@tangle-network/agent-eval 0.181.0 → 0.183.0

package/docs/public-api.md

@@ -7,11 +7,11 @@ Generated by `pnpm api:census` on demand — this is a dated reading, not a gate
 | measure | count |
 | --- | --- |
 | export subpaths | 28 |
-| published value exports (subpath x symbol) | 1403 |
-| distinct symbols | 1231 |
-| production | 944 |
-| planned | 218 |
-| none | 241 |
+| published value exports (subpath x symbol) | 1416 |
+| distinct symbols | 1240 |
+| production | 941 |
+| planned | 239 |
+| none | 236 |
 
 Type-only exports are not listed: a type binds no runtime surface, and removing one cannot break a caller at run time.
 
@@ -111,7 +111,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `argHash` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
 | `assertCapabilityHeadroom` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
 | `assertCrossFamily` | production | agent-builder:frontier/judges/artifact-head-to-head.ts |
-| `assertCrossFamilyServed` | planned | doc: README.md |
+| `assertCrossFamilyServed` | planned | doc: docs/building-doctrine.md |
 | `assertNoHiddenLeak` | planned | doc: docs/design/statistics-decisions.md |
 | `assertNoJudgeVerdict` | production | this package: src/analyst/policy-edit.ts:6 |
 | `assertProductBenchmarkRun` | production | creative-agent:eval/research-package.ts |
@@ -191,7 +191,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `createTraceAnalyst` | production | blueprint-agent:scripts/experiments/lib/sandbox-driver/analyst-steer.ts |
 | `CrossFamilyError` | production | creative-agent:eval/lib/judge-ensemble.ts |
 | `decidePairedPromotion` | production | discovery-lab:tools/decide.mjs |
-| `DECISION_PAIRED_DELTA_STATISTIC` | production | this package: src/campaign/gates/promotion-policy.ts:33 |
+| `DECISION_PAIRED_DELTA_STATISTIC` | production | this package: src/campaign/gates/promotion-policy.ts:19 |
 | `DEFAULT_BOUNDED_PROCESS_TIMEOUT_MS` | production | this package: src/command-runner.ts:28 |
 | `DEFAULT_FAILURE_REASON_RULES` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
 | `DEFAULT_PERMUTATIONS` | none | — |
@@ -211,7 +211,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `domainEvidencePattern` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/session-loader.ts |
 | `dominates` | production | blueprint-agent:scripts/experiments/lib/competition-analytics.ts |
 | `ensembleJudge` | production | blueprint-agent:scripts/experiments/lib/qa-grader.ts |
-| `eProcess` | production | this package: src/campaign/gates/sequential.ts:35 |
+| `eProcess` | production | this package: src/campaign/gates/sequential.ts:37 |
 | `EquivalenceProtocolError` | planned | doc: docs/verification-strategies.md |
 | `equivalenceVerdict` | planned | doc: docs/verdicts.md |
 | `ERROR_COUNT_PATTERNS` | production | blueprint-agent:scripts/experiments/lib/error-count-extractor.ts |
@@ -292,13 +292,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
 | `makePolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `makePolicyEditCandidateRecord` | planned | doc: docs/campaign-proposers.md |
-| `makeProposalFinding` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
-| `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:34 |
+| `makeProposalFinding` | production | agent-runtime:examples/improve/improve.ts |
+| `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:36 |
 | `MANN_WHITNEY_EXACT_MAX_STATES` | none | — |
 | `MANN_WHITNEY_EXACT_MAX_WORK` | none | — |
 | `mannWhitneyU` | production | blueprint-agent:scripts/experiments/lib/competition-analytics.ts |
 | `maximumChargeForLlmRequest` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
-| `mcnemar` | production | agent-runtime:bench/src/swe-arena/analyze.ts |
+| `mcnemar` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
 | `mcnemarPower` | production | supervisor-lab:bench/deepswe/headroom.ts |
 | `mcnemarRequiredN` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
 | `minimumPairsForPairedDeltaTest` | production | agent-dev-container:products/intelligence/api/src/routes/optimizations.ts |
@@ -318,18 +318,18 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `otlpTextToTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
 | `OUTPUT_VALUE` | production | agent-runtime:src/runtime/supervise-surface.ts |
 | `pairArms` | production | agent-knowledge:src/memory/experiment/learning-pairs.ts |
-| `pairedBinaryScale` | production | this package: src/paired-promotion-decision.ts:51 |
+| `pairedBinaryScale` | production | this package: src/paired-promotion-decision.ts:50 |
 | `pairedBootstrap` | production | agent-builder:frontier/adapters/fleet-eval-runner.ts |
-| `pairedCohensDz` | production | this package: src/contract/analyze-runs.ts:37 |
+| `pairedCohensDz` | production | this package: src/contract/analyze-runs.ts:38 |
 | `pairedDeltaTest` | production | gtm-agent:eval/matrix/report.ts |
-| `pairedDeltaTieFraction` | production | this package: src/paired-promotion-decision.ts:51 |
+| `pairedDeltaTieFraction` | production | this package: src/paired-promotion-decision.ts:50 |
 | `pairedEvalueSequence` | production | creative-agent:src/lib/experiments/ab-design.ts |
 | `pairedMde` | production | discovery-lab:tools/design-gate.mjs |
 | `pairedRiskDifference` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
-| `pairedRiskDifferenceExact` | production | this package: src/paired-promotion-decision.ts:51 |
-| `pairedRiskDifferenceScore` | production | this package: src/paired-promotion-decision.ts:51 |
+| `pairedRiskDifferenceExact` | production | this package: src/paired-promotion-decision.ts:50 |
+| `pairedRiskDifferenceScore` | production | this package: src/paired-promotion-decision.ts:50 |
 | `pairedSignTest` | production | agent-dev-container:products/intelligence/api/src/lib/paired-stats.ts |
-| `pairedTTest` | production | this package: src/contract/analyze-runs.ts:37 |
+| `pairedTTest` | production | this package: src/contract/analyze-runs.ts:38 |
 | `pairRunRecords` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `PairwiseSteeringOptimizer` | production | browser-agent-driver:bench/research/webvoyager-agent-eval-loop.mjs |
 | `paretoChart` | production | workcomp-agent:eval/benchmark/select.ts |
@@ -507,7 +507,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS` | production | this package: src/analyst/chat-trace-engine.ts:46 |
 | `defaultIsMaterial` | none | only this package's tests: src/analyst/analyst.test.ts:8 |
 | `defineCustomAnalyst` | planned | doc: docs/trace-analysis.md |
-| `defineTraceAnalyst` | planned | doc: docs/charter.md |
+| `defineTraceAnalyst` | planned | doc: docs/feature-guide.md |
 | `deriveEfficiencyFindings` | none | only this package's tests: src/trace-analyst/behavioral-metrics.test.ts:2 |
 | `diffFindings` | production | agent-runtime:src/analyst-loop/run-analyst-loop.ts |
 | `effectiveAnalystProtocolSha256` | production | this package: src/analyst/benchmark-command-persistence.ts:31 |
@@ -532,7 +532,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `loadCodeTraceVerificationArtifacts` | production | this package: src/analyst/benchmark-public-data.ts:32 |
 | `loadPublicBenchmarkRows` | production | this package: scripts/gepa-analyst-campaign.ts:64 |
 | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
-| `makeProposalFinding` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
+| `makeProposalFinding` | production | agent-runtime:examples/improve/improve.ts |
 | `MAX_INCORRECT_BLOCK_STEPS` | production | this package: src/analyst/benchmark-public-adapters.ts:9 |
 | `MAX_INCORRECT_BLOCKS` | production | this package: src/analyst/benchmark-public-adapters.ts:9 |
 | `mergePrimeRawUsage` | planned | doc: docs/prime-analyst.md |
@@ -628,7 +628,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./campaign`
 
-122 value exports — 81 production, 15 planned, 26 none.
+124 value exports — 80 production, 18 planned, 26 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -637,7 +637,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertCampaignDesign` | production | this package: src/campaign/plan-campaign-run.ts:10 |
 | `assertCampaignSplitIdentity` | production | agent-knowledge:src/memory/experiment/learning-pairs.ts |
 | `assertCodeSurfaceIdentity` | none | — |
-| `assertCompleteSearchHistory` | production | this package: src/campaign/optimization-method.ts:9 |
+| `assertCompleteSearchHistory` | production | this package: src/campaign/optimization-method.ts:14 |
 | `assertSearchHistoryMatchesReplay` | planned | doc: docs/search-history-receipts.md |
 | `autoevalsScorerJudge` | none | only this package's tests: src/campaign/upstream-evaluators.test.ts:6 |
 | `buildCellSchedule` | production | this package: src/campaign/plan-campaign-run.ts:9 |
@@ -646,9 +646,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `buildTraceAnalystSurfaceDispatch` | none | only this package's tests: src/campaign/analyst-surface.test.ts:4 |
 | `campaignBreakdown` | production | this package: src/campaign/external-text-evaluation.ts:11 |
 | `campaignMeanComposite` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
-| `campaignMeasurementDigest` | production | this package: src/contract/self-improve-method.ts:12 |
-| `campaignScenarioIdentity` | production | agent-runtime:bench/src/swe-arena/premeasured-from-cells.mts |
-| `campaignSplitDigest` | production | agent-runtime:bench/src/swe-arena/premeasured-from-cells.mts |
+| `campaignMeasurementDigest` | production | this package: src/contract/self-improve-method.ts:13 |
+| `campaignScenarioIdentity` | production | agent-runtime:src/improvement/method-identity.ts |
+| `campaignSplitDigest` | production | discovery-lab:tools/profile-population.mjs |
 | `campaignSplitDigestFromIdentities` | production | agent-runtime:src/improvement/method-identity.ts |
 | `canonicalDigest` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
 | `cellCachePath` | production | discovery-lab:tools/strict-screen.mjs |
@@ -669,15 +669,15 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `DEFAULT_EXTERNAL_OPTIMIZER_CALLBACK_LIMITS` | none | — |
 | `DEFAULT_EXTERNAL_OPTIMIZER_PROCESS_LIMITS` | none | — |
 | `defaultProductionGate` | production | agent-app:src/eval-campaign/index.ts |
-| `detectScale` | production | this package: src/campaign/gates/promotion-policy.ts:39 |
+| `detectScale` | production | this package: src/campaign/gates/promotion-policy.ts:25 |
 | `dimensionRegressions` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
 | `discoverEvalFixtures` | planned | doc: docs/eval-fixtures.md |
-| `emitLoopProvenance` | production | this package: src/contract/self-improve.ts:26 |
+| `emitLoopProvenance` | production | this package: src/contract/self-improve.ts:36 |
 | `externalTextOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
 | `FileSearchLedger` | none | — |
 | `finalizeProfileMatrix` | production | discovery-lab:tools/run-profile-confirmation.mjs |
 | `fsCampaignStorage` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
-| `FsLabeledScenarioStore` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
+| `FsLabeledScenarioStore` | planned | named in agent-runtime (bind not in the import graph) |
 | `gepaOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
 | `gitWorktreeAdapter` | production | agent-runtime:src/improvement/code-execution.ts |
 | `heldOutGate` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-gate.ts |
@@ -690,13 +690,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
 | `loadEvalFixture` | planned | doc: docs/eval-fixtures.md |
 | `loadEvalFixtureScenarios` | planned | example: examples/eval-fixtures-quickstart/index.ts:11 |
-| `loopProvenanceArgsFromResult` | production | this package: src/contract/self-improve.ts:26 |
+| `loopProvenanceArgsFromResult` | production | this package: src/contract/self-improve.ts:36 |
 | `loopProvenanceSpans` | none | only this package's tests: src/campaign/provenance-integrity.test.ts:5 |
 | `makePlaybackDispatch` | none | only this package's tests: src/campaign/presets/playback.test.ts:6 |
-| `makeProposalFinding` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
+| `makeProposalFinding` | production | agent-runtime:examples/improve/improve.ts |
 | `neutralizationGate` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/evolve.ts |
 | `neutralizeText` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/compile-and-prove/compile-diff.ts |
-| `openAutoPr` | production | this package: src/campaign/presets/run-improvement-loop.ts:7 |
+| `openAutoPr` | production | this package: src/campaign/presets/run-improvement-loop.ts:8 |
 | `openSearchLedger` | production | this package: src/campaign/gepa-optimization-method.ts:66 |
 | `optimizationTokenUsageFromSummary` | production | this package: src/campaign/external-text-optimization.ts:41 |
 | `pairHoldout` | production | agent-dev-container:products/intelligence/api/src/lib/run-provenance.ts |
@@ -728,21 +728,23 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `runOptimization` | production | agent-dev-container:products/sandbox/evals/src/auto-optimization.ts |
 | `runProfileMatrix` | production | agent-runtime:examples/product-eval/product-eval.ts |
 | `runProfileMatrixSegment` | production | discovery-lab:tools/run-profile-confirmation.mjs |
+| `scopedOptimizationMethod` | planned | doc: docs/campaign-proposers.md |
 | `scoreboardSummary` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
 | `scoreDiscrimination` | production | supervisor-lab:bench/comms/seat-discrimination.ts |
 | `scoreUserStory` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/scoreboard-core.ts |
-| `searchHistoryCoverageRow` | production | this package: src/campaign/optimization-method.ts:9 |
-| `SearchHistoryRequiredError` | none | only this package's tests: src/campaign/presets/compare-optimization-methods-history.test.ts:10 |
-| `SearchLedgerConflictError` | production | this package: src/campaign/search-ledger.ts:34 |
-| `SearchLedgerError` | production | this package: src/campaign/search-ledger.ts:34 |
+| `searchHistoryCoverageRow` | production | this package: src/campaign/optimization-method.ts:14 |
+| `SearchHistoryRequiredError` | none | only this package's tests: src/campaign/presets/compare-optimization-methods-history.test.ts:14 |
+| `SearchLedgerConflictError` | production | this package: src/campaign/search-ledger.ts:32 |
+| `SearchLedgerError` | production | this package: src/campaign/search-ledger.ts:32 |
 | `SearchLedgerIntegrityError` | production | this package: src/campaign/search-ledger-file.ts:10 |
 | `SearchRecorder` | production | this package: src/campaign/presets/run-optimization.ts:38 |
 | `selectDiscriminative` | none | only this package's tests: src/campaign/scenario-selection.test.ts:2 |
 | `sequentialDecide` | planned | doc: docs/experiment.md |
+| `sequentialOptimizationMethod` | planned | doc: docs/campaign-proposers.md |
 | `sequentialPairedGate` | planned | consumer tests: legal-agent:tests/eval/self-improve.ts |
 | `skillOptOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
 | `surfaceContentHash` | production | discovery-lab:tools/run-profile-confirmation.mjs |
-| `surfaceDispatchRef` | production | this package: src/campaign/presets/run-final-comparison.ts:4 |
+| `surfaceDispatchRef` | production | this package: src/campaign/presets/run-final-comparison.ts:11 |
 | `surfaceHash` | production | agent-builder:src/lib/.server/eval/loops/evolution-runner.ts |
 | `tangleTracesRoot` | none | only this package's tests: src/campaign/run-dir.test.ts:4 |
 | `traceAnalystQualityJudge` | production | this package: scripts/gepa-analyst-campaign.ts:74 |
@@ -751,7 +753,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `validateSearchLedgerEvent` | planned | consumer tests: discovery-lab:tools/search-ledger-planless.test.mjs |
 | `verifyCodeSurface` | production | agent-runtime:src/candidate-execution/builder.ts |
 | `verifyLoopProvenanceRecord` | none | only this package's tests: src/campaign/provenance-integrity.test.ts:5 |
-| `verifySearchHistoryArtifact` | production | this package: src/campaign/optimization-method.ts:9 |
+| `verifySearchHistoryArtifact` | production | this package: src/campaign/optimization-method.ts:14 |
 | `verifySearchHistoryReceipt` | planned | doc: docs/search-history-receipts.md |
 | `WorktreeAdapterError` | none | only this package's tests: tests/campaign/worktree.test.ts:17 |
 
@@ -764,7 +766,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `analyzeRuns` | production | agent-builder:eval/scripts/insight-report.ts |
 | `buildDefaultAnalystRegistry` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
 | `buildEvidenceVector` | planned | doc: docs/experiment.md |
-| `campaignSplitDigest` | production | agent-runtime:bench/src/swe-arena/premeasured-from-cells.mts |
+| `campaignSplitDigest` | production | discovery-lab:tools/profile-population.mjs |
 | `compareOptimizationMethods` | production | agent-app:src/eval-campaign/index.ts |
 | `composeGate` | production | discovery-lab:tools/confirmation-gate.mjs |
 | `createChatClient` | production | agent-dev-container:products/intelligence/api/src/lib/intent-audit-analyst.ts |
@@ -792,7 +794,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `inMemoryCampaignStorage` | production | agent-dev-container:products/sandbox/evals/src/auto-optimization.ts |
 | `InMemoryOutcomeStore` | planned | consumer tests: phony:products/builder/api/src/eval/outcomes-correlate.test.ts |
 | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
-| `makeProposalFinding` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
+| `makeProposalFinding` | production | agent-runtime:examples/improve/improve.ts |
 | `measuredComparisonFromAgentProfileImprovementExperiment` | production | agent-runtime:src/intelligence/authored-profile-improvement.ts |
 | `measuredComparisonFromCandidateExperiment` | production | agent-runtime:src/intelligence/improvement-cycle.ts |
 | `observeCodeAgentSession` | production | this package: src/contract/intake/code-agent-session.ts:13 |
@@ -829,12 +831,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./experiment`
 
-84 value exports — 50 production, 17 planned, 17 none.
+89 value exports — 55 production, 17 planned, 17 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `amendExperiment` | planned | doc: docs/experiment.md |
-| `assertDesignAdequate` | planned | doc: docs/experiment.md |
+| `assertDesignAdequate` | planned | doc: docs/eval-surface-map.md |
 | `assertFunnelReconciles` | none | only this package's tests: tests/experiment/funnel.test.ts:7 |
 | `assertMatchedBudgets` | planned | doc: docs/experiment.md |
 | `benjaminiHochberg` | production | agent-runtime:bench/src/corpus-report.mts |
@@ -846,30 +848,33 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `clusteredPower` | production | this package: scripts/tb-gated-stop-ab.ts:55 |
 | `comparePairedArms` | production | agent-knowledge:src/memory/experiment/learning-metrics.ts |
 | `composeFunnels` | planned | doc: docs/experiment.md |
-| `computeEstimand` | production | this package: src/experiment/define.ts:21 |
-| `computeInterval` | production | this package: src/experiment/define.ts:21 |
+| `computeEstimand` | production | this package: src/experiment/define.ts:20 |
+| `computeInterval` | production | this package: src/experiment/define.ts:20 |
 | `createCampaignEvidenceReceipt` | production | this package: src/campaign/presets/compare-optimization-methods.ts:11 |
 | `createEvidenceReceipt` | production | this package: src/experiment/campaign-evidence.ts:7 |
+| `defineEvaluationClaim` | production | this package: src/campaign/final-evidence.ts:2 |
 | `defineExperiment` | production | this package: scripts/tb-gated-stop-ab.ts:55 |
 | `DesignRefusalError` | none | only this package's tests: tests/experiment/power.test.ts:10 |
-| `eProcess` | production | this package: src/campaign/gates/sequential.ts:35 |
+| `eProcess` | production | this package: src/campaign/gates/sequential.ts:37 |
 | `evaluateCondition` | planned | named in agent-dev-container (bind not in the import graph) |
-| `evaluateHaltRule` | production | this package: src/experiment/define.ts:21 |
+| `evaluateHaltRule` | production | this package: src/experiment/define.ts:20 |
 | `evaluateHypothesis` | none | only this package's tests: tests/tier2.test.ts:8 |
-| `evaluateIdentityGate` | production | this package: src/experiment/define.ts:21 |
-| `evaluateOracleDeterminismGate` | production | this package: src/experiment/define.ts:21 |
-| `evaluatePopulationReproducibilityGate` | production | this package: src/experiment/define.ts:21 |
-| `evaluatePowerFloorGate` | production | this package: src/experiment/define.ts:21 |
+| `evaluateIdentityGate` | production | this package: src/experiment/define.ts:20 |
+| `evaluateOracleDeterminismGate` | production | this package: src/experiment/define.ts:20 |
+| `evaluatePopulationReproducibilityGate` | production | this package: src/experiment/define.ts:20 |
+| `evaluatePowerFloorGate` | production | this package: src/experiment/define.ts:20 |
 | `evaluatePredicate` | production | this package: src/experiment/funnel.ts:17 |
-| `evaluateProvenanceGate` | production | this package: src/experiment/define.ts:21 |
+| `evaluateProvenanceGate` | production | this package: src/experiment/define.ts:20 |
 | `EVIDENCE_AUTHORITY_KINDS` | none | — |
 | `EVIDENCE_RECEIPT_VERSION` | none | — |
 | `EVIDENCE_STATES` | none | only this package's tests: src/experiment/evidence-record.test.ts:4 |
 | `evidenceRegistryRecordSchema` | none | — |
-| `executeAdmissionRule` | production | this package: src/experiment/define.ts:58 |
-| `executeDecisionRule` | production | this package: src/experiment/define.ts:21 |
+| `executeAdmissionRule` | production | this package: src/experiment/define.ts:65 |
+| `executeDecisionRule` | production | this package: src/experiment/define.ts:20 |
 | `ExperimentTracker` | production | phony:products/builder/api/src/eval/evolution.ts |
 | `fileExperimentStore` | production | phony:products/builder/api/src/eval/evolution.ts |
+| `FinalEvidenceConflictError` | production | this package: src/campaign/final-evidence.ts:7 |
+| `FinalEvidenceError` | production | this package: src/campaign/final-evidence.ts:7 |
 | `FunnelIntegrityError` | none | only this package's tests: tests/experiment/funnel.test.ts:7 |
 | `hashJson` | production | agent-dev-container:products/intelligence/api/src/lib/ingest-optimization-mapping.ts |
 | `heldoutSignificance` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
@@ -877,44 +882,46 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `INDEPENDENT_EVIDENCE_AUTHORITY_KINDS` | none | — |
 | `inMemoryExperimentStore` | none | only this package's tests: src/experiment-tracker.test.ts:2 |
 | `isIndependentEvidence` | planned | consumer tests: agent-runtime:tests/integration/runtime-eval-pursuit-evidence.test.ts |
-| `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:34 |
+| `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:36 |
 | `MatchedBudgetError` | none | only this package's tests: tests/experiment/budget-and-seal.test.ts:8 |
-| `mcnemar` | production | agent-runtime:bench/src/swe-arena/analyze.ts |
+| `mcnemar` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
 | `mcnemarPower` | production | supervisor-lab:bench/deepswe/headroom.ts |
 | `mcnemarRequiredN` | production | blueprint-agent:scripts/experiments/analyze-convergence.ts |
 | `mulberry32` | production | agent-knowledge:src/memory/holdout.ts |
+| `openFinalEvidenceLedger` | planned | example: examples/evaluation-integrity/index.ts:10 |
 | `openSealedExperiment` | production | this package: scripts/tb-gated-stop-ab.ts:55 |
 | `pairArms` | production | agent-knowledge:src/memory/experiment/learning-pairs.ts |
 | `pairedBootstrap` | production | agent-builder:frontier/adapters/fleet-eval-runner.ts |
 | `pairedEvalueSequence` | production | creative-agent:src/lib/experiments/ab-design.ts |
 | `pairedMde` | production | discovery-lab:tools/design-gate.mjs |
 | `pairedRiskDifference` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
-| `pairedRiskDifferenceExact` | production | this package: src/paired-promotion-decision.ts:51 |
-| `pairedRiskDifferenceScore` | production | this package: src/paired-promotion-decision.ts:51 |
+| `pairedRiskDifferenceExact` | production | this package: src/paired-promotion-decision.ts:50 |
+| `pairedRiskDifferenceScore` | production | this package: src/paired-promotion-decision.ts:50 |
 | `pairHoldout` | production | agent-dev-container:products/intelligence/api/src/lib/run-provenance.ts |
 | `pairRunRecords` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `paretoPolicy` | none | only this package's tests: src/campaign/gates/promotion-policy.test.ts:3 |
 | `paretoSignificanceGate` | production | agent-app:src/eval-campaign/index.ts |
 | `parseEvidenceRegistryRecord` | none | only this package's tests: src/experiment/evidence-record.test.ts:4 |
 | `powerPreflight` | production | discovery-lab:tools/run-sequential-profile-improvement.mjs |
-| `projectNLadderBudget` | production | this package: src/experiment/define.ts:21 |
-| `readField` | planned | named in agent-dev-container (bind not in the import graph) |
+| `projectNLadderBudget` | production | this package: src/experiment/define.ts:20 |
+| `readField` | production | this package: src/experiment/claim.ts:4 |
 | `renderEvidenceIndex` | production | this package: scripts/render-evidence-index.ts:15 |
 | `renderFunnelTable` | planned | example: examples/sealed-experiment/index.ts:12 |
 | `requiredPairedSampleSize` | production | discovery-lab:tools/design-gate.mjs |
 | `requiredSampleSize` | planned | doc: docs/design/statistics-decisions.md |
-| `runSelectionRule` | production | this package: src/experiment/define.ts:21 |
-| `runUniformPassBudget` | production | this package: src/experiment/define.ts:21 |
+| `runSelectionRule` | production | this package: src/experiment/define.ts:20 |
+| `runUniformPassBudget` | production | this package: src/experiment/define.ts:20 |
 | `sealExperiment` | production | this package: scripts/tb-gated-stop-ab.ts:55 |
 | `SealIntegrityError` | none | only this package's tests: tests/experiment/budget-and-seal.test.ts:8 |
 | `sequentialCrossingHorizon` | none | only this package's tests: tests/sequential.test.ts:2 |
 | `sequentialDecide` | planned | doc: docs/experiment.md |
 | `sequentialPairedGate` | planned | consumer tests: legal-agent:tests/eval/self-improve.ts |
 | `signManifest` | production | phony:products/builder/api/src/eval/champion-sign.ts |
+| `summarizeEvaluationUnits` | production | this package: src/campaign/final-evidence.ts:2 |
 | `validateEvidenceRegistry` | none | only this package's tests: src/experiment/evidence-record.test.ts:4 |
 | `verifyEvidenceReceipt` | planned | consumer tests: agent-runtime:tests/integration/runtime-eval-pursuit-evidence.test.ts |
 | `verifyManifest` | production | phony:products/builder/api/src/eval/champion-sign.ts |
-| `verifyMatchedBudgets` | production | this package: src/experiment/define.ts:57 |
+| `verifyMatchedBudgets` | production | this package: src/experiment/define.ts:58 |
 | `verifySealedExperiment` | planned | example: examples/sealed-experiment/index.ts:12 |
 | `wilson` | production | agent-dev-container:products/intelligence/api/src/lib/project-analysis-coverage-recommendations.ts |
 
@@ -941,7 +948,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./hosted`
 
-11 value exports — 7 production, 3 planned, 1 none.
+11 value exports — 7 production, 2 planned, 2 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -953,7 +960,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `IngestEvalRunsRequestSchema` | production | this package: src/hosted/client.ts:19 |
 | `IngestResponseSchema` | production | this package: src/hosted/client.ts:19 |
 | `IngestTracesRequestSchema` | production | this package: src/hosted/client.ts:19 |
-| `InsightReportSchema` | planned | doc: docs/insight-report.md |
+| `InsightReportSchema` | none | only this package's tests: tests/contract-analyze-runs.test.ts:29 |
 | `TraceSpanEventSchema` | planned | example: examples/hosted-ingest-server/server.ts:33 |
 | `UnixNanoTimestampSchema` | none | — |
 
@@ -969,7 +976,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `FileLedgerJournal` | production | this package: src/campaign/search-ledger.ts:22 |
 | `hashCanonical` | production | discovery-lab:tools/provenance.mjs |
 | `jsonDocument` | production | this package: src/analyst/benchmark-command-artifact.ts:2 |
-| `LEDGER_HASH_PATTERN` | production | this package: src/ledger-core/trusted-head.ts:55 |
+| `LEDGER_HASH_PATTERN` | production | this package: src/campaign/final-evidence.ts:13 |
 | `LedgerCanonicalizationError` | none | only this package's tests: src/ledger-core/canonical.test.ts:5 |
 | `probeAtomicFileLock` | production | this package: src/campaign/single-run-lock.ts:17 |
 | `readTrustedHeadFile` | production | this package: src/ledger-core/journal.ts:29 |
@@ -993,28 +1000,37 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./meta-eval`
 
-18 value exports — 10 production, 6 planned, 2 none.
+27 value exports — 13 production, 13 planned, 1 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
-| `calibrationCurve` | none | only this package's tests: tests/meta-eval.test.ts:2 |
-| `catchRate` | planned | doc: README.md |
+| `auditEvaluator` | planned | example: examples/evaluation-integrity/index.ts:15 |
+| `calibrateJudge` | production | creative-agent:eval/calibrate-judges.ts |
+| `calibrateJudgeContinuous` | planned | consumer tests: tax-agent:tests/eval/lib/judge-sentinel.ts |
+| `calibrationCurve` | planned | doc: docs/eval-surface-map.md |
+| `calibrationFromPairs` | planned | doc: docs/eval-surface-map.md |
+| `catchRate` | planned | doc: docs/eval-surface-map.md |
+| `continuousAgreement` | production | agent-builder:frontier/judges/eval-validity.ts |
 | `correlationStudy` | production | phony:products/builder/api/src/eval/outcomes.ts |
-| `definePlant` | planned | doc: docs/plants.md |
+| `definePlant` | planned | doc: docs/eval-surface-map.md |
 | `evalHealthStamp` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `fileSentinelStore` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `FileSystemOutcomeStore` | production | phony:products/builder/api/src/eval/outcomes.ts |
 | `InMemoryOutcomeStore` | planned | consumer tests: phony:products/builder/api/src/eval/outcomes-correlate.test.ts |
 | `inMemorySentinelStore` | none | only this package's tests: tests/judge-sentinel.test.ts:7 |
 | `judgeSentinelReport` | production | creative-agent:eval/lib/judge-sentinel.ts |
+| `OutcomeStoreError` | planned | doc: docs/outcome-validity.md |
 | `perturbEvidence` | planned | doc: docs/plants.md |
-| `plantByPerturbation` | planned | doc: README.md |
+| `plantByPerturbation` | planned | doc: docs/plants.md |
+| `positionalBias` | planned | doc: docs/concepts.md |
 | `rubricPredictiveValidity` | production | physim:apps/server/src/scripts/agent-eval/validate-rubrics.ts |
-| `seedPlants` | planned | doc: README.md |
+| `seedPlants` | planned | doc: docs/eval-surface-map.md |
+| `selfPreference` | planned | doc: docs/concepts.md |
 | `snapshotFromAgreement` | production | physim:apps/server/src/scripts/agent-eval/judge-sentinel.ts |
 | `snapshotFromCalibration` | production | gtm-agent:eval/calibrate-judges.ts |
 | `snapshotFromSentinelSet` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `validateSentinelSnapshot` | production | creative-agent:eval/lib/judge-sentinel.ts |
+| `verbosityBias` | production | blueprint-agent:scripts/experiments/calibration/judge-agreement.ts |
 
 ### `./multishot`
 
@@ -1127,7 +1143,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./rl`
 
-65 value exports — 18 production, 15 planned, 32 none.
+65 value exports — 18 production, 19 planned, 28 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1153,7 +1169,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `extractVerifiableRewardsFromRecords` | production | creative-agent:eval/canonical-export.ts |
 | `FileSystemOutcomeStore` | production | phony:products/builder/api/src/eval/outcomes.ts |
 | `filterDeterministicallyRewarded` | production | this package: src/rl/reward-hacking.ts:43 |
-| `firstPassK` | none | only this package's tests: tests/rl-adaptation-eval.test.ts:3 |
+| `firstPassK` | planned | doc: docs/statistical-evidence.md |
 | `fitBradleyTerry` | none | only this package's tests: tests/rl-tournament.test.ts:2 |
 | `injectIrrelevantClause` | none | only this package's tests: tests/rl-contamination.test.ts:2 |
 | `InMemoryOutcomeStore` | planned | consumer tests: phony:products/builder/api/src/eval/outcomes-correlate.test.ts |
@@ -1163,16 +1179,16 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `observationsFromRunRecords` | none | only this package's tests: tests/rl-active-curriculum.test.ts:3 |
 | `offPolicyEstimateAll` | none | only this package's tests: tests/rl-off-policy.test.ts:3 |
 | `paretoFrontier` | production | agent-dev-container:products/sandbox/evals/run.ts |
-| `PredictiveValidityResearcher` | none | only this package's tests: tests/rl-predictive-validity-researcher.test.ts:4 |
+| `PredictiveValidityResearcher` | planned | doc: docs/design/mlbenchmarks-book-review.md |
 | `prmTrainingPairs` | planned | doc: examples/fine-tune-with-prime-rl/README.md |
 | `quantileEdges` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
 | `readCorpus` | planned | named in agent-runtime (bind not in the import graph) |
 | `renameVariables` | none | only this package's tests: tests/rl-contamination.test.ts:2 |
-| `runAdaptationCurve` | none | only this package's tests: tests/rl-adaptation-eval.test.ts:3 |
+| `runAdaptationCurve` | planned | doc: docs/statistical-evidence.md |
 | `runComputeCurve` | none | only this package's tests: tests/rl-adversarial-and-compute.test.ts:2 |
-| `runContaminationProbe` | none | only this package's tests: tests/rl-contamination.test.ts:2 |
+| `runContaminationProbe` | planned | doc: docs/statistical-evidence.md |
 | `runEvalCampaign` | production | agent-builder:scripts/eval.ts |
-| `runRLCampaign` | planned | named in creative-agent (bind not in the import graph) |
+| `runRLCampaign` | planned | doc: docs/outcome-validity.md |
 | `runwiseStepRewardSummary` | none | only this package's tests: tests/rl-process-reward.test.ts:3 |
 | `selfConsistency` | none | only this package's tests: tests/rl-adversarial-and-compute.test.ts:2 |
 | `selfNormalizedImportanceWeighting` | planned | consumer tests: agent-knowledge:tests/memory-holdout.test.ts |
@@ -1199,26 +1215,26 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./rollout`
 
-67 value exports — 49 production, 8 planned, 10 none.
+67 value exports — 42 production, 15 planned, 10 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `addScrubCounts` | production | this package: src/rollout/release/hf-dataset.ts:34 |
-| `appendRolloutLines` | production | agent-runtime:bench/src/rollout-ledger/settle-capture.mts |
+| `appendRolloutLines` | planned | doc: docs/rollout.md |
 | `assertGateReport` | production | this package: src/rollout/release/card.ts:12 |
 | `assertMinted` | production | blueprint-agent:scripts/experiments/lib/steering-dataset.ts |
-| `assertMintedLines` | planned | consumer tests: agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.test.mts |
+| `assertMintedLines` | planned | doc: docs/rollout.md |
 | `assertRolloutLine` | production | this package: src/rollout/interchange/harbor.ts:60 |
 | `ATIF_SCHEMA_VERSION` | none | only this package's tests: src/rollout/interchange/harbor.test.ts:6 |
 | `buildDatasetCard` | production | this package: src/rollout/release/hf-dataset.ts:25 |
 | `buildHfDataset` | production | supervisor-lab:bench/vertical-rollout-package.ts |
-| `claudeProjectSlug` | planned | consumer tests: agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.test.mts |
-| `DEFAULT_CLAUDE_PROJECTS_DIR` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
-| `DEFAULT_OPENCODE_DB` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
+| `claudeProjectSlug` | planned | named in agent-runtime (bind not in the import graph) |
+| `DEFAULT_CLAUDE_PROJECTS_DIR` | planned | named in agent-runtime (bind not in the import graph) |
+| `DEFAULT_OPENCODE_DB` | planned | named in agent-runtime (bind not in the import graph) |
 | `defaultRolloutScrubber` | production | supervisor-lab:bench/vertical-rollout-package.ts |
 | `emptyScrubCounts` | production | this package: src/rollout/release/hf-dataset.ts:34 |
-| `findClaudeTranscripts` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
-| `findOpencodeSessionsByDirectory` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
+| `findClaudeTranscripts` | planned | doc: docs/rollout.md |
+| `findOpencodeSessionsByDirectory` | planned | named in agent-runtime (bind not in the import graph) |
 | `FORMAT_FILES` | production | this package: src/rollout/release/hf-dataset.ts:25 |
 | `FORMAT_GATE_DISPOSITION` | production | this package: src/rollout/release/card.ts:12 |
 | `fromHarborTrajectory` | planned | doc: docs/rollout.md |
@@ -1237,11 +1253,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `mintRolloutRows` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
 | `observedScore` | production | this package: src/rl/active-curriculum.ts:34 |
 | `observedSplitScore` | production | starter-foundry:src/lib/held-out-gate.ts |
-| `openOpencodeDb` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
+| `openOpencodeDb` | production | discovery-lab:dashboard/lib/transcript.mjs |
 | `parseRolloutReleaseArgs` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
 | `planPushCommand` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
-| `readClaudeTranscript` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
-| `readOpencodeSessionMessages` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
+| `readClaudeTranscript` | planned | doc: docs/rollout.md |
+| `readOpencodeSessionMessages` | planned | doc: docs/rollout.md |
 | `readRolloutJournal` | none | only this package's tests: src/rollout/ledger.test.ts:6 |
 | `readRolloutLedger` | production | this package: src/rollout/release/hf-dataset.ts:23 |
 | `relabelImportedSplit` | planned | doc: docs/rollout.md |
@@ -1249,7 +1265,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `releaseRowRefs` | production | this package: src/rollout/release/hf-dataset.ts:26 |
 | `ROLLOUT_CAPTURES` | production | this package: src/rollout/interchange/harbor.ts:60 |
 | `ROLLOUT_ROLES` | production | this package: src/rollout/interchange/harbor.ts:60 |
-| `ROLLOUT_SCHEMA` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
+| `ROLLOUT_SCHEMA` | production | this package: src/rollout/interchange/harbor.ts:60 |
 | `ROLLOUT_SPLITS` | production | this package: src/rollout/interchange/harbor.ts:60 |
 | `runRolloutReleaseCli` | production | this package: src/cli.ts:19 |
 | `scoreOrigin` | production | this package: src/rollout/mint.ts:38 |
@@ -1269,7 +1285,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `trainingScore` | production | this package: src/eval-trace-store.ts:20 |
 | `unmintableReasons` | production | supervisor-lab:bench/mint-audit.ts |
 | `validateRolloutLine` | production | this package: src/supervisor-run/integrity-tree.ts:1 |
-| `writeRolloutLedger` | production | agent-runtime:bench/src/rollout-ledger/backfill-swe-arena.mts |
+| `writeRolloutLedger` | production | this package: src/rollout/release/hf-dataset.ts:23 |
 
 ### `./storyboard`
 
@@ -1289,7 +1305,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./supervisor-run`
 
-33 value exports — 23 production, 4 planned, 6 none.
+30 value exports — 20 production, 5 planned, 5 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1297,23 +1313,20 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `analyzeSupervisorRunIntegrity` | production | discovery-lab:pursuits/final-agent-authored-campaign-20260810/materialize-candidates.mjs |
 | `analyzeSupervisorRunSources` | production | discovery-lab:experiments/0005-run-visibility/probe.mjs |
 | `claudeCodeSupervisorRunReader` | none | only this package's tests: src/supervisor-run/claude-code-reader.test.ts:6 |
-| `findSupervisorRunDirIn` | none | only this package's tests: src/supervisor-run/loops-reader.test.ts:11 |
 | `findSupervisorRunDirs` | production | traces:src/cli.ts |
 | `isRuntimeSupervisorRunDir` | production | discovery-lab:tools/disco.mjs |
 | `isUnavailable` | production | discovery-lab:tools/disco.mjs |
-| `loopsSupervisorRunReader` | planned | named in traces (bind not in the import graph) |
 | `NO_SOURCE_LIMITS` | production | traces:src/supervisor-run-context.ts |
 | `NO_TERMINAL_RECORD` | none | only this package's tests: src/supervisor-run/terminal-record.test.ts:8 |
 | `parsePatch` | planned | named in browser-agent-driver (bind not in the import graph) |
 | `parseSupervisorTree` | production | discovery-lab:experiments/0005-run-visibility/probe.mjs |
 | `readClaudeCodeSupervisorRun` | none | only this package's tests: src/supervisor-run/claude-code-reader.test.ts:6 |
-| `readLoopsSupervisorRun` | planned | named in discovery-lab (bind not in the import graph) |
 | `readRuntimeSupervisorRun` | production | discovery-lab:pursuits/final-agent-authored-campaign-20260810/materialize-candidates.mjs |
 | `readTerminalRecord` | production | this package: src/supervisor-run/analyze.ts:18 |
 | `renderSupervisorRollupMarkdown` | production | traces:src/cli.ts |
 | `renderSupervisorRunHeadline` | production | discovery-lab:experiments/0005-run-visibility/probe.mjs |
-| `renderSupervisorRunMarkdown` | production | agent-runtime:bench/src/swe-arena/run-report.mts |
-| `reportSupervisorRound` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
+| `renderSupervisorRunMarkdown` | production | discovery-lab:experiments/0005-run-visibility/render-run.mjs |
+| `reportSupervisorRound` | planned | named in agent-runtime (bind not in the import graph) |
 | `rollupSupervisorRuns` | production | discovery-lab:tools/disco.mjs |
 | `runSupervisorRunCommand` | production | this package: src/cli.ts:20 |
 | `RUNTIME_FAILED_STATUS` | none | — |
@@ -1324,8 +1337,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `SUPERVISOR_RUN_SCHEMA` | production | this package: src/supervisor-run/analyze.ts:19 |
 | `supervisorRunRolloutLines` | planned | consumer tests: discovery-lab:tools/runtime-journal-eval.test.mjs |
 | `unavailable` | production | this package: src/supervisor-run/analyze.ts:19 |
-| `writeSupervisorRunReport` | production | agent-runtime:bench/src/swe-arena/run-report.mts |
-| `writeSupervisorRunReportSafe` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
+| `writeSupervisorRunReport` | planned | named in agent-runtime (bind not in the import graph) |
+| `writeSupervisorRunReportSafe` | planned | named in agent-runtime (bind not in the import graph) |
 
 ### `./trace-attributes`
 
@@ -1435,7 +1448,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `REPAIR_CONTRACT_LINES` | production | this package: src/trace-repair/arm-completion.ts:37 |
 | `REPAIR_QUESTION` | production | this package: src/trace-repair/arm-completion.ts:37 |
 | `REPAIR_REPAIR_CONTRACT_LINES` | production | this package: src/trace-repair/arm-completion.ts:37 |
-| `repairArmAsymmetries` | planned | doc: docs/charter.md |
+| `repairArmAsymmetries` | planned | doc: docs/trace-repair-analyst-arms.md |
 | `repairArmPromptSha256` | production | this package: src/trace-repair/analyst-arm.ts:42 |
 | `repairArmResponse` | planned | doc: docs/trace-repair-analyst-arms.md |
 | `repairCredit` | production | this package: src/trace-repair/grade.ts:40 |
@@ -1575,7 +1588,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `TRACE_ANALYST_TOOL_NAMESPACE` | none | only this package's tests: src/trace-analyst/tools.test.ts:4 |
 | `TRACE_ANALYST_TRUNCATION_MARKER_PREFIX` | production | agent-runtime:src/analyst-loop/iterations-to-trace-store.ts |
 | `TRACE_SCHEMA_VERSION` | production | skeletal-os:src/eval/agentEvalBridge.ts |
-| `TraceAnalysisLimitError` | production | this package: src/trace-analyst/store-bounds.ts:3 |
+| `TraceAnalysisLimitError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
 | `TraceAnalysisStoreContractError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
 | `TraceAnalysisValidationError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
 | `traceAnalystFunctionGroup` | none | only this package's tests: src/trace-analyst/tools.test.ts:4 |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.181.0",
+  "version": "0.183.0",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {