Struct InferenceProbeConfig 

pub struct InferenceProbeConfig {
    pub endpoint: String,
    pub model: String,
    pub prompt: String,
    pub max_tokens: u32,
    pub timeout_secs: u64,
    pub max_latency_ms: Option<u64>,
}

Configuration for inference probe health check

Sends a minimal completion request to verify the model can actually process requests, not just that the server is running.

Fields

endpoint: String

Endpoint for completion request

model: String

Model to probe (required)

prompt: String

Probe prompt (minimal to reduce cost/latency)

max_tokens: u32

Max tokens in response (keep minimal)

timeout_secs: u64

Timeout for probe request in seconds

max_latency_ms: Option<u64>

Mark unhealthy if probe latency exceeds this threshold (ms)

Trait Implementations

impl Clone for InferenceProbeConfig

fn clone(&self) -> InferenceProbeConfig

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for InferenceProbeConfig

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for InferenceProbeConfig

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl PartialEq for InferenceProbeConfig

fn eq(&self, other: &InferenceProbeConfig) -> 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 Serialize for InferenceProbeConfig

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl Eq for InferenceProbeConfig

impl StructuralPartialEq for InferenceProbeConfig