Enum LlmError 

#[non_exhaustive]
pub enum LlmError {
    RateLimit {
        retry_after: Option<Duration>,
    },
    QuotaExceeded {
        detail: String,
    },
    ContextLengthExceeded {
        max_tokens: u32,
    },
    AuthFailed {
        detail: String,
    },
    ModelNotFound(String),
    ModelUnavailable(String),
    ProviderUnavailable(String),
    ContentFiltered {
        detail: String,
    },
    Network(String),
    Timeout(Duration),
    InvalidRequest(String),
    UnsupportedCapability(String),
    Protocol(String),
    StreamInterrupted(String),
    Provider(String),
}

Error taxonomy for LLM component operations.

Provider-agnostic — no provider-specific variants. Use the Provider(String) catch-all for provider-specific errors; the constructor truncates messages to 200 bytes with UTF-8 safety.

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.

RateLimit

Rate limited by provider; optionally carries a retry-after duration.

Fields

retry_after: Option<Duration>

Optional duration to wait before retrying.

QuotaExceeded

Usage quota exceeded (e.g., billing limit reached).

Fields

detail: String

Human-readable detail.

ContextLengthExceeded

Request exceeds provider context window.

Fields

max_tokens: u32

Maximum allowed tokens for the model.

AuthFailed

Authentication / authorization failure.

Fields

detail: String

Human-readable detail.

ModelNotFound(String)

Requested model does not exist.

ModelUnavailable(String)

Model is temporarily unavailable (e.g., overloaded).

ProviderUnavailable(String)

Provider endpoint is unreachable or returning server errors.

ContentFiltered

Response was blocked by the provider’s content safety policy.

Fields

detail: String

Human-readable detail.

Network(String)

Transient network error (connection reset, DNS failure, etc.).

Timeout(Duration)

Request exceeded the configured timeout.

InvalidRequest(String)

Request was malformed or violated provider constraints.

UnsupportedCapability(String)

The operation is not supported by this provider.

Protocol(String)

Response could not be decoded or parsed.

StreamInterrupted(String)

Stream was terminated before completion.

Provider(String)

Provider-specific error (catch-all). Message is automatically truncated to 200 bytes with UTF-8 safety via LlmError::provider.

Implementations

impl LlmError

pub fn provider(msg: impl Into<String>) -> Self

Create a provider error with automatic message truncation.

The message is truncated to 200 bytes at a UTF-8 safe boundary, preventing unbounded error messages from propagating.

Trait Implementations

impl Clone for LlmError

fn clone(&self) -> LlmError

Returns a duplicate of the value.

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

Performs copy-assignment from source.

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<LlmError> for CamelError

fn from(e: LlmError) -> Self

Converts to this type from the input type.