Struct ModelSettings 

pub struct ModelSettings {

    pub max_tokens: Option<u32>,
    pub temperature: Option<f64>,
    pub top_p: Option<f64>,
    pub top_k: Option<u32>,
    pub timeout_ms: Option<u64>,
    pub parallel_tool_calls: Option<bool>,
    pub tool_choice: Option<ToolChoice>,
    pub seed: Option<u64>,
    pub stop_sequences: Vec<String>,
    pub presence_penalty: Option<f64>,
    pub frequency_penalty: Option<f64>,
    pub logit_bias: BTreeMap<String, i32>,
    pub thinking: Option<ThinkingSettings>,
    pub service_tier: Option<ServiceTier>,
    pub provider_replay: Option<ProviderReplaySettings>,
    pub provider_settings: ProviderSettings,
    pub provider_options: Option<Value>,
    pub extra_headers: BTreeMap<String, String>,
    pub extra_body: Map<String, Value>,
}

Per-request generation configuration.

Fields

max_tokens: Option<u32>

Maximum generated tokens.

temperature: Option<f64>

Sampling temperature.

top_p: Option<f64>

Nucleus sampling.

top_k: Option<u32>

Top-k sampling.

timeout_ms: Option<u64>

Request timeout in milliseconds.

This is the Rust transport-friendly representation of a cross-provider timeout model setting.

parallel_tool_calls: Option<bool>

Allow multiple tool calls in one response.

tool_choice: Option<ToolChoice>

Tool forcing or availability policy.

seed: Option<u64>

Best-effort deterministic seed.

stop_sequences: Vec<String>

Stop strings.

presence_penalty: Option<f64>

Presence penalty.

frequency_penalty: Option<f64>

Frequency penalty.

logit_bias: BTreeMap<String, i32>

Token-level logit bias.

thinking: Option<ThinkingSettings>

Reasoning or thinking controls.

service_tier: Option<ServiceTier>

Latency/cost tier.

provider_replay: Option<ProviderReplaySettings>

Provider replay and server-side state controls.

provider_settings: ProviderSettings

Typed provider-specific settings.

provider_options: Option<Value>

Provider-specific raw settings escape hatch.

extra_headers: BTreeMap<String, String>

Request headers merged after adapter defaults and before request-level overrides.

extra_body: Map<String, Value>

Extra JSON object merged into the top-level request body.

Implementations

impl ModelSettings

pub fn merge(&self, overlay: &Self) -> Self

Merge two settings values field by field, taking values from overlay when present.

Trait Implementations

impl Clone for ModelSettings

fn clone(&self) -> ModelSettings

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelSettings

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

Formats the value using the given formatter.

impl Default for ModelSettings

fn default() -> ModelSettings

Returns the “default value” for a type.

impl<'de> Deserialize<'de> for ModelSettings

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for ModelSettings

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ModelSettings

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 ModelSettings