Struct LlmCacheKeyInput 

pub struct LlmCacheKeyInput {
    pub model: String,
    pub messages: Vec<Value>,
    pub tools: Vec<Value>,
    pub config: Option<()>,
}

Input for LLM cache key generation

Contains the parameters that influence cache key generation for LLM calls.

Examples

use juncture_tracing::types::LlmCacheKeyInput;
use serde_json::json;

let input = LlmCacheKeyInput {
    model: "gpt-4".to_string(),
    messages: vec![json!({"role": "user", "content": "Hello"})],
    tools: vec![],
    config: None,
};

Fields

model: String

Model name

messages: Vec<Value>

Messages in the conversation

tools: Vec<Value>

Tools available in the call

config: Option<()>

Optional call configuration

Reserved for future use with CallOptions type. Currently unused but kept for API compatibility.

Trait Implementations

impl Clone for LlmCacheKeyInput

fn clone(&self) -> LlmCacheKeyInput

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for LlmCacheKeyInput

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.