation.Id, name, argsJson, outputJson, ct);
}
await _upstream.SendJsonAsync(RealtimeEvents.FunctionCallOutput(callId, outputJson), ct);
await _upstream.SendJsonAsync(RealtimeEvents.ResponseCreate(), ct);
}
private async Task ForwardAudioDeltaAsync(JsonObject evt, CancellationToken ct)
{
var b64 = (string?)evt["delta"];