Struct LlmRequest 

pub struct LlmRequest {
    pub model: Option<String>,
    pub instructions: Vec<InstructionBlock>,
    pub messages: Vec<Message>,
    pub tools: Vec<ToolDefinition>,
    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 requested by the inbound client.

instructions: Vec<InstructionBlock>

System and developer instructions separated from conversation turns.

messages: Vec<Message>

Ordered conversation messages.

tools: Vec<ToolDefinition>

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.

Implementations

impl LlmRequest

pub fn seal_preservation(&mut self)

Records the current shape of this request against its preserved bodies.

Codecs call this once decoding is complete. Until it is called the preserved bodies are treated as stale, so an un-sealed request always re-encodes from normalized fields.

pub fn preserved_request_is_current(&self) -> bool

Whether the preserved bodies still describe this request.

Returns false once anything has changed since Self::seal_preservation — a routing algorithm inserting a tier system prompt, appending a handoff note, rewriting the model — which is what stops a same-format hop from replaying a body that predates the change.

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 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<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for LlmRequest

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

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 LlmRequest