Tracing

Rebyte supports execution tracing for the Agents API through its Langfuse integration. Traces connect a Session's model calls and tool activity to individual Turns, so you can investigate results, failures and latency.

View traces in Platform

1. Open Platform and select the organization that owns your API Agent.
2. Open the Agent to see its execution traces across Sessions.
3. Open a Session to narrow the trace view to that conversation, or open a Turn for its individual execution trace.

The embedded trace view uses your Rebyte organization access. If it asks you to sign in, use the sign-in action in the trace panel. An API key alone does not grant browser access to the trace dashboard.

What is recorded

Each Turn has its own trace identity. Reusing an Agent across Sessions does not combine their execution traces. Turn duration measures the persisted lifetime from creation to completion; it can include queueing and waiting for client function results, rather than only active model execution. Your application's client function runs outside Rebyte, so its internal execution is not automatically instrumented.

Tracing runs on the Rebyte service; API consumers do not need to install a Langfuse SDK or pass a tracing flag when creating an Agent or Session. Recording depends on the deployment's tracing configuration. Self-hosted deployments must configure the Langfuse integration before traces are available.

Inspect execution through the API

Use Session, Turn and Item IDs to correlate your application logs with the trace view. You can also retrieve persisted outcomes with the official OpenAI client configured for Rebyte:

const turns = await client.beta.agents.sessions.turns.list(sessionId);
for (const turn of turns.data) {
  console.log({
    sessionId,
    turnId: turn.id,
    status: turn.status,
    usage: turn.usage,
    error: turn.error,
  });
}

See Observability and usage for Items, live events and token usage.

OpenAI compatibility

OpenAI's managed Agents API enables tracing by default and presents turn traces in its dashboard. It also supports paginated OTLP JSON export through GET /v1/agents/sessions/{session_id}/traces when trace export is enabled for the organization and the key has the required permission. See OpenAI's trace export guide.

Rebyte does not currently implement that public trace-export endpoint. Its Platform/Langfuse trace view is a separate integration. See the compatibility comparison for current gaps.

Rebyte provides its execution trace dashboard through Langfuse in Platform. Use Sessions, Turns and Items for programmatic inspection, and live events for progress. The separate OpenAI Agents SDK is a different product; its application-side tracing configuration should not be assumed to apply to the managed Agents API.