Struct ModelInfo 

pub struct ModelInfo {
    pub id: String,
    pub provider: ProviderId,
    pub display_name: Option<String>,
    pub description: Option<String>,
    pub created_at: Option<OffsetDateTime>,
    pub context_window: Option<usize>,
}

The per-turn steering seam, whole: the trait a host implements and every type its signatures make that host name.

Re-exported rather than wrapped, under the rule stated on CancellationToken — a mentra type basis’s surface asks a caller to write is a name basis re-exports, or the caller pins mentra in their own manifest to spell it. And like the token, a strategy is an identity rather than a value: TurnOptions::with_round_strategy hands mentra the caller’s own Arc, so a basis-owned mirror of RoundDecision would be a translation layer with opinions of its own — the opposite of a seam.

The set is exactly what implementing costs. RoundStrategy is the trait (spelled with async_trait, which basis already re-exports); RoundContext and RoundBoundary are its question; RoundDecision, RoundAdjustment, ReasoningChange and RoundToolResult are its vocabulary for answering. The last three are here because the vocabulary’s own signatures demand them: RoundDecision::inject takes ContentBlocks, RoundAdjustment::with_model a ModelInfo, and ReasoningChange::Set a ReasoningOptions — whose effort field an Effort converts into, so switching effort mid-run never names mentra’s own level enum. Metadata describing a model available from a provider.

Fields

id: String

provider: ProviderId

display_name: Option<String>

description: Option<String>

created_at: Option<OffsetDateTime>

context_window: Option<usize>

How many tokens the model accepts in one request, when the provider says so.

Most providers do not: neither Anthropic’s nor OpenAI’s model listing reports a limit, so this is None for them and a host that knows the number can set it. Gemini reports it as inputTokenLimit. It is the only thing that lets anything downstream — a compaction threshold, a context-usage report — be expressed relative to the model rather than as a constant that is wrong for most of them.

Implementations

impl ModelInfo

pub fn new(id: impl Into<String>, provider: impl Into<ProviderId>) -> ModelInfo

pub fn with_context_window(self, context_window: usize) -> ModelInfo

Returns this model with its context window set.

Trait Implementations

impl Clone for ModelInfo

fn clone(&self) -> ModelInfo

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelInfo

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for ModelInfo

fn deserialize<__D>( __deserializer: __D, ) -> Result<ModelInfo, <__D as Deserializer<'de>>::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl Eq for ModelInfo

impl From<AnthropicModel> for ModelInfo

fn from(model: AnthropicModel) -> ModelInfo

Converts to this type from the input type.

impl From<GeminiModel> for ModelInfo

fn from(model: GeminiModel) -> ModelInfo

Converts to this type from the input type.

impl PartialEq for ModelInfo

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

Equality operator ==.

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

Inequality operator !=.

impl Serialize for ModelInfo

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for ModelInfo