Struct ModelProfile 

pub struct ModelProfile {

    pub name: String,
    pub family: String,
    pub description: Option<String>,
    pub release_date: Option<String>,
    pub last_updated: Option<String>,
    pub attachment: bool,
    pub reasoning: bool,
    pub temperature: bool,
    pub knowledge: Option<String>,
    pub tool_call: bool,
    pub structured_output: bool,
    pub open_weights: bool,
    pub cost: Option<ModelCost>,
    pub limits: Option<ModelLimits>,
    pub modalities: Option<ModelModalities>,
    pub reasoning_effort: Option<ReasoningEffortConfig>,
    pub speed: Option<SpeedConfig>,
    pub verbosity: Option<VerbosityConfig>,
    pub tool_search: bool,
    pub supported_parameters: Vec<String>,
    pub supports_phases: bool,
    pub supports_server_compaction: bool,
    pub decisions: Option<DecisionModelProfile>,
}

LLM Model Profile describing model capabilities Based on models.dev structure (https://models.dev/api.json)

The registry of profiles lives in crate::model_profile_data::profiles; retired models are dropped from it as vendors sunset them.

Fields

name: String

Display name of the model

family: String

Model family (e.g., “gpt-5.6-sol”, “claude-sonnet-5”)

description: Option<String>

Short human-readable description of the model’s strengths and intended use

release_date: Option<String>

Release date (YYYY-MM-DD format)

last_updated: Option<String>

Last updated date (YYYY-MM-DD format)

attachment: bool

Whether the model supports file/image attachments

reasoning: bool

Whether the model has reasoning/chain-of-thought capabilities

temperature: bool

Whether temperature control is supported

knowledge: Option<String>

Knowledge cutoff date (YYYY-MM-DD format)

tool_call: bool

Whether the model supports tool/function calling

structured_output: bool

Whether the model supports structured output (JSON mode)

open_weights: bool

Whether the model has open weights

cost: Option<ModelCost>

Cost per million tokens

limits: Option<ModelLimits>

Token limits

modalities: Option<ModelModalities>

Supported modalities

reasoning_effort: Option<ReasoningEffortConfig>

Reasoning effort configuration (for reasoning models)

speed: Option<SpeedConfig>

Speed (service tier) configuration, for models served with selectable latency/price tiers (OpenAI service_tier).

verbosity: Option<VerbosityConfig>

Verbosity configuration, for models that expose output-length control (OpenAI verbosity).

tool_search: bool

Whether the model supports tool_search (deferred tool loading). When true, the driver can use namespaces and defer_loading to reduce token usage for large tool sets. Currently supported by GPT-5.4 and newer.

supported_parameters: Vec<String>

Provider-advertised request parameters supported by this model.

supports_phases: bool

Whether the model supports native execution phases (“commentary” / “final_answer”). When true, the driver sends the phase field on assistant messages in the wire format. Currently supported by GPT-5.4 and newer via OpenAI Responses API.

supports_server_compaction: bool

Whether the direct provider API supports threshold server-side compaction.

This is an explicit rollout control. Unknown models and provider surfaces that do not opt in remain disabled.

decisions: Option<DecisionModelProfile>

Typed semantics when this profile describes a decision model.

Implementations

impl ModelProfile

pub fn supports_parameter(&self, parameter: &str) -> bool

Whether this profile advertises a provider request parameter.

impl ModelProfile

pub fn minimal(name: impl Into<String>) -> Self

Minimal metadata for a declared service with otherwise unknown capabilities.

Trait Implementations

impl Clone for ModelProfile

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelProfile

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelProfile

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelProfile

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ModelProfile

fn serialize<__S>(&self, __serializer: __S) -> Result<__S::Ok, __S::Error>

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelProfile