Enum GraphOutput 

pub enum GraphOutput {
    Reasoning {
        id: String,
        content: String,
    },
    Message {
        id: String,
        content: String,
        tool_calls: Option<Vec<ToolCall>>,
    },
}

Graph output items from LLM execution

Represents structured outputs that can be persisted and traced separately. This is distinct from praxis_llm::openai::OutputItem which is the raw API format.

Variants

Reasoning

Reasoning output from models like GPT-5, o1

Fields

id: String

content: String

Message

Regular message output

Fields

id: String

content: String

tool_calls: Option<Vec<ToolCall>>

Implementations

impl GraphOutput

pub fn reasoning(id: impl Into<String>, content: impl Into<String>) -> Self

pub fn message(id: impl Into<String>, content: impl Into<String>) -> Self

pub fn message_with_tools( id: impl Into<String>, content: impl Into<String>, tool_calls: Vec<ToolCall>, ) -> Self

pub fn id(&self) -> &str

pub fn content(&self) -> &str

Trait Implementations

impl Clone for GraphOutput

fn clone(&self) -> GraphOutput

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for GraphOutput

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

Formats the value using the given formatter.