Struct ChatRequest 

pub struct ChatRequest {
    pub messages: Vec<ChatMessage>,
    pub tools: Vec<Value>,
    pub reasoning: Option<ReasoningConfig>,
    pub response_format: Option<ResponseFormat>,
    pub model: Option<String>,
}

Unified chat request format.

Fields

messages: Vec<ChatMessage>

Message list (supports multimodal content)

tools: Vec<Value>

Available tools

reasoning: Option<ReasoningConfig>

Reasoning/thinking configuration

response_format: Option<ResponseFormat>

Response format configuration

model: Option<String>

Optional model override.

• None: Use the provider’s default model
• Some(name): Use the specified model for this request

This enables multi-model routing: the application can set different models for different scenes (e.g., “lite” for sub-agents, “advanced” for architecture decisions) without creating multiple providers.

Implementations

impl ChatRequest

pub fn new(messages: Vec<ChatMessage>) -> ChatRequest

Create a simple text request.

pub fn with_model(self, model: impl Into<String>) -> ChatRequest

Set model override.

pub fn with_tools(self, tools: Vec<Value>) -> ChatRequest

Add tools.

pub fn with_reasoning(self, reasoning: ReasoningConfig) -> ChatRequest

Add reasoning configuration.

pub fn with_response_format(self, format: ResponseFormat) -> ChatRequest

Set response format.

Trait Implementations

impl Clone for ChatRequest

fn clone(&self) -> ChatRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ChatRequest

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

Formats the value using the given formatter.