Struct ModelFamily 

pub struct ModelFamily {

    pub slug: String,
    pub family: String,
    pub provider: Provider,
    pub context_window: Option<i64>,
    pub auto_compact_token_limit: Option<i64>,
    pub supports_reasoning_summaries: bool,
    pub default_reasoning_effort: Option<ReasoningEffortLevel>,
    pub supports_parallel_tool_calls: bool,
    pub needs_special_apply_patch_instructions: bool,
    pub shell_type: ShellToolType,
    pub truncation_policy: TruncationPolicy,
    pub experimental_supported_tools: Vec<String>,
    pub effective_context_window_percent: i64,
    pub support_verbosity: bool,
    pub supports_tool_use: bool,
    pub supports_streaming: bool,
    pub supports_thinking: bool,
}

A model family groups models that share certain characteristics.

Fields

slug: String

The full model slug used to derive this model family

family: String

The model family name (e.g., “gemini-2.5”, “claude-opus”)

provider: Provider

The provider this model belongs to

context_window: Option<i64>

Maximum supported context window, if known

auto_compact_token_limit: Option<i64>

Token threshold for automatic compaction

supports_reasoning_summaries: bool

Whether the model supports reasoning summaries

default_reasoning_effort: Option<ReasoningEffortLevel>

Default reasoning effort for this model family

supports_parallel_tool_calls: bool

Whether this model supports parallel tool calls

needs_special_apply_patch_instructions: bool

Whether the model needs special apply_patch instructions

shell_type: ShellToolType

Preferred shell tool type for this model family

truncation_policy: TruncationPolicy

Truncation policy for model output

experimental_supported_tools: Vec<String>

Names of experimental tools supported by this model family

effective_context_window_percent: i64

Percentage of context window considered usable for inputs

support_verbosity: bool

Whether the model supports verbosity settings

supports_tool_use: bool

Whether the model supports tool use

supports_streaming: bool

Whether the model supports streaming

supports_thinking: bool

Whether the model supports thinking/reasoning output

Implementations

impl ModelFamily

pub fn new( slug: impl Into<String>, family: impl Into<String>, provider: Provider, ) -> Self

Create a new model family with the given slug

pub fn auto_compact_token_limit(&self) -> Option<i64>

Get the auto-compact token limit, computing a default if not set

pub fn get_model_slug(&self) -> &str

Get the model slug

pub fn supports_feature(&self, feature: &str) -> bool

Check if this family supports a specific feature

Trait Implementations

impl Clone for ModelFamily

fn clone(&self) -> ModelFamily

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelFamily

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

Formats the value using the given formatter.

impl Default for ModelFamily

fn default() -> Self

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelFamily

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelFamily

fn eq(&self, other: &ModelFamily) -> 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 Serialize for ModelFamily

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 ModelFamily