Enum LlmStreamEvent 

pub enum LlmStreamEvent {
    ContentChunk(String),
    Reasoning(String),
    ToolCallChunk {
        id: String,
        name: Option<String>,
        arguments: String,
    },
    ToolCall(ToolCall),
    Usage(TokenUsage),
}

An event emitted during a streaming LLM response.

Variants

ContentChunk(String)

Reasoning(String)

A chunk of reasoning-model “thinking” text, distinct from the answer content (e.g. OpenRouter’s reasoning / Zhipu’s reasoning_content).

ToolCallChunk

Fields

id: String

name: Option<String>

arguments: String

ToolCall(ToolCall)

Usage(TokenUsage)

What the request cost, as reported by the provider. Terminal: it arrives in the final chunk, after the content. Absent on endpoints that do not report usage while streaming — see OpenAiConfig::stream_usage.

Trait Implementations

impl Clone for LlmStreamEvent

fn clone(&self) -> LlmStreamEvent

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for LlmStreamEvent

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

Formats the value using the given formatter.