Module: eval
Classes
- EvalComparisonError
- EvalConfigError
- EvalDefinitionError
- EvalDiscoveryError
- EvalFixtureError
- EvalHarnessError
- EvalRunStoreError
- EvalRunWriter
Interfaces
- ClaudeSemanticGraderRawOutput
- ClaudeSemanticGraderRun
- CreateEvalRunOptions
- DiscoveredEvalSuite
- DiscoverEvalSuitesOptions
- EvalActivationEvidence
- EvalArtifactBinding
- EvalAssertionAggregate
- EvalAssertionResult
- EvalCase
- EvalCaseAggregate
- EvalCaseInput
- EvalComparableRow
- EvalComparisonDelta
- EvalComparisonOptions
- EvalComparisonSide
- EvalComparisonSummary
- EvalComparisonUsage
- EvalConditionMetrics
- EvalConfigInput
- EvalDraftConversion
- EvalDraftConversionOptions
- EvalDraftProvenance
- EvalEvidenceOptions
- EvalExitCodeAssertion
- EvalFileGraderSpec
- EvalFixture
- EvalFixtureInput
- EvalFixturePlan
- EvalFixturePlanEntry
- EvalGraderContext
- EvalGraderFailure
- EvalGraderRun
- EvalHarnessFailure
- EvalHostBinding
- EvalInvocation
- EvalJsonSchemaGraderSpec
- EvalMcpCallAssertion
- EvalMcpCallRecord
- EvalMcpEvidence
- EvalNoMcpCallAssertion
- EvalNonComparableCause
- EvalNonComparableRow
- EvalNoSkillActivationAssertion
- EvalOutcomeAssertion
- EvalPluginFailure
- EvalProcessEvidence
- EvalProcessProbe
- EvalReliability
- EvalRepositoryGraderSpec
- EvalRunEvent
- EvalRunEventInput
- EvalRunEventsRead
- EvalRunOwner
- EvalRunProvenance
- EvalRunRecord
- EvalRunSummary
- EvalScriptEvidence
- EvalScriptGraderSpec
- EvalScriptOutcome
- EvalSemanticGraderInput
- EvalSemanticGraderProvenance
- EvalSkillActivationAssertion
- EvalSuite
- EvalSuiteInput
- EvalTrialEvidence
- EvalTrialInvocationProvenance
- EvalTrialProvenance
- EvalTrialRecord
- EvalTrialUsage
- EvalUnrecordedSemanticGraderProvenance
- ExpectMcpCallOptions
- ExpectNoMcpCallOptions
- ExpectNoSkillActivationOptions
- ExpectOutcomeOptions
- ExpectSkillActivationOptions
- FindEvalSuiteFilesOptions
- ListEvalRunsOptions
- MaterializedEvalFixture
- MaterializeEvalFixtureOptions
- NormalizedEvalConfig
- NormalizedEvalSemanticGrader
- PlanEvalFixtureOptions
- PreparedEvalArtifact
- PrepareEvalArtifactOptions
- ReproduceEvalTrialAssertionsOptions
- RunClaudeSemanticGraderOptions
- RunDeterministicTrialOptions
Type Aliases
- ActivationEvidence
- EvalAlignmentFacet
- EvalAssertion
- EvalAssertionKind
- EvalAssertionOutcome
- EvalComparisonErrorCode
- EvalComparisonEvidence
- EvalComparisonRow
- EvalConfigErrorCode
- EvalDefinitionErrorCode
- EvalDiscoveryErrorCode
- EvalFixtureErrorCode
- EvalGraderFunction
- EvalGraderSpec
- EvalHarnessErrorCode
- EvalHarnessFailureCode
- EvalHarnessFailureStage
- EvalInvocationMode
- EvalNonComparableReason
- EvalPluginFailureCode
- EvalRecordedUsage
- EvalRunStoreErrorCode
- EvalTrialRecordInput
- EvalTrialSemanticGraderProvenance
Variables
- claudeSemanticGraderContractRevision
- claudeSemanticGraderId
- defaultEvalInclude
- defaultEvalRunsDir
- evalReliabilityMinimumTrials
Functions
- aggregateEvalTrials
- compareEvalRuns
- createEvalRun
- defineEvalSuite
- discoverEvalSuites
- evalCaseFromDraft
- evalScriptGraderSpec
- evalTargetDigests
- evidenceRank
- expectExitCode
- expectMcpCall
- expectNoMcpCall
- expectNoSkillActivation
- expectOutcome
- expectSkillActivation
- findEvalSuiteFiles
- isEvalScriptOutcome
- listEvalRuns
- loadEvalSuite
- materializeEvalFixture
- normalizeEvalCase
- normalizeEvalConfig
- parseClaudeSemanticGraderResult
- parseClaudeSemanticGraderStream
- parseEvalSuite
- planEvalFixture
- prepareEvalArtifact
- readEvalRun
- readEvalRunEvents
- readEvalTrials
- reproduceEvalTrialAssertions
- resolveEvalAssertion
- resolveEvalAssertions
- runClaudeSemanticGrader
- runDeterministicTrial
- runEvalGrader
- runEvalGraders
- satisfiesEvidence
- summarizeEvalRun
References
CodexCommandInput
Re-exports CodexCommandInput
CodexCommandResult
Re-exports CodexCommandResult
CodexCommandRunner
Re-exports CodexCommandRunner
CodexEvalHarness
Re-exports CodexEvalHarness
createCodexEvalHarness
Re-exports createCodexEvalHarness
createEvalHarness
Re-exports createEvalHarness
EvalComparison
Re-exports EvalComparison
EvalHarness
Re-exports EvalHarness
EvalSemanticGrader
Re-exports EvalSemanticGrader
EvalSemanticGraderContext
Re-exports EvalSemanticGraderContext
EvalSemanticGraderSpec
Re-exports EvalSemanticGraderSpec
runClaudeTrial
Re-exports runClaudeTrial
RunClaudeTrialOptions
Re-exports RunClaudeTrialOptions
runCodexEvalTrial
Re-exports runCodexEvalTrial
RunCodexEvalTrialOptions
Re-exports RunCodexEvalTrialOptions