Struct ChatRequest 

pub struct ChatRequest {

    pub model: String,
    pub messages: Vec<Message>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub temperature: Option<f64>,
    pub max_tokens: Option<u32>,
    pub top_p: Option<f64>,
    pub seed: Option<u64>,
    pub tool_choice: Option<ToolChoice>,
    pub stop_sequences: Option<Vec<String>>,
    pub prefill: Option<String>,
    pub reasoning: Option<ReasoningConfig>,
    pub max_reasoning_tokens: Option<u32>,
    pub extra: Option<Map<String, Value>>,
}

统一的聊天请求。

Fields

model: String

messages: Vec<Message>

tools: Option<Vec<ToolDefinition>>

temperature: Option<f64>

max_tokens: Option<u32>

top_p: Option<f64>

seed: Option<u64>

tool_choice: Option<ToolChoice>

stop_sequences: Option<Vec<String>>

prefill: Option<String>

reasoning: Option<ReasoningConfig>

推理配置 — 控制模型是否进行深度推理。

None = 不干预 Provider 默认行为 Some(Disabled) = 显式关闭推理 Some(Low/Medium/High) = 开启对应级别的推理

max_reasoning_tokens: Option<u32>

单次 LLM 调用的推理 Token 上限（可选，默认无限制）。

与 max_tokens 分离：reasoning 是模型内部推理，不计入输出预算。 透传给 Provider Adapter，由 Adapter 映射为协议特定字段。

两种语义：

• 流式: Hard limit — 达到限额当场切断 stream，省钱
• 非流式: Soft limit — response 已完整返回，事后检测并标记

Adapter 映射示例：

• DeepSeek: max_thinking_tokens
• OpenAI: 无直接对应，由 reasoning 级别间接控制
• 其他: 放入 extra 或忽略

extra: Option<Map<String, Value>>

Provider 特有参数（如 OpenAI 的 presence_penalty），由 Adapter 自行处理。

Implementations

impl ChatRequest

pub fn user_prompt(prompt: String) -> Self

便捷构造：单条用户消息

pub fn with_temperature(self, temp: f64) -> Self

pub fn with_max_tokens(self, max: u32) -> Self

pub fn with_top_p(self, top_p: f64) -> Self

pub fn with_seed(self, seed: u64) -> Self

pub fn with_model(self, model: String) -> Self

pub fn with_tools(self, tools: Vec<ToolDefinition>) -> Self

pub fn with_system_prompt(self, prompt: String) -> Self

便捷构造：单条系统消息

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

设置推理配置

pub fn with_max_reasoning_tokens(self, max: u32) -> Self

设置单次调用的推理 Token 上限

pub fn with_extra(self, extra: Map<String, Value>) -> Self

设置 Provider 特有参数

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

Formats the value using the given formatter.

impl Default for ChatRequest

fn default() -> ChatRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ChatRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Serialize for ChatRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.