Skip to main content

Module evaluation

Module evaluation 

Source
Available on crate feature evaluation only.
Expand description

Evaluation framework: judge runs over production AI traffic, failure replay with repair hints, and the auto-improve loop.

Modules§

error
Typed error boundary for the systemprompt-evaluation crate.
extension
Extension registration — wires the evaluation schemas (runs, cases, results, pairs, judge calls, rubrics) and their reconcile migrations into the extension framework.
models
Data model for evaluation runs, cases, results, rubrics, and sampling.
repository
Repositories over the eval_* tables plus the sampling reader over the ai_requests trace owned by systemprompt-ai.
services
Evaluation services: sampling, judging, replay, and the auto-improve loop.

Structs§

AutoImproveLoop
Sample → judge → repair-hint → replay → re-judge, one pass.
CanonicalMessage
CanonicalPrompt
Provider-neutral reconstruction of an AI request.
DimensionScore
EvalCase
EvalCaseRepository
EvalJudgeCallRepository
EvalRepositories
EvalResult
EvalResultRepository
EvalRubricRepository
EvalRun
EvalRunRepository
EvaluationExtension
EvaluationService
JudgeService
JudgeVerdict
Structured output the judge model is constrained to produce.
LoopLimits
LoopReport
NewCaseParams
NewResultParams
NewRunParams
ReplayService
Rubric
RubricDimension
RunRequest
SampleFilter
SampledRequest
A completed production request hydrated with everything the judge needs.
SamplerService
SamplingRepository

Enums§

EvalRunKind
EvalRunStatus
EvaluationError
TriggerSource
Verdict

Type Aliases§

Result