Struct TaskAnalysis 

pub struct TaskAnalysis {
    pub estimated_tokens: usize,
    pub requires_reasoning: bool,
    pub requires_code_generation: bool,
    pub requires_structured_output: bool,
    pub multi_step: bool,
    pub max_latency: Option<Duration>,
    pub category: TaskCategory,
    pub requires_vision: bool,
    pub requires_audio: bool,
}

Analysis of a task for routing.

Fields

estimated_tokens: usize

Estimated input tokens.

requires_reasoning: bool

Whether the task requires complex reasoning.

requires_code_generation: bool

Whether the task requires code generation.

requires_structured_output: bool

Whether structured JSON output is required.

multi_step: bool

Whether this is a multi-step task.

max_latency: Option<Duration>

Maximum acceptable latency.

category: TaskCategory

Task category.

requires_vision: bool

Whether the task requires vision capabilities.

requires_audio: bool

Whether the task requires audio capabilities.

Implementations

impl TaskAnalysis

pub fn from_prompt(prompt: &str) -> Self

Create analysis from a prompt.

pub fn extraction(html_length: usize) -> Self

Create analysis for extraction task.

pub fn action(instruction: &str) -> Self

Create analysis for action task.

pub fn with_max_latency(self, latency: Duration) -> Self

Set max latency requirement.

pub fn to_requirements(&self) -> ModelRequirements

Convert to model requirements for the selector.

Trait Implementations

impl Clone for TaskAnalysis

fn clone(&self) -> TaskAnalysis

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for TaskAnalysis

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

Formats the value using the given formatter.

impl Default for TaskAnalysis

fn default() -> TaskAnalysis

Returns the “default value” for a type.