Struct ModelSpec 

pub struct ModelSpec(/* private fields */);

A validated model selection: a single model or several alloyed models, parsed from a comma-separated provider:model list.

Implementations

impl ModelSpec

pub fn models(&self) -> &[LlmModel]

pub fn reasoning_levels(&self) -> Vec<ReasoningEffort>

Reasoning levels supported by every model in the spec.

pub fn validate_reasoning_effort( &self, effort: Option<ReasoningEffort>, ) -> Result<(), ReasoningEffortError>

pub fn clamp_reasoning_effort( &self, effort: Option<ReasoningEffort>, ) -> Option<ReasoningEffort>

The nearest effort supported by every model in the spec, or None when the spec does not support reasoning at all.

Trait Implementations

impl Clone for ModelSpec

fn clone(&self) -> ModelSpec

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelSpec

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

Formats the value using the given formatter.

impl Display for ModelSpec

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

Formats the value using the given formatter.

impl Eq for ModelSpec

impl FromStr for ModelSpec

type Err = ModelSpecError

The associated error which can be returned from parsing.

fn from_str(spec: &str) -> Result<Self, Self::Err>

Parses a string s to return a value of this type.

impl PartialEq for ModelSpec

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

Tests for self and other values to be equal, and is used by ==.

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

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for ModelSpec