Enum LlmError 

#[non_exhaustive]
pub enum LlmError {
    InvalidRequest(String),
    Auth(String),
    RateLimited {
        retry_after: Option<Duration>,
        message: String,
    },
    Provider {
        status: u16,
        message: String,
    },
    Transport(String),
    Timeout,
    Serialization(String),
    Stream(String),
    BudgetExceeded(String),
    Tool {
        tool: String,
        message: String,
    },
    Unsupported(String),
    AllProvidersFailed(Vec<LlmError>),
    Other(String),
}

The single error type returned by every llmkit operation.

Variants (Non-exhaustive)

Non-exhaustive enums could have additional variants added in future. Therefore, when matching against variants of non-exhaustive enums, an extra wildcard arm must be added to account for any future variants.

InvalidRequest(String)

Request rejected before sending (missing model, empty messages, …).

Auth(String)

Authentication failed (missing or invalid API key).

RateLimited

Provider returned HTTP 429.

Fields

retry_after: Option<Duration>

Suggested delay before retrying, if provided.

message: String

Provider message.

Provider

Provider returned a non-success status with a body.

Fields

status: u16

HTTP status code.

message: String

Extracted message or body.

Transport(String)

Network / transport failure.

Timeout

Request exceeded the configured timeout.

Serialization(String)

Failed to (de)serialize a body.

Stream(String)

Error while parsing or driving a streaming response.

BudgetExceeded(String)

A configured budget (e.g. session cost cap) was exceeded.

Tool

A tool invocation failed during execution.

Fields

tool: String

Tool name.

message: String

Handler error message.

Unsupported(String)

Capability not supported by this provider.

AllProvidersFailed(Vec<LlmError>)

Every provider in a fallback chain failed.

Other(String)

Catch-all.

Implementations

impl LlmError

pub fn is_retryable(&self) -> bool

Whether retrying might succeed. Used by the retry layer.

pub fn invalid(msg: impl Display) -> Self

Construct an LlmError::InvalidRequest.

pub fn serde(msg: impl Display) -> Self

Construct an LlmError::Serialization.

Trait Implementations

impl Debug for LlmError

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

Formats the value using the given formatter.

impl Display for LlmError

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

Formats the value using the given formatter.

impl Error for LlmError

fn source(&self) -> Option<&(dyn Error + 'static)>

Returns the lower-level source of this error, if any.

fn description(&self) -> &str

👎Deprecated since 1.42.0:

use the Display impl or to_string()

fn cause(&self) -> Option<&dyn Error>

👎Deprecated since 1.33.0:

replaced by Error::source, which can support downcasting

fn provide<'a>(&'a self, request: &mut Request<'a>)

🔬This is a nightly-only experimental API. (error_generic_member_access)

Provides type-based access to context intended for error reports.

impl From<Error> for LlmError

fn from(e: Error) -> Self

Converts to this type from the input type.