> 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 Response Cache Config

> Configuration for the adaptive plugin's LLM response and opt-in tool-result cache feature.

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 />

Configuration for the adaptive plugin's LLM response and opt-in tool-result cache feature.

## Fields

### `ttl_seconds: u64`

How long a stored answer stays reusable, in seconds.

### `namespace: String`

Required, non-empty trust-domain partition folded into every key.

One response-cache namespace must not span mutually untrusted tenants or upstreams. The empty default is an unconfigured sentinel rejected when the response-cache section is enabled.

### `priority: i32`

Execution-intercept priority; lower runs first/outermost (default `50`).

### `bypass_rate: f64`

Probability in `[0.0, 1.0]` of skipping the cache and running live.

### `cache_nondeterministic: bool`

Cache nondeterministic requests too. Set `false` to cache only requests explicitly pinned deterministic (`temperature` = 0) - absent or unreadable temperatures count as nondeterministic.

### `key_strategy: ResponseCacheKeyStrategy`

Typed key-derivation strategy.

### `header_allowlist: Vec<String>`

Request headers (case-insensitive) folded into the key; never auth headers.

### `backend: BackendConfig`

Storage backend selection.

### `tools: Option<ToolCacheConfig>`

Opt-in tool-result cache configuration.

## Implementations

### `impl ResponseCacheConfig`

<pre />

#### `ttl`

<pre />

TTL as a [`std::time::Duration`](https://doc.rust-lang.org/1.96.1/core/time/struct.Duration.html).

## Trait Implementations

### `impl Clone for ResponseCacheConfig`

<pre />

#### `clone`

<pre />

#### `clone_from`

<pre />

### `impl Debug for ResponseCacheConfig`

<pre />

#### `fmt`

<pre />

### `impl Default for ResponseCacheConfig`

<pre />

#### `default`

<pre />

### `impl<'de> Deserialize<'de> for ResponseCacheConfigwhere ResponseCacheConfig: Default,`

<pre />

#### `deserialize`

<pre />

### `impl EditorConfig for ResponseCacheConfig`

<pre />

#### `editor_schema`

<pre />

### `impl Serialize for ResponseCacheConfig`

<pre />

#### `serialize`

<pre />