Module types 

Core LLM request/response types. Core types for the LLM client module.

Structs

ChatMessage

A single message in a chat conversation.

LLMRequest

A chat completion request to an LLM provider.

LLMRequestBuilder

Builder for constructing LLMRequest instances with a fluent API.

LLMResponse

A chat completion response from an LLM provider.

ModelConfig

Configuration for a specific LLM model and provider.

ObservabilityContext

Vendor-neutral observability context carried on an LLMRequest.

ReasoningConfig

Reasoning-model controls for a chat completion request.

TokenUsage

Token usage statistics from an LLM response.

Enums

ContentPart

A single content part in a multimodal chat message.

MessageRole

Role of a message sender in a chat conversation.

ReasoningEffort

Reasoning effort for reasoning models (OpenAI reasoning_effort).

ReasoningSummary

Summary style for reasoning models (Responses-API reasoning.summary, also accepted inside OpenRouter’s reasoning object).

ResponseFormat

Desired output format for the LLM response.

StreamEvent

A single event in an LLM streaming response.

Verbosity

Verbosity of the model’s response (OpenAI verbosity).

Type Aliases

LLMStream

Type alias for a boxed streaming response.