Struct EconomicsPair 

pub struct EconomicsPair {

    pub suite: String,
    pub task: String,
    pub category: String,
    pub sessions: usize,
    pub repetition: u32,
    pub control: Option<String>,
    pub treatment: Option<String>,
    pub status: EconomicsPairStatus,
    pub reasons: Vec<String>,
    pub control_usage: Option<EconomicsUsage>,
    pub treatment_usage: Option<EconomicsUsage>,
    pub token_reduction: Option<f64>,
    pub cost_reduction: Option<f64>,
    pub tool_call_reduction: Option<f64>,
    pub continuation_reduction: Option<f64>,
    pub first_request_overhead: Option<i64>,
}

A control run and its treatment run, and what follows from them.

use majordomus_cli::economics::model::{EconomicsPair, EconomicsPairStatus};
let p: EconomicsPair = serde_json::from_value(serde_json::json!({
    "suite": "pilot", "task": "vat-rounding", "category": "bugfix", "sessions": 1,
    "repetition": 2, "control": "vat-rounding--baseline--r2", "status": "missing",
    "reasons": ["no treatment run recorded"]
}))
.unwrap();
assert_eq!(p.status, EconomicsPairStatus::Missing);
assert!(p.treatment.is_none() && p.token_reduction.is_none(), "no side, no reduction");

Fields

suite: String

The suite.

task: String

The task.

category: String

The task’s category.

sessions: usize

Sessions the task spans.

repetition: u32

The repetition.

control: Option<String>

The control run’s id, when recorded.

treatment: Option<String>

The treatment run’s id, when recorded.

status: EconomicsPairStatus

Whether it counts.

reasons: Vec<String>

Why not, when it does not.

control_usage: Option<EconomicsUsage>

The control’s totals.

treatment_usage: Option<EconomicsUsage>

The treatment’s totals.

token_reduction: Option<f64>

1 - treatment / control on total tokens. Negative: the treatment cost more. Present on a valid pair, and on an excluded pair that would otherwise be valid, so that the outlier rule’s effect can be shown both ways; only valid pairs enter a metric other than effective_token_reduction.including_excluded. The same holds for every reduction and overhead below.

cost_reduction: Option<f64>

The same on the harness’s cost projection.

tool_call_reduction: Option<f64>

The same on tool calls.

continuation_reduction: Option<f64>

The same on the tokens of the last session only: what continuing cost.

first_request_overhead: Option<i64>

First-request input of the treatment minus that of the control: what the treatment adds before the model has done anything.

Trait Implementations

impl Clone for EconomicsPair

fn clone(&self) -> EconomicsPair

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for EconomicsPair

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

Formats the value using the given formatter.

impl<'de> Deserialize<'de> for EconomicsPair

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

where __D: Deserializer<'de>,

Deserialize this value from the given Serde deserializer.

impl JsonSchema for EconomicsPair

fn schema_name() -> Cow<'static, str>

The name of the generated JSON Schema.

fn schema_id() -> Cow<'static, str>

Returns a string that uniquely identifies the schema produced by this type.

fn json_schema(generator: &mut SchemaGenerator) -> Schema

Generates a JSON Schema for this type.

fn inline_schema() -> bool

Whether JSON Schemas generated for this type should be included directly in parent schemas, rather than being re-used where possible using the $ref keyword.

impl PartialEq for EconomicsPair

fn eq(&self, other: &EconomicsPair) -> 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 EconomicsPair

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

where __S: Serializer,

Serialize this value into the given Serde serializer.

impl StructuralPartialEq for EconomicsPair