Files
Assistant/backend/Realtime/OpenAIRealtimeUpstream.cs
T
tes 7294a81a9a Realtime: migrate to OpenAI GA shape (beta API was retired)
Upstream returned 'beta_api_shape_disabled' on every wake. Changes:
- Drop OpenAI-Beta: realtime=v1 header from the upgrade.
- session.update payload nests audio under session.audio.{input,output}
  and adds session.type='realtime'; audio.{input,output}.format is now
  an object {type:audio/pcm, rate:24000} instead of 'pcm16' string.
- Default model bumped to gpt-realtime (the GA name); the relay also
  promotes any stored 'gpt-4o-realtime-preview*' to gpt-realtime so
  pre-Plan-3 DeviceConfig rows keep working without a manual DB edit.
2026-06-12 06:42:21 +00:00

58 lines
2.0 KiB
C#

using System.Net.WebSockets;
using System.Text;
using System.Text.Json.Nodes;
namespace backend.Realtime;
public class OpenAIRealtimeUpstream : IRealtimeUpstream
{
private readonly ClientWebSocket _ws = new();
public async Task ConnectAsync(string apiKey, string model, CancellationToken ct)
{
_ws.Options.SetRequestHeader("Authorization", $"Bearer {apiKey}");
// The GA Realtime API does NOT take the OpenAI-Beta: realtime=v1 header.
// Sending it returns upstream error code=beta_api_shape_disabled.
var uri = new Uri($"wss://api.openai.com/v1/realtime?model={Uri.EscapeDataString(model)}");
await _ws.ConnectAsync(uri, ct);
}
public async Task SendJsonAsync(JsonObject envelope, CancellationToken ct)
{
var json = envelope.ToJsonString();
var bytes = Encoding.UTF8.GetBytes(json);
await _ws.SendAsync(bytes, WebSocketMessageType.Text, endOfMessage: true, ct);
}
public async Task<JsonObject?> ReceiveJsonAsync(CancellationToken ct)
{
var buffer = new byte[8192];
using var stream = new MemoryStream();
while (true)
{
WebSocketReceiveResult result;
try { result = await _ws.ReceiveAsync(buffer, ct); }
catch (WebSocketException) { return null; }
catch (OperationCanceledException) { return null; }
if (result.MessageType == WebSocketMessageType.Close) return null;
stream.Write(buffer, 0, result.Count);
if (result.EndOfMessage)
{
var json = Encoding.UTF8.GetString(stream.ToArray());
return JsonNode.Parse(json)?.AsObject();
}
}
}
public async ValueTask DisposeAsync()
{
if (_ws.State == WebSocketState.Open)
{
try { await _ws.CloseAsync(WebSocketCloseStatus.NormalClosure, "bye", CancellationToken.None); }
catch { }
}
_ws.Dispose();
}
}