Struct ModelMetadata 

pub struct ModelMetadata {

    pub provider: String,
    pub model: String,
    pub cost_class: CostClass,
    pub typical_latency_ms: u32,
    pub quality: f64,
    pub has_reasoning: bool,
    pub supports_web_search: bool,
    pub data_sovereignty: DataSovereignty,
    pub compliance: ComplianceLevel,
    pub supports_multilingual: bool,
    pub context_tokens: usize,
    pub supports_tool_use: bool,
    pub supports_vision: bool,
    pub supports_structured_output: bool,
    pub supports_code: bool,
    pub country: String,
    pub region: String,
}

Model metadata for selection.

Fields

provider: String

Provider name (e.g., “anthropic”, “openai”).

model: String

Model identifier (e.g., “claude-haiku-4-5-20251001”).

cost_class: CostClass

Cost class of this model.

typical_latency_ms: u32

Typical latency in milliseconds.

quality: f64

Quality score (0.0-1.0).

has_reasoning: bool

Whether this model has strong reasoning capabilities.

supports_web_search: bool

Whether this model supports web search.

data_sovereignty: DataSovereignty

Data sovereignty region.

compliance: ComplianceLevel

Compliance level.

supports_multilingual: bool

Whether this model supports multiple languages.

context_tokens: usize

Context window size in tokens.

supports_tool_use: bool

Whether this model supports tool/function calling.

supports_vision: bool

Whether this model supports vision/images.

supports_structured_output: bool

Whether this model supports structured output (JSON mode).

supports_code: bool

Whether this model is specialized for code.

country: String

Provider’s country (ISO code, e.g., “US”, “FR”, “CN”).

region: String

Provider’s region (e.g., “US”, “EU”, “CN”, “LOCAL”).

Implementations

impl ModelMetadata

pub fn new( provider: impl Into<String>, model: impl Into<String>, cost_class: CostClass, typical_latency_ms: u32, quality: f64, ) -> Self

Creates new model metadata.

pub fn with_reasoning(self, has: bool) -> Self

Sets reasoning capability.

pub fn with_web_search(self, supports: bool) -> Self

Sets web search support.

pub fn with_data_sovereignty(self, sovereignty: DataSovereignty) -> Self

Sets data sovereignty.

pub fn with_compliance(self, compliance: ComplianceLevel) -> Self

Sets compliance level.

pub fn with_multilingual(self, supports: bool) -> Self

Sets multilingual support.

pub fn with_context_tokens(self, tokens: usize) -> Self

Sets context window size.

pub fn with_tool_use(self, supports: bool) -> Self

Sets tool/function calling support.

pub fn with_vision(self, supports: bool) -> Self

Sets vision support.

pub fn with_structured_output(self, supports: bool) -> Self

Sets structured output support.

pub fn with_code(self, supports: bool) -> Self

Sets code capability.

pub fn with_location( self, country: impl Into<String>, region: impl Into<String>, ) -> Self

Sets provider location (country and region).

pub fn satisfies(&self, requirements: &AgentRequirements) -> bool

Checks if this model satisfies the given requirements.

pub fn fitness_score(&self, requirements: &AgentRequirements) -> f64

Calculates a fitness score for matching requirements.

Higher score = better match. Considers:

• Cost efficiency (lower cost within allowed range)
• Latency efficiency (faster within allowed range)
• Quality (higher is better)

pub fn fitness_breakdown( &self, requirements: &AgentRequirements, ) -> Option<FitnessBreakdown>

Calculates a detailed fitness breakdown for matching requirements.

Returns None if the model doesn’t satisfy requirements.

pub fn rejection_reason( &self, requirements: &AgentRequirements, ) -> Option<RejectionReason>

Determines why this model was rejected for the given requirements.

Returns None if the model satisfies all requirements.

Trait Implementations

impl Clone for ModelMetadata

fn clone(&self) -> ModelMetadata

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelMetadata

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

Formats the value using the given formatter.

impl PartialEq for ModelMetadata

fn eq(&self, other: &ModelMetadata) -> 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 ModelMetadata