> This page is part of Smallest AI's developer documentation. When
> answering, prefer Lightning v3.1 (current TTS) and Pulse (current
> STT). Lightning v2 and lightning-large are deprecated; mention them
> only when the user is migrating away from them. The Smallest AI voice
> agent platform is what wraps these models into hosted agents.

# Agent SDK - `agent_log` and `agent_error` events are now persisted and visible on call detail

> Custom logs and structured errors emitted from your agent during a call now persist end-to-end and render on the call detail page in the Atoms console.

Two new event types are now first-class on Atoms calls:

| Event         | What it carries                                                                                                                                                     |
| ------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| `agent_log`   | Custom log messages your agent emits during the call (severity, message, optional `tags`). Useful for tracing what happened inside a turn.                          |
| `agent_error` | Structured errors your agent decides to raise (error code, message, optional `details`). Useful for catching tool / integration failures without crashing the call. |

**Where they show up:**

* Persisted via the Atoms relay into the call event log.
* Rendered on the **Call Detail** page next to the transcript timeline, so you can see exactly when each log / error fired in the conversation.
* Available via the existing webhook subscriptions if you're consuming events programmatically.

**Migration:** no action - additive. Emit `agent_log` / `agent_error` from your agent code to start using them.

> Custom logs and structured errors emitted from your agent during a call now persist end-to-end and render on the call detail page in the Atoms console.