Struct AnnotatedLlmRequest 

pub struct AnnotatedLlmRequest {

    pub messages: Vec<Message>,
    pub instructions: Option<MessageContent>,
    pub model: Option<String>,
    pub params: Option<GenerationParams>,
    pub tools: Option<Vec<ToolDefinition>>,
    pub tool_choice: Option<ToolChoice>,
    pub store: Option<bool>,
    pub previous_response_id: Option<String>,
    pub truncation: Option<Value>,
    pub reasoning: Option<Value>,
    pub include: Option<Value>,
    pub user: Option<String>,
    pub metadata: Option<Value>,
    pub service_tier: Option<String>,
    pub parallel_tool_calls: Option<bool>,
    pub max_output_tokens: Option<u64>,
    pub max_tool_calls: Option<u64>,
    pub top_logprobs: Option<u64>,
    pub stream: Option<bool>,
    pub api_specific: Option<ApiSpecificRequest>,
    pub extra: Map<String, Value>,
}

Structured view of an LLM request, produced by a Codec from opaque LlmRequest content.

The extra field captures unknown future top-level keys. Modeled provider-specific controls belong in AnnotatedLlmRequest::api_specific.

Fields

messages: Vec<Message>

Parsed conversation messages.

instructions: Option<MessageContent>

Provider-level instructions that are not part of the conversation array.

Anthropic encodes this as system; OpenAI Responses uses instructions.

model: Option<String>

Model identifier (e.g., "gpt-4", "claude-sonnet-4-20250514").

params: Option<GenerationParams>

Common generation parameters, normalized.

tools: Option<Vec<ToolDefinition>>

Tool definitions (function schemas) available to the model.

tool_choice: Option<ToolChoice>

Tool choice control.

store: Option<bool>

OpenAI Responses: whether to persist response state server-side.

previous_response_id: Option<String>

OpenAI Responses: prior response to continue from.

truncation: Option<Value>

OpenAI Responses: context truncation behavior.

reasoning: Option<Value>

OpenAI Responses: reasoning configuration object.

include: Option<Value>

OpenAI Responses: include filter for additional output/state items.

user: Option<String>

OpenAI user identifier.

metadata: Option<Value>

OpenAI metadata map/object.

service_tier: Option<String>

OpenAI service tier preference.

parallel_tool_calls: Option<bool>

OpenAI tool parallelism toggle.

max_output_tokens: Option<u64>

OpenAI Responses max output token limit.

max_tool_calls: Option<u64>

OpenAI Responses max tool calls.

top_logprobs: Option<u64>

OpenAI logprob fanout count.

stream: Option<bool>

OpenAI streaming toggle.

api_specific: Option<ApiSpecificRequest>

API-specific request data that does not have portable semantics.

extra: Map<String, Value>

Unknown future top-level fields.

Baseline-aware codecs remove deleted keys and overlay changed or added keys without rebuilding untouched provider JSON.

Implementations

impl AnnotatedLlmRequest

pub fn system_prompt(&self) -> Option<&str>

Extract the text content of the first system message, if any.

For MessageContent::Text, returns the string directly. For MessageContent::Parts, returns the text of the first ContentPart::Text part.

pub fn last_user_message(&self) -> Option<&str>

Get the text content of the last user message, if any.

Searches messages in reverse order and returns the first user message found. For MessageContent::Parts, returns the text of the first ContentPart::Text part.

pub fn has_tool_calls(&self) -> bool

Check if any assistant message in the conversation contains tool calls.

Returns true if at least one Message::Assistant variant has a non-empty tool_calls field.

Trait Implementations

impl Clone for AnnotatedLlmRequest

fn clone(&self) -> AnnotatedLlmRequest

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for AnnotatedLlmRequest

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

Formats the value using the given formatter.

impl Default for AnnotatedLlmRequest

fn default() -> AnnotatedLlmRequest

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for AnnotatedLlmRequest

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for AnnotatedLlmRequest

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for AnnotatedLlmRequest

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 AnnotatedLlmRequest