> 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 full documentation content, see https://docs.nvidia.com/nemo/relay/llms-full.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nemo/relay/_mcp/server.

# Struct Cache Policy

> Policy controlling when ACG outputs can be cached and reused.

Generated from `cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi`.

<pre />

Policy controlling when ACG outputs can be cached and reused.

## Fields

### `min_stability_score: f64`

Minimum stability score required before caching is allowed.

### `min_evidence_count: u32`

Minimum number of observations required before caching is allowed.

### `default_sharing_scope: SharingScope`

Default sharing scope used for cached artifacts.

### `warm_first_enabled: bool`

Whether warm-first coordination is enabled for eligible fan-outs.

### `max_fanout_for_warm_first: Option<u32>`

Optional upper bound on fan-out width for warm-first coordination.

## Trait Implementations

### `impl Clone for CachePolicy`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for CachePolicy`

<pre />

#### `fmt`

<pre />

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

<pre />

#### `deserialize`

<pre />

### `impl PartialEq for CachePolicy`

<pre />

#### `eq`

<pre />

#### `ne`

<pre />

### `impl Serialize for CachePolicy`

<pre />

#### `serialize`

<pre />

### `impl StructuralPartialEq for CachePolicy`

<pre />