Enum ModelRuntimeError 

pub enum ModelRuntimeError {
    ModelNotFound(String),
    ModelLoading,
    AdmissionTimeout(String),
    SpawnFailed(String),
    HealthCheckFailed(String),
    ModelFileNotFound(String),
    PinnedModelMismatch {
        expected: String,
        requested: String,
    },
    Internal(String),
}

Errors that can occur during model runtime operations.

Variants

ModelNotFound(String)

The requested model was not found in the catalog.

ModelLoading

A model is currently loading; try again later. Callers should return 503 Service Unavailable.

AdmissionTimeout(String)

Retryable: the request sat in the admission queue past its deadline without ever reaching the front.

Reaching this means the GPU stayed continuously occupied by other models for longer than a request can reasonably wait — not that a collision was mishandled. The queue’s own fairness bounds make it rare; when it does happen the caller gets a 503 with Retry-After and control of its own backoff.

SpawnFailed(String)

Failed to spawn the model server process.

HealthCheckFailed(String)

The model server failed its health check.

ModelFileNotFound(String)

The model file was not found on disk.

PinnedModelMismatch

A model other than the pinned one was requested.

Only reachable in pinned mode (gglib serve <model>), which exists to give single-model clients — VS Code Copilot’s BYOK endpoint, for one — an endpoint that never switches models underneath them. Swapping to the requested model would defeat that guarantee, so the request is refused rather than served.

Fields

expected: String

The model this server was pinned to at startup.

requested: String

The model the caller asked for.

Internal(String)

Internal error during runtime operations.

Implementations

impl ModelRuntimeError

pub const fn is_retryable(&self) -> bool

Returns true if this error indicates a temporary condition where retrying may succeed.

pub const fn suggested_status_code(&self) -> u16

Returns a suggested HTTP status code for this error.

Trait Implementations

impl Clone for ModelRuntimeError

fn clone(&self) -> ModelRuntimeError

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ModelRuntimeError

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

Formats the value using the given formatter.

impl Display for ModelRuntimeError

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

Formats the value using the given formatter.

impl Error for ModelRuntimeError

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<&ModelRuntimeError> for RuntimeErrorEnvelope

fn from(err: &ModelRuntimeError) -> Self

Converts to this type from the input type.