Struct LLMRequest 

pub struct LLMRequest {
    pub messages: Vec<Message>,
    pub system_prompt: Option<String>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub model: String,
    pub max_tokens: Option<u32>,
    pub temperature: Option<f32>,
    pub stream: bool,
    pub tool_choice: Option<ToolChoice>,
    pub parallel_tool_calls: Option<bool>,
    pub parallel_tool_config: Option<ParallelToolConfig>,
    pub reasoning_effort: Option<String>,
}

Universal LLM request structure

Fields

messages: Vec<Message>

system_prompt: Option<String>

tools: Option<Vec<ToolDefinition>>

model: String

max_tokens: Option<u32>

temperature: Option<f32>

stream: bool

tool_choice: Option<ToolChoice>

Tool choice configuration based on official API docs Supports: “auto” (default), “none”, “any”, or specific tool selection

parallel_tool_calls: Option<bool>

Whether to enable parallel tool calls (OpenAI specific)

parallel_tool_config: Option<ParallelToolConfig>

Parallel tool use configuration following Anthropic best practices

reasoning_effort: Option<String>

Reasoning effort level for models that support it (low, medium, high) Applies to: Claude, GPT-5, Gemini, Qwen3, DeepSeek with reasoning capability

Trait Implementations

impl Clone for LLMRequest

fn clone(&self) -> LLMRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LLMRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for LLMRequest

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for LLMRequest

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.