> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nemo/relay/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Trait Event Normalization Ext

> Core-only normalized LLM accessors for ATOF events.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-pii-redaction -p nemo-relay-ffi -p nemo-relay-types -p nemo-relay-plugin -p nemo-relay-worker-proto -p nemo-relay-worker`.

<pre />

Core-only normalized LLM accessors for ATOF events.

These helpers use built-in codec resolution, so they live in the runtime crate rather than the shared DTO crate.

## Required Methods

#### `normalized_llm_request`

<pre />

Normalized LLM request: the codec annotation when present, otherwise a best-effort decode of the start-event input payload.

The fallback decode requires the start-event input to be the serialized [`LlmRequest`](/reference/api/rust-library-reference/nemo-relay/api/llm/struct-llmrequest) wire shape (`{headers, content}`) emitted by the managed LLM pipeline; events whose input is a bare payload or a non-LLM shape yield `None`.

#### `normalized_llm_response`

<pre />

Normalized LLM response: the codec annotation when present, otherwise a best-effort decode of the end-event output payload.

## Implementors

### `impl EventNormalizationExt for Event`

<pre />