Struct CompletionRequest 

pub struct CompletionRequest {

    pub messages: Vec<Message>,
    pub model: String,
    pub max_tokens: Option<u32>,
    pub temperature: Option<f32>,
    pub top_p: Option<f32>,
    pub stream: Option<bool>,
    pub n: Option<u32>,
    pub stop: Option<Vec<String>>,
    pub presence_penalty: Option<f32>,
    pub frequency_penalty: Option<f32>,
    pub user: Option<String>,
    pub response_format: Option<ResponseFormat>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub tool_choice: Option<ToolChoice>,
    pub instructions: Option<String>,
    pub previous_response_id: Option<String>,
    pub store: Option<bool>,
}

A completion request to an LLM provider.

Fields

messages: Vec<Message>

List of messages in the conversation

model: String

Model identifier (e.g., “gpt-4”, “claude-3-opus”)

max_tokens: Option<u32>

Maximum tokens to generate

temperature: Option<f32>

Sampling temperature (0.0-2.0)

top_p: Option<f32>

Nucleus sampling threshold (0.0-1.0)

stream: Option<bool>

Enable streaming responses

n: Option<u32>

Number of completions to generate

stop: Option<Vec<String>>

Stop sequences

presence_penalty: Option<f32>

Presence penalty (-2.0 to 2.0)

frequency_penalty: Option<f32>

Frequency penalty (-2.0 to 2.0)

user: Option<String>

User identifier (for abuse detection)

response_format: Option<ResponseFormat>

Response format for structured outputs (OpenAI only)

tools: Option<Vec<ToolDefinition>>

Tool definitions for tool calling.

tool_choice: Option<ToolChoice>

Tool choice configuration.

instructions: Option<String>

System instructions (Responses API)

previous_response_id: Option<String>

Previous response ID for multi-turn (Responses API)

store: Option<bool>

Whether to store the response (Responses API)

Implementations

impl CompletionRequest

pub fn new(model: impl Into<String>) -> Self

Create a new request with the given model and default fields.

pub fn messages(self, messages: Vec<Message>) -> Self

Set messages on the request (builder-style).

pub fn instructions(self, instructions: impl Into<String>) -> Self

Set system instructions (Responses API).

pub fn previous_response_id(self, id: impl Into<String>) -> Self

Set previous response ID for multi-turn (Responses API).

pub fn store(self, store: bool) -> Self

Set whether to store the response (Responses API).

pub fn builder() -> CompletionRequestBuilder

Create a new builder.

Example

use simple_agent_type::request::CompletionRequest;
use simple_agent_type::message::Message;

let request = CompletionRequest::builder()
    .model("gpt-4")
    .message(Message::user("Hello!"))
    .build()
    .unwrap();

pub fn validate(&self) -> Result<()>

Validate the request.

Validation Rules

• Messages: 1-1000 items, each < 1MB
• Model: alphanumeric + -_./ only
• Temperature: 0.0-2.0
• Top_p: 0.0-1.0
• No null bytes (security)

Trait Implementations

impl Clone for CompletionRequest

fn clone(&self) -> CompletionRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for CompletionRequest

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for CompletionRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for CompletionRequest

fn eq(&self, other: &CompletionRequest) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl Serialize for CompletionRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for CompletionRequest