Struct LlmRequest 

pub struct LlmRequest {

    pub model: Option<String>,
    pub instructions: Vec<InstructionBlock>,
    pub messages: Vec<Message>,
    pub temporary_note_count: usize,
    pub is_compaction: bool,
    pub has_compaction: bool,
    pub tools: Vec<Tool>,
    pub tool_choice: Option<ToolChoice>,
    pub sampling: SamplingParams,
    pub output: OutputParams,
    pub reasoning: ReasoningParams,
    pub stream: bool,
    pub extensions: ProviderExtensions,
    pub preservation: PreservationMetadata,
}

Normalized request representation shared by Switchyard components.

Fields

model: Option<String>

Model currently addressed by the request.

This initially contains the name supplied by the inbound client. A routing host may replace it with the selected target before serving the request.

instructions: Vec<InstructionBlock>

System and developer instructions separated from conversation turns.

messages: Vec<Message>

Ordered conversation messages.

temporary_note_count: usize

This request-local count tracks temporary notes appended after the caller’s conversation. The HTTP client uses it to choose a cache breakpoint before the notes, subject to provider support, caller policy, marker limits, and an eligible prefix. Rust moves and clones retain the count. Serialization omits the count, and deserialization resets it to zero. Note text and preserved provider bodies remain serialized.

is_compaction: bool

Whether this request performs compaction or resumes from a summary.

has_compaction: bool

Whether the history contains a recognized compaction marker.

tools: Vec<Tool>

Tools available to the model.

tool_choice: Option<ToolChoice>

Policy controlling model tool selection.

sampling: SamplingParams

Common sampling controls.

output: OutputParams

Output budget and shape controls.

reasoning: ReasoningParams

Reasoning controls.

stream: bool

Whether the caller requested a streamed response.

extensions: ProviderExtensions

Provider fields without first-class normalized equivalents.

preservation: PreservationMetadata

Exact provider bodies used by codecs for lossless same-format round trips. This is separate from a host’s optional Request::raw_request.

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<(), Error>

Formats the value using the given formatter.

impl Default for LlmRequest

fn default() -> LlmRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for LlmRequest

where LlmRequest: Default,

fn deserialize<__D>( __deserializer: __D, ) -> Result<LlmRequest, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for LlmRequest

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for LlmRequest

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for LlmRequest