Enum ModelError 

pub enum ModelError {
    RateLimit,
    ContextTooLong,
    InvalidRequest(String),
    ServerError(String),
    Timeout,
    Unavailable,
}

Errors that can be returned by a model inference call.

Variants

RateLimit

HTTP 429 / token-bucket exhausted.

ContextTooLong

Prompt + completion would exceed the model’s context window.

InvalidRequest(String)

The request itself was malformed (bad parameters, etc.).

ServerError(String)

The provider returned a 5xx or equivalent error.

Timeout

No response received within the allowed time window.

Unavailable

The model endpoint is temporarily unavailable.

Implementations

impl ModelError

pub fn is_retryable(&self) -> bool

Returns true for errors that are worth retrying on the same model.

pub fn suggests_fallback(&self) -> bool

Returns true for errors that should trigger a move to the next model in the chain.

Trait Implementations

impl Clone for ModelError

fn clone(&self) -> ModelError

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelError

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

Formats the value using the given formatter.

impl PartialEq for ModelError

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