Struct RunUsage 

#[non_exhaustive]
pub struct RunUsage {
    pub reported_attempts: usize,
    pub input_tokens: u64,
    pub cached_input_tokens: u64,
    pub cache_write_input_tokens: u64,
    pub output_tokens: u64,
    pub by_model: BTreeMap<String, TokenUsage>,
    pub overflowed: bool,
}

Cumulative token usage across every provider response in one materialization run.

Providers normally use one model for the whole run, but by_model preserves accounting if a provider reports different concrete model versions across retries. Keys use the response’s model identifier when present and the configured model as a fallback.

Fields (Non-exhaustive)

Non-exhaustive structs could have additional fields added in future. Therefore, non-exhaustive structs cannot be constructed in external crates using the traditional Struct { .. } syntax; cannot be matched against without a wildcard ..; and struct update syntax will not work.

reported_attempts: usize

Number of attempts whose provider response included token usage.

This can be lower than the number of attempts when a transport error occurs or a provider omits usage metadata.

input_tokens: u64

Cumulative input tokens across all reported responses.

cached_input_tokens: u64

Cumulative input tokens served from provider prompt caches.

This is a subset of input_tokens.

cache_write_input_tokens: u64

Cumulative input tokens written to provider prompt caches.

This is a subset of input_tokens.

output_tokens: u64

Cumulative output tokens across all reported responses.

by_model: BTreeMap<String, TokenUsage>

Cumulative usage grouped by reported model, or configured-model fallback.

overflowed: bool

Whether any cumulative counter exceeded its representable range.

When this is true, affected counters and total_tokens() saturate at their maximum value rather than panicking or wrapping.

Implementations

impl RunUsage

pub fn new() -> Self

Create an empty cumulative usage record.

pub fn from_response(usage: TokenUsage) -> Self

Create cumulative usage from one provider response.

pub fn record(&mut self, usage: TokenUsage)

Add one provider response to the cumulative totals.

pub fn total_tokens(&self) -> u64

Total known tokens used across the run.

Trait Implementations

impl Clone for RunUsage

fn clone(&self) -> RunUsage

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for RunUsage

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

Formats the value using the given formatter.

impl Default for RunUsage

fn default() -> RunUsage

Returns the “default value” for a type.

impl Eq for RunUsage

impl PartialEq for RunUsage

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

Equality operator ==.

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

Inequality operator !=.

impl StructuralPartialEq for RunUsage