> This page is for NeMo Relay, version v0.9.4.
> For other versions, use one of these documentation indexes:
> - Latest (v0.10.0) (default): https://docs.nvidia.com/nemo/relay/latest/llms.txt
> - dev: https://docs.nvidia.com/nemo/relay/dev/llms.txt
> - v0.10.0: https://docs.nvidia.com/nemo/relay/v0.10.0/llms.txt
> - v0.9.4: https://docs.nvidia.com/nemo/relay/v0.9.4/llms.txt
> - v0.8.4: https://docs.nvidia.com/nemo/relay/v0.8.4/llms.txt
> - v0.7.3: https://docs.nvidia.com/nemo/relay/v0.7.3/llms.txt
> - v0.6.0: https://docs.nvidia.com/nemo/relay/v0.6.0/llms.txt
> - v0.5.0: https://docs.nvidia.com/nemo/relay/v0.5.0/llms.txt

> 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.

# Struct LlmRequest Intercept Outcome

> Result of an LLM request intercept that can schedule lifecycle marks.

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 />

Result of an LLM request intercept that can schedule lifecycle marks.

## Fields

### `request: LlmRequest`

Rewritten provider request when no request codec is active.

With a request codec, callbacks may rewrite `headers`, but `content` is read-only and provider-body changes must be made through [`Self::annotated_request`](/reference/api/rust-library-reference/nemo-relay-worker/struct-llmrequestinterceptoutcome).

### `annotated_request: Option<AnnotatedLlmRequest>`

Optional normalized request annotation to carry forward.

This is required and authoritative for provider content when a request codec is active. It remains optional when no request codec is active.

### `pending_marks: Vec<PendingMarkSpec>`

Ordered marks to emit after Relay creates and starts the LLM scope.

### `optimization_contributions: Vec<LlmOptimizationContribution>`

Ordered plugin-neutral optimization evidence for this LLM call.

## Implementations

### `impl LlmRequestInterceptOutcome`

<pre />

#### `new`

<pre />

Create an outcome without pending marks.

#### `with_pending_mark`

<pre />

Append one pending mark while preserving interceptor order.

#### `with_optimization_contribution`

<pre />

Append one optimization contribution while preserving interceptor order.

## Trait Implementations

### `impl Clone for LlmRequestInterceptOutcome`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for LlmRequestInterceptOutcome`

<pre />

#### `fmt`

<pre />

### `impl<'de> Deserialize<'de> for LlmRequestInterceptOutcome`

<pre />

#### `deserialize`

<pre />

### `impl From<(LlmRequest, AnnotatedLlmRequest)> for LlmRequestInterceptOutcome`

<pre />

#### `from`

<pre />

### `impl From<(LlmRequest, Option<AnnotatedLlmRequest>)> for LlmRequestInterceptOutcome`

<pre />

#### `from`

<pre />

### `impl From<LlmRequest> for LlmRequestInterceptOutcome`

<pre />

#### `from`

<pre />

### `impl PartialEq for LlmRequestInterceptOutcome`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl Serialize for LlmRequestInterceptOutcome`

<pre />

#### `serialize`

<pre />

### `impl StructuralPartialEq for LlmRequestInterceptOutcome`

<pre />