Struct Cache Telemetry Event | NVIDIA NeMo Relay

Generated from cargo doc --no-deps -p nemo-relay -p nemo-relay-adaptive -p nemo-relay-ffi.

pub struct CacheTelemetryEvent {
    pub request_id: Uuid,
    pub agent_identity: AgentIdentity,
    pub cache_read_tokens: u64,
    pub cache_creation_tokens: u64,
    pub total_prompt_tokens: u64,
    pub hit_rate: f64,
    pub miss_reason: Option<CacheMissReason>,
    pub miss_diagnosis: Option<CacheMissDiagnosis>,
    pub provider: String,
    pub timestamp: DateTime<Utc>,
}

Per-call cache telemetry event.

Captures provider-agnostic cache metrics for a single LLM request. The agent_identity field cross-references the Phase 3 AgentIdentity type for per-agent grouping.

Fields

`request_id: Uuid`

Request ID this telemetry pertains to.

`agent_identity: AgentIdentity`

Identity of the agent that issued the request.

`cache_read_tokens: u64`

Number of tokens served from cache.

`cache_creation_tokens: u64`

Number of tokens written to cache.

`total_prompt_tokens: u64`

Total prompt tokens (for hit rate calculation).

`hit_rate: f64`

Computed cache hit rate [0.0, 1.0].

`miss_reason: Option<CacheMissReason>`

Reason for cache miss, if applicable.

`miss_diagnosis: Option<CacheMissDiagnosis>`

Structured miss diagnosis, when the miss can be justified safely.

`provider: String`

Provider name (e.g., “anthropic”, “openai”).

`timestamp: DateTime<Utc>`

When this telemetry was recorded.

Implementations

`impl CacheTelemetryEvent`

impl CacheTelemetryEvent

`compute_hit_rate`

pub fn compute_hit_rate(cache_read_tokens: u64, total_prompt_tokens: u64) -> f64

Computes hit rate from token counts. Returns 0.0 if total_prompt_tokens is zero to avoid division by zero.

`from_usage`

pub fn from_usage(
    request_id: Uuid,
    agent_identity: AgentIdentity,
    provider: CacheTelemetryProvider,
    usage: &Usage,
    timestamp: DateTime<Utc>,
    request_facts: Option<&CacheRequestFacts>,
) -> Option<Self>

Builds a canonical cache telemetry event from normalized usage fields.

Returns None when the normalized usage payload does not contain prompt_tokens, because Phase 10 does not invent missing totals.

Trait Implementations

`impl Clone for CacheTelemetryEvent`

impl Clone for CacheTelemetryEvent

`clone`

fn clone(&self) -> CacheTelemetryEvent

`clone_from`

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

`impl Debug for CacheTelemetryEvent`

impl Debug for CacheTelemetryEvent

`fmt`

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

`impl<'de> Deserialize<'de> for CacheTelemetryEvent`

impl<'de> Deserialize<'de> for CacheTelemetryEvent

`deserialize`

fn deserialize<__D>(__deserializer: __D) -> Result<Self, __D::Error>where
    __D: Deserializer<'de>,

`impl PartialEq for CacheTelemetryEvent`

impl PartialEq for CacheTelemetryEvent

`eq`

fn eq(&self, other: &CacheTelemetryEvent) -> bool

`ne`

fn ne(&self, other: &Rhs) -> bool

`impl Serialize for CacheTelemetryEvent`

impl Serialize for CacheTelemetryEvent

`serialize`

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

`impl StructuralPartialEq for CacheTelemetryEvent`

impl StructuralPartialEq for CacheTelemetryEvent