@tangle-network/agent-eval 0.198.1 → 0.199.0

package/docs/public-api.md

@@ -6,12 +6,12 @@ Generated by `pnpm api:census` on demand — this is a dated reading, not a gate
 
 | measure | count |
 | --- | --- |
-| export subpaths | 32 |
-| published value exports (subpath x symbol) | 1511 |
-| distinct symbols | 1324 |
-| production | 992 |
-| planned | 268 |
-| none | 251 |
+| export subpaths | 33 |
+| published value exports (subpath x symbol) | 1570 |
+| distinct symbols | 1382 |
+| production | 1047 |
+| planned | 266 |
+| none | 257 |
 
 Type-only exports are not listed: a type binds no runtime surface, and removing one cannot break a caller at run time.
 
@@ -84,7 +84,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `.`
 
-360 value exports — 277 production, 42 planned, 41 none.
+360 value exports — 279 production, 40 planned, 41 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -223,7 +223,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `evaluateInterimReleaseConfidence` | production | agent-builder:scripts/eval.ts |
 | `evaluateOracles` | planned | doc: docs/verdicts.md |
 | `evaluateReleaseConfidence` | production | agent-knowledge:src/release.ts |
-| `evaluateTraceContract` | planned | doc: docs/trace-contracts.md |
+| `evaluateTraceContract` | planned | doc: docs/verdicts.md |
 | `expandProfileAxes` | production | agent-runtime:src/runtime/define-leaderboard.ts |
 | `explainTraceContract` | planned | doc: docs/trace-contracts.md |
 | `exportProductBenchmark` | production | creative-agent:eval/research-package.ts |
@@ -258,7 +258,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `hashJson` | production | agent-dev-container:products/intelligence/api/src/lib/ingest-optimization-mapping.ts |
 | `HeldOutGate` | production | agent-builder:src/lib/.server/eval/gates/promotion.ts |
 | `hiddenGrade` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
-| `holm` | planned | doc: docs/design/statistics-decisions.md |
+| `holm` | production | this package: src/search/lenses/edit-credit.ts:47 |
 | `improvementVerdict` | production | blueprint-agent:scripts/experiments/lib/vb-improve-harness.ts |
 | `inferDomainKeywords` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/suite-projection.ts |
 | `INFRA_FAILURE_BLAMES` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
@@ -329,7 +329,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
-| `pairedPromotionPower` | planned | doc: docs/design/statistics-decisions.md |
+| `pairedPromotionPower` | production | this package: src/campaign/search-claim.ts:22 |
 | `pairedRiskDifference` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
 | `pairedRiskDifferenceExact` | production | this package: src/paired-promotion-decision.ts:50 |
 | `pairedRiskDifferenceScore` | production | this package: src/paired-promotion-decision.ts:50 |
@@ -584,7 +584,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `rlmEngineLimits` | none | only this package's tests: src/analyst/definition-parity.test.ts:26 |
 | `roundAgentRxStep` | production | this package: src/analyst/benchmark-agentrx-calibration.ts:2 |
 | `runAnalystBenchmark` | production | this package: benchmarks/trace-analysis/codetracebench-glm52-20260730/summarize-codetracer.mjs:6 |
-| `runAnalystBenchmarkCommand` | production | this package: src/cli.ts:18 |
+| `runAnalystBenchmarkCommand` | production | this package: src/cli.ts:19 |
 | `runPrimeExchange` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
 | `runTraceAnalyst` | production | this package: scripts/gepa-analyst-campaign.ts:71 |
 | `scoreAnalystFindings` | production | this package: scripts/gepa-analyst-campaign.ts:57 |
@@ -644,23 +644,27 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./campaign`
 
-144 value exports — 92 production, 26 planned, 26 none.
+166 value exports — 117 production, 22 planned, 27 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `acquireSingleRunLock` | production | agent-knowledge:src/memory/run-control.ts |
+| `aide` | production | this package: scripts/search-sim.ts:145 |
 | `analyzeCrossSurfaceInteractions` | none | only this package's tests: src/campaign/cross-surface-interaction.test.ts:2 |
+| `asha` | production | this package: scripts/search-sim.ts:119 |
 | `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:14 |
 | `assertSearchHistoryMatchesState` | planned | doc: docs/search-ledger.md |
 | `autoevalsScorerJudge` | none | only this package's tests: src/campaign/upstream-evaluators.test.ts:6 |
+| `beam` | production | this package: scripts/search-sim.ts:145 |
 | `buildCellSchedule` | production | this package: src/campaign/plan-campaign-run.ts:9 |
 | `buildEvidenceVector` | planned | doc: docs/experiment.md |
-| `buildLoopProvenanceRecord` | none | only this package's tests: src/campaign/provenance-integrity.test.ts:5 |
+| `buildLoopProvenanceRecord` | none | only this package's tests: tests/campaign/candidate-attribution.test.ts:5 |
 | `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 |
+| `campaignCellSearchResult` | production | this package: src/campaign/presets/run-optimization.ts:51 |
 | `campaignMeanComposite` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
 | `campaignMeasurementDigest` | production | this package: src/contract/self-improve-method.ts:14 |
 | `campaignScenarioIdentity` | production | agent-runtime:src/improvement/method-identity.ts |
@@ -672,7 +676,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `codeSurfaceIdentityMaterial` | none | — |
 | `combineComparisonCosts` | production | this package: src/campaign/external-text-optimization.ts:41 |
 | `compareOptimizationMethods` | production | agent-app:src/eval-campaign/index.ts |
-| `compareRankKeys` | production | this package: src/campaign/presets/run-optimization.ts:30 |
 | `componentSurfaceIdentityMaterial` | none | only this package's tests: src/campaign/surface-identity.test.ts:4 |
 | `composeGate` | production | discovery-lab:tools/confirmation-gate.mjs |
 | `costFromLedgerSummary` | production | supervisor-lab:bench/drain/seat.ts |
@@ -680,21 +683,22 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `createReferenceEquivalenceJudge` | none | only this package's tests: src/reference-equivalence-judge.test.ts:13 |
 | `createRunCostLedger` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `createSearchHistoryReceipt` | production | this package: src/campaign/search-ledger-recording.ts:27 |
-| `crowdedFrontierParent` | planned | doc: docs/campaign-proposers.md |
+| `crowdedFrontierParent` | production | this package: scripts/search-sim.ts:145 |
+| `decideSearchClaim` | production | this package: src/campaign/search-kernel.ts:42 |
 | `decodeExternalTextCandidate` | production | agent-runtime:src/improvement/method-execution.ts |
 | `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:25 |
-| `developmentClaim` | production | this package: src/campaign/gepa-search-import.ts:23 |
+| `developmentClaim` | production | this package: scripts/generate-synthetic-search-ledger.ts:34 |
 | `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:36 |
-| `estimateNode` | planned | doc: docs/search-ledger.md |
-| `estimateNodeFromCells` | planned | doc: docs/search-ledger.md |
+| `estimateNode` | production | this package: scripts/search-sim.ts:120 |
+| `estimateNodeFromCells` | production | this package: scripts/synthetic-search-ledger.ts:60 |
 | `externalSurface` | none | — |
 | `externalTextOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
-| `FileSearchLedger` | planned | doc: docs/search-ledger.md |
+| `FileSearchLedger` | production | this package: src/campaign/search-kernel.ts:52 |
 | `finalizeProfileMatrix` | production | discovery-lab:tools/run-profile-confirmation.mjs |
 | `fsCampaignStorage` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `FsLabeledScenarioStore` | planned | named in agent-runtime (bind not in the import graph) |
@@ -704,6 +708,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `heldoutSignificance` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
 | `importExternalEvaluations` | planned | doc: docs/search-ledger.md |
 | `importGepaPopulation` | planned | doc: docs/search-ledger.md |
+| `incumbent` | production | this package: scripts/search-meta-sim.ts:48 |
+| `incumbentWithOperatorBandit` | production | this package: scripts/prove-operator-bandit.mts:18 |
 | `inMemoryCampaignStorage` | production | agent-dev-container:products/sandbox/evals/src/auto-optimization.ts |
 | `isProposedCandidate` | production | supervisor-lab:bench/sequential-arena.ts |
 | `isTransientTransportFailure` | production | gtm-agent:eval/suites/persona.ts |
@@ -713,21 +719,22 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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:36 |
-| `loopProvenanceSpans` | none | only this package's tests: src/campaign/provenance-integrity.test.ts:5 |
+| `loopProvenanceSpans` | none | only this package's tests: tests/campaign/presets.test.ts:6 |
 | `makePlaybackDispatch` | none | only this package's tests: src/campaign/presets/playback.test.ts:6 |
 | `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:8 |
-| `openSearchLedger` | production | this package: src/campaign/gepa-search-import.ts:22 |
+| `openSearchLedger` | production | this package: scripts/generate-synthetic-search-ledger.ts:34 |
 | `optimizationTokenUsageFromSummary` | production | this package: src/campaign/external-text-optimization.ts:41 |
 | `pairHoldout` | production | agent-dev-container:products/intelligence/api/src/lib/run-provenance.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 |
-| `parseSearchLedgerLine` | production | this package: src/hosted/search-ledger-wire.ts:24 |
+| `parseSearchLedgerLine` | production | this package: scripts/search-sim.ts:132 |
 | `phoenixEvaluatorJudge` | none | only this package's tests: src/campaign/upstream-evaluators.test.ts:6 |
 | `planCampaignRun` | production | this package: src/campaign/fixtures.ts:5 |
 | `planEvalFixtureRun` | planned | example: examples/eval-fixtures-quickstart/index.ts:11 |
+| `planSearchClaim` | production | this package: src/campaign/search-kernel.ts:42 |
 | `powerPreflight` | production | discovery-lab:tools/run-sequential-profile-improvement.mjs |
 | `ProfileMatrixError` | production | this package: src/campaign/presets/segmented-profile-matrix.ts:22 |
 | `provenanceRecordPath` | planned | consumer tests: agent-dev-container:products/intelligence/api/tests/optimization-engine.test.ts |
@@ -736,10 +743,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `readCachedCell` | production | discovery-lab:tools/strict-screen.mjs |
 | `readExternalOptimizerObservationArtifact` | production | agent-runtime:src/improvement/method-execution.ts |
 | `readGepaCandidatePopulationArtifact` | production | agent-runtime:src/improvement/method-execution.ts |
-| `recordGepaSearch` | production | this package: src/campaign/gepa-optimization-method.ts:58 |
+| `recordGepaSearch` | production | this package: scripts/import-vb-climb.ts:35 |
+| `recordSkillOptSearch` | production | this package: src/campaign/skillopt-optimization-method.ts:41 |
 | `renderScoreboardMarkdown` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
+| `renderSearchSummary` | production | this package: scripts/search-meta-sim.ts:50 |
 | `renderSurfaceDiff` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-evidence-packet.ts |
-| `replaySearchLedgerText` | production | this package: src/campaign/search-history-receipt.ts:5 |
+| `replaySearchLedgerText` | production | this package: scripts/generate-synthetic-search-ledger.ts:34 |
 | `resolveExternalOptimizerCallbackLimits` | production | this package: src/analyst/dspy-rlm-engine.ts:1 |
 | `resolveExternalOptimizerProcessLimits` | production | this package: src/analyst/benchmark-command-persistence.ts:6 |
 | `resolveRunDir` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
@@ -751,25 +760,36 @@ 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 |
+| `runSearch` | production | this package: scripts/search-sim.ts:121 |
 | `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 |
+| `SEARCH_CLAIM_RULE` | production | this package: src/campaign/search-kernel.ts:42 |
 | `SEARCH_ESTIMATOR` | planned | doc: docs/search-ledger.md |
-| `SEARCH_LEDGER_SCHEMA` | production | this package: src/campaign/search-ledger.ts:41 |
-| `searchCellId` | production | this package: src/campaign/search-ledger-recording.ts:57 |
+| `SEARCH_KERNEL_SOURCE` | production | this package: src/campaign/presets/run-optimization.ts:57 |
+| `SEARCH_LEDGER_SCHEMA` | production | this package: src/campaign/search-ledger.ts:43 |
+| `searchCellId` | production | this package: src/campaign/search-kernel.ts:74 |
 | `searchCellSetDigest` | planned | doc: docs/search-ledger.md |
+| `searchClaimReserveUsd` | production | this package: scripts/search-meta-sim.ts:43 |
+| `searchDivergence` | planned | doc: docs/search-ledger.md |
 | `searchEdgeId` | planned | doc: docs/search-ledger.md |
+| `searchExpansionIndex` | production | this package: scripts/search-sim.ts:121 |
 | `searchHistoryCoverageRow` | production | this package: src/campaign/optimization-method.ts:14 |
 | `SearchHistoryRequiredError` | none | — |
-| `SearchLedgerConflictError` | production | this package: src/campaign/search-ledger.ts:34 |
+| `SearchLedgerConflictError` | production | this package: src/campaign/search-ledger.ts:36 |
 | `SearchLedgerError` | production | this package: src/campaign/estimate-node.ts:20 |
 | `SearchLedgerIntegrityError` | production | this package: src/campaign/search-ledger-file.ts:10 |
+| `searchModelIdentity` | none | — |
 | `searchNodeId` | production | this package: src/campaign/search-ledger-recording.ts:57 |
-| `searchPosterior` | planned | doc: docs/search-ledger.md |
-| `SearchRecorder` | production | this package: src/campaign/gepa-search-import.ts:23 |
-| `SearchState` | production | this package: src/campaign/search-ledger.ts:48 |
-| `SearchStateView` | production | this package: src/campaign/estimate-node.ts:28 |
+| `searchPolicyView` | production | this package: scripts/prove-operator-bandit.mts:18 |
+| `searchPosterior` | production | this package: src/campaign/search-claim.ts:27 |
+| `searchProposalExecution` | production | this package: src/campaign/presets/run-optimization.ts:51 |
+| `searchProposerView` | production | this package: src/campaign/presets/run-optimization.ts:86 |
+| `searchReceiptAccounting` | production | this package: src/campaign/presets/run-optimization.ts:51 |
+| `SearchRecorder` | production | this package: scripts/generate-synthetic-search-ledger.ts:34 |
+| `SearchState` | production | this package: scripts/search-sim.ts:144 |
+| `SearchStateView` | production | this package: scripts/search-meta-sim.ts:49 |
 | `searchTaskSetDigest` | production | this package: src/campaign/search-ledger-recording.ts:57 |
 | `searchUnitScores` | production | this package: src/campaign/estimate-node.ts:28 |
 | `selectDiscriminative` | none | only this package's tests: src/campaign/scenario-selection.test.ts:2 |
@@ -778,17 +798,19 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
-| `surfaceDiff` | production | this package: src/campaign/gepa-search-import.ts:23 |
+| `surfaceDiff` | production | this package: scripts/synthetic-search-ledger.ts:54 |
 | `surfaceDispatchRef` | production | this package: src/campaign/presets/run-final-comparison.ts:11 |
 | `surfaceHash` | production | agent-builder:src/lib/.server/eval/loops/evolution-runner.ts |
-| `surfaceNode` | production | this package: src/campaign/gepa-search-import.ts:23 |
+| `surfaceNode` | production | this package: scripts/synthetic-search-ledger.ts:54 |
 | `tangleTracesRoot` | none | only this package's tests: src/campaign/run-dir.test.ts:4 |
 | `traceAnalystQualityJudge` | production | this package: scripts/gepa-analyst-campaign.ts:74 |
 | `transientDispatchFailure` | planned | doc: docs/eval-surface-map.md |
+| `uniform` | production | this package: scripts/search-meta-sim.ts:42 |
 | `userStoryScoreboard` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
 | `validateSearchLedgerEvent` | production | this package: src/campaign/search-ledger-recording.ts:28 |
 | `verifyCodeSurface` | production | agent-runtime:src/candidate-execution/builder.ts |
-| `verifyLoopProvenanceRecord` | none | only this package's tests: src/campaign/provenance-integrity.test.ts:5 |
+| `verifyLoopProvenanceRecord` | none | — |
+| `verifySearchClaim` | production | this package: src/campaign/search-kernel.ts:42 |
 | `verifySearchHistoryArtifact` | production | this package: src/campaign/optimization-method.ts:14 |
 | `verifySearchHistoryReceipt` | planned | doc: docs/search-ledger.md |
 | `WorktreeAdapterError` | none | only this package's tests: tests/campaign/worktree.test.ts:17 |
@@ -891,7 +913,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./experiment`
 
-91 value exports — 53 production, 20 planned, 18 none.
+91 value exports — 54 production, 19 planned, 18 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -937,7 +959,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
-| `holm` | planned | doc: docs/design/statistics-decisions.md |
+| `holm` | production | this package: src/search/lenses/edit-credit.ts:47 |
 | `INDEPENDENT_EVIDENCE_AUTHORITY_KINDS` | none | — |
 | `isIndependentEvidence` | planned | consumer tests: agent-runtime:tests/integration/runtime-eval-pursuit-evidence.test.ts |
 | `joinProspectiveCanaryReceipts` | planned | doc: docs/experiment.md |
@@ -1014,7 +1036,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
-| `admitSearchLedgerBatch` | planned | example: examples/hosted-ingest-server/server.ts:30 |
+| `admitSearchLedgerBatch` | planned | example: examples/hosted-ingest-server/server.ts:34 |
 | `createHostedClient` | production | traces:src/index.ts |
 | `HOSTED_WIRE_VERSION` | production | agent-dev-container:packages/sdk-data/src/sink/intelligence-sink.ts |
 | `hostedClientFromEnv` | production | traces:src/index.ts |
@@ -1032,16 +1054,16 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `SearchLedgerConflictSchema` | production | this package: src/hosted/client.ts:23 |
 | `searchLedgerHeadPath` | production | this package: src/hosted/client.ts:23 |
 | `SearchLedgerHeadSchema` | production | this package: src/hosted/client.ts:23 |
-| `SearchRunKindSchema` | production | this package: src/search-command.ts:13 |
-| `SearchShipConflictError` | production | this package: src/search-command.ts:14 |
+| `SearchRunKindSchema` | production | this package: src/search-command.ts:37 |
+| `SearchShipConflictError` | production | this package: src/search-command.ts:38 |
 | `shipSearchLedger` | production | this package: src/contract/self-improve-method.ts:24 |
 | `startSearchShipper` | production | this package: src/contract/self-improve.ts:66 |
-| `TraceSpanEventSchema` | planned | example: examples/hosted-ingest-server/server.ts:29 |
+| `TraceSpanEventSchema` | planned | example: examples/hosted-ingest-server/server.ts:33 |
 | `UnixNanoTimestampSchema` | none | — |
 
 ### `./jev`
 
-14 value exports — 6 production, 7 planned, 1 none.
+15 value exports — 7 production, 7 planned, 1 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1056,35 +1078,38 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `jevReviewFindings` | planned | example: examples/jev-behavior-review.ts:3 |
 | `jevUsage` | production | this package: src/jev.ts:7 |
 | `normalizedJevScore` | planned | doc: docs/jev.md |
+| `parseJevQuestions` | production | this package: src/jev.ts:7 |
 | `parseJevRequest` | production | this package: src/jev-review.ts:9 |
 | `parseJevResult` | production | this package: src/jev-review.ts:9 |
 | `prepareJevReview` | planned | example: examples/jev-behavior-review.ts:3 |
 
 ### `./jev/protocol`
 
-4 value exports — 3 production, 0 planned, 1 none.
+5 value exports — 4 production, 0 planned, 1 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `JevResponseError` | none | — |
 | `jevUsage` | production | this package: src/jev.ts:7 |
+| `parseJevQuestions` | production | this package: src/jev.ts:7 |
 | `parseJevRequest` | production | this package: src/jev-review.ts:9 |
 | `parseJevResult` | production | this package: src/jev-review.ts:9 |
 
 ### `./ledger-core`
 
-19 value exports — 18 production, 0 planned, 1 none.
+20 value exports — 19 production, 0 planned, 1 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `appendLedgerLine` | production | this package: src/campaign/search-ledger-file.ts:3 |
 | `AtomicFileLockError` | production | this package: src/ledger-core/journal-file.ts:16 |
-| `canonicalString` | production | this package: src/agent-profile-cell.ts:3 |
+| `canonicalString` | production | this package: scripts/search-sim.ts:154 |
 | `FileLedgerJournal` | production | this package: src/campaign/search-ledger.ts:23 |
 | `hashCanonical` | production | discovery-lab:tools/provenance.mjs |
 | `jsonDocument` | production | this package: src/agent-profile-cell.ts:3 |
 | `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 |
+| `MemoryLedgerJournal` | production | this package: src/campaign/search-ledger.ts:23 |
 | `probeAtomicFileLock` | production | this package: src/campaign/single-run-lock.ts:17 |
 | `projectorSnapshotPathFor` | production | this package: src/ledger-core/journal.ts:48 |
 | `readProjectorSnapshotFile` | production | this package: src/ledger-core/journal.ts:48 |
@@ -1255,7 +1280,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./rl`
 
-65 value exports — 18 production, 19 planned, 28 none.
+63 value exports — 18 production, 18 planned, 27 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1288,7 +1313,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `inverseProbabilityWeighting` | planned | consumer tests: agent-knowledge:tests/memory-holdout.test.ts |
 | `jsDivergence` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
 | `loadVerifiedFindingsDataset` | planned | doc: docs/verified-labels-flywheel.md |
-| `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` | planned | doc: docs/design/mlbenchmarks-book-review.md |
@@ -1308,7 +1332,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `simFidelityReport` | none | only this package's tests: src/rl/sim-fidelity.test.ts:3 |
 | `stepRewardsToJsonl` | none | only this package's tests: src/rollout/gate-properties.test.ts:38 |
 | `summarizeVerifiedFindings` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
-| `thompsonCurriculum` | planned | doc: docs/design/statistics-decisions.md |
 | `toAnthropicFormat` | production | blueprint-agent:scripts/experiments/lib/steering-dataset.ts |
 | `toDpoJsonl` | production | this package: src/rl/dataset.ts:27 |
 | `toDpoRows` | production | this package: src/rl/dataset.ts:27 |
@@ -1363,7 +1386,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `isTrainableSplit` | production | this package: src/rollout/release/hf-dataset.ts:24 |
 | `measureFormatGate` | production | this package: src/rollout/release/hf-dataset.ts:26 |
 | `mintRolloutRows` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
-| `observedScore` | production | this package: src/rl/active-curriculum.ts:34 |
+| `observedScore` | production | this package: src/rl/reward-hacking.ts:40 |
 | `observedSplitScore` | production | starter-foundry:src/lib/held-out-gate.ts |
 | `openOpencodeDb` | production | discovery-lab:dashboard/lib/transcript.mjs |
 | `parseRolloutReleaseArgs` | none | only this package's tests: src/rollout/release/hf-dataset.test.ts:9 |
@@ -1379,7 +1402,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `ROLLOUT_ROLES` | production | this package: src/rollout/interchange/harbor.ts:60 |
 | `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:20 |
+| `runRolloutReleaseCli` | production | this package: src/cli.ts:21 |
 | `scoreOrigin` | production | this package: src/rollout/mint.ts:39 |
 | `scrubLines` | production | supervisor-lab:bench/vertical-rollout-package.ts |
 | `scrubRolloutLine` | none | only this package's tests: src/rollout/release/scrub.test.ts:4 |
@@ -1399,6 +1422,51 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `validateRolloutLine` | production | this package: src/supervisor-run/integrity-tree.ts:1 |
 | `writeRolloutLedger` | production | this package: src/rollout/release/hf-dataset.ts:23 |
 
+### `./search`
+
+38 value exports — 26 production, 6 planned, 6 none.
+
+| symbol | consumer | evidence |
+| --- | --- | --- |
+| `draftOnPlateau` | production | this package: scripts/search-sim.ts:161 |
+| `EDIT_CREDIT_ESTIMATOR` | none | — |
+| `EDIT_CREDIT_SIGNAL` | none | — |
+| `editCredit` | production | this package: scripts/synthetic-search-ledger.ts:70 |
+| `editCreditText` | production | this package: src/search-command.ts:39 |
+| `EXPANSION_OPERATORS` | production | this package: src/campaign/search-policy.ts:18 |
+| `formatLandscape` | production | this package: src/search-command.ts:41 |
+| `formatSkillManifold` | production | this package: src/search-command.ts:45 |
+| `front` | production | this package: src/search-command.ts:40 |
+| `landscape` | production | this package: scripts/search-sim.ts:155 |
+| `lineageEdits` | planned | doc: docs/search-ledger.md |
+| `lineEditDistance` | production | this package: scripts/search-sim.ts:155 |
+| `META_SEARCH_SCORE_SOURCE` | production | this package: scripts/search-meta-sim.ts:52 |
+| `META_SEARCH_SIGNAL` | none | — |
+| `metaSearch` | production | this package: scripts/search-meta-sim.ts:52 |
+| `metaSearchScore` | production | this package: src/search/nested-search.ts:46 |
+| `MIN_OUTCOMES_FOR_WEIGHT` | planned | doc: docs/search-ledger.md |
+| `nearestNeighbours` | none | — |
+| `nestedSearchId` | planned | doc: docs/search-ledger.md |
+| `nextUnitExtension` | production | this package: scripts/search-sim.ts:162 |
+| `objectiveKey` | production | this package: scripts/search-meta-sim.ts:52 |
+| `operatorYield` | production | this package: scripts/prove-operator-bandit.mts:24 |
+| `profileTextLines` | none | — |
+| `rankingSplit` | production | this package: src/search/lenses/edit-credit.ts:53 |
+| `renderMetaSearchText` | production | this package: scripts/search-meta-sim.ts:52 |
+| `runNestedSearch` | production | this package: scripts/search-meta-sim.ts:58 |
+| `screenedNodes` | production | this package: src/search/lenses/landscape.ts:38 |
+| `searchConfigCodec` | planned | doc: docs/search-ledger.md |
+| `searchPlateau` | production | this package: src/search/lenses/landscape.ts:49 |
+| `searchPolicyGenome` | planned | doc: docs/search-ledger.md |
+| `skillCalibration` | production | this package: scripts/search-sim.ts:162 |
+| `skillManifold` | production | this package: scripts/search-sim.ts:162 |
+| `summarizeSamples` | production | this package: src/search/lenses/meta-search.ts:55 |
+| `surfaceDigestEdits` | none | — |
+| `surfaceTextEdits` | production | this package: src/search-command.ts:41 |
+| `taskMatrix` | production | this package: src/search-command.ts:46 |
+| `tree` | production | this package: src/search-command.ts:47 |
+| `vectorEmbedding` | planned | doc: docs/search-ledger.md |
+
 ### `./storyboard`
 
 9 value exports — 5 production, 2 planned, 2 none.
@@ -1440,7 +1508,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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:22 |
+| `runSupervisorRunCommand` | production | this package: src/cli.ts:23 |
 | `RUNTIME_FAILED_STATUS` | none | — |
 | `runtimeSupervisorRunReader` | none | only this package's tests: src/supervisor-run/index.test.ts:2 |
 | `showMeasured` | production | this package: src/supervisor-run/render.ts:8 |
@@ -1472,7 +1540,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `LLM_COST_USD` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `LLM_INPUT_TOKEN_ATTR_KEYS` | production | traces:src/file-export.ts |
 | `LLM_INPUT_TOKENS` | production | braid:src/adapters/analysis/trace-event-projection.ts |
-| `LLM_MODEL_ATTR_KEYS` | production | this package: src/contract/intake/otel-spans.ts:44 |
+| `LLM_MODEL_ATTR_KEYS` | production | this package: src/contract/intake/otel-spans.ts:45 |
 | `LLM_MODEL_NAME` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `LLM_OUTPUT_TOKEN_ATTR_KEYS` | production | traces:src/file-export.ts |
 | `LLM_OUTPUT_TOKENS` | production | braid:src/adapters/analysis/trace-event-projection.ts |
@@ -1480,12 +1548,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `LLM_REASONING_TOKENS` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `OPENINFERENCE_SPAN_KIND` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `OUTPUT_VALUE` | production | agent-runtime:src/runtime/supervise-surface.ts |
-| `RUN_COST_ATTR_KEYS` | production | this package: src/trace/execution-measurements.ts:2 |
+| `RUN_COST_ATTR_KEYS` | production | this package: src/trace/execution-measurements.ts:3 |
 | `SPAN_KIND_ATTR_KEYS` | production | traces:src/run-span-tree.ts |
-| `TOOL_ARGS_CAPTURED` | production | this package: src/trace/otlp-attributes.ts:3 |
-| `TOOL_LATENCY_MS` | production | this package: src/trace/otlp-attributes.ts:3 |
+| `TOOL_ARGS_CAPTURED` | production | this package: src/trace/otlp-attributes.ts:4 |
+| `TOOL_LATENCY_MS` | production | this package: src/trace/otlp-attributes.ts:4 |
 | `TOOL_NAME` | production | supervisor-lab:bench/analyst/rewrite-views.mts |
-| `TOOL_NAME_ATTR_KEYS` | production | this package: src/trace/otlp-attributes.ts:3 |
+| `TOOL_NAME_ATTR_KEYS` | production | this package: src/trace-analyst/behavioral-metrics.ts:13 |
 
 ### `./trace-repair`
 
@@ -1592,7 +1660,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./traces`
 
-126 value exports — 98 production, 8 planned, 20 none.
+124 value exports — 96 production, 8 planned, 20 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1610,7 +1678,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `buildTraceInsightPrompt` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/brief.ts |
 | `captureFetchToRawSink` | production | creative-agent:eval/canonical-runner.ts |
 | `classifyKey` | planned | doc: docs/redaction.md |
-| `classifyOtlpSpanRole` | production | this package: src/contract/intake/otel-spans.ts:44 |
 | `combineVerdicts` | none | — |
 | `contextInputTokens` | none | only this package's tests: tests/trace-otel.test.ts:3 |
 | `convertTraceStoresToOtlp` | planned | consumer tests: legal-agent:tests/eval/lib/traces-to-otlp.ts |
@@ -1632,7 +1699,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `FileSystemRawProviderSink` | production | agent-builder:scripts/eval.ts |
 | `FileSystemTraceStore` | production | agent-builder:scripts/eval.ts |
 | `firstNumberAttr` | production | traces:src/file-export.ts |
-| `firstStringAttr` | production | this package: src/trace-analyst/otlp-to-run-records.ts:63 |
+| `firstStringAttr` | production | this package: src/trace-analyst/otlp-to-run-records.ts:60 |
 | `flattenOtlpExportToNdjson` | production | creative-agent:eval/trace-analyst-runner.ts |
 | `groupBy` | production | this package: src/tool-use-metrics.ts:10 |
 | `hasCapturedToolArgs` | production | this package: src/pipelines/failure-cluster.ts:10 |
@@ -1642,7 +1709,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `INPUT_VALUE` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `isJudgeSpan` | production | this package: src/trace/query.ts:13 |
 | `isLlmSpan` | production | agent-runtime:src/candidate-execution/finalize.ts |
-| `isOtlpModelCall` | production | this package: src/contract/intake/otel-spans.ts:44 |
 | `isRunMetric` | none | — |
 | `isToolSpan` | production | agent-runtime:src/runtime/supervise/trace-evidence.ts |
 | `isTraceInsightArtifact` | none | — |
@@ -1658,7 +1724,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `LLM_COST_USD` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `LLM_INPUT_TOKEN_ATTR_KEYS` | production | traces:src/file-export.ts |
 | `LLM_INPUT_TOKENS` | production | braid:src/adapters/analysis/trace-event-projection.ts |
-| `LLM_MODEL_ATTR_KEYS` | production | this package: src/contract/intake/otel-spans.ts:44 |
+| `LLM_MODEL_ATTR_KEYS` | production | this package: src/contract/intake/otel-spans.ts:45 |
 | `LLM_MODEL_NAME` | production | braid:src/adapters/analysis/trace-event-projection.ts |
 | `LLM_OUTPUT_TOKEN_ATTR_KEYS` | production | traces:src/file-export.ts |
 | `LLM_OUTPUT_TOKENS` | production | braid:src/adapters/analysis/trace-event-projection.ts |
@@ -1677,14 +1743,14 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `otlpToTraceRunRecords` | none | only this package's tests: src/trace-analyst/otlp-to-run-records.test.ts:3 |
 | `OUTPUT_VALUE` | production | agent-runtime:src/runtime/supervise-surface.ts |
 | `planTraceInsightQuestions` | none | only this package's tests: src/trace-analyst/insights.test.ts:3 |
-| `projectOtlpFlatLine` | production | this package: src/trace-analyst/otlp-to-run-records.ts:63 |
+| `projectOtlpFlatLine` | production | this package: src/trace-analyst/otlp-to-run-records.ts:60 |
 | `providerFromBaseUrl` | production | this package: src/llm-client.ts:53 |
 | `redact` | production | this package: scripts/redaction-corpus.ts:9 |
 | `redactForShare` | production | this package: scripts/redaction-corpus.ts:9 |
 | `REDACTION_PROFILES` | production | this package: scripts/redaction-corpus.ts:9 |
 | `REDACTION_VERSION` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
 | `redactText` | production | this package: scripts/redaction-corpus.ts:9 |
-| `RUN_COST_ATTR_KEYS` | production | this package: src/trace/execution-measurements.ts:2 |
+| `RUN_COST_ATTR_KEYS` | production | this package: src/trace/execution-measurements.ts:3 |
 | `RUN_METRICS` | none | — |
 | `runFailureClass` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
 | `RunIntegrityError` | production | creative-agent:eval/canonical-runner.ts |
@@ -1697,10 +1763,10 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `stringField` | planned | named in agent-dev-container (bind not in the import graph) |
 | `throwIfRunIncomplete` | none | only this package's tests: tests/run-integrity.test.ts:3 |
 | `tokenizeDomainWords` | planned | consumer tests: blueprint-agent:scripts/experiments/__tests__/analyze-vb-run.test.ts |
-| `TOOL_ARGS_CAPTURED` | production | this package: src/trace/otlp-attributes.ts:3 |
-| `TOOL_LATENCY_MS` | production | this package: src/trace/otlp-attributes.ts:3 |
+| `TOOL_ARGS_CAPTURED` | production | this package: src/trace/otlp-attributes.ts:4 |
+| `TOOL_LATENCY_MS` | production | this package: src/trace/otlp-attributes.ts:4 |
 | `TOOL_NAME` | production | supervisor-lab:bench/analyst/rewrite-views.mts |
-| `TOOL_NAME_ATTR_KEYS` | production | this package: src/trace/otlp-attributes.ts:3 |
+| `TOOL_NAME_ATTR_KEYS` | production | this package: src/trace-analyst/behavioral-metrics.ts:13 |
 | `toolSpans` | production | this package: src/pipelines/failure-cluster.ts:10 |
 | `toolSpansToTraceAnalysisStore` | production | agent-runtime:src/runtime/supervise/trace-evidence.ts |
 | `ToolTraceMissingError` | none | only this package's tests: src/trace-analyst/store-tool-spans.test.ts:10 |
@@ -1785,7 +1851,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
-| `buildOpenApi` | production | this package: src/cli.ts:24 |
+| `buildOpenApi` | production | this package: src/cli.ts:25 |
 | `createApp` | planned | doc: docs/wire-protocol.md |
 | `dispatchRpc` | planned | doc: docs/wire-protocol.md |
 | `ErrorResponseSchema` | production | this package: src/wire/openapi.ts:15 |
@@ -1796,7 +1862,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `handleJudge` | production | this package: src/wire/rpc.ts:15 |
 | `handleListRubrics` | production | this package: src/wire/rpc.ts:15 |
 | `handleTracesIngest` | production | this package: src/wire/server.ts:20 |
-| `handleVersion` | production | this package: src/cli.ts:23 |
+| `handleVersion` | production | this package: src/cli.ts:24 |
 | `hashRubric` | production | this package: src/wire/handlers.ts:22 |
 | `HealthResponseSchema` | production | this package: src/wire/openapi.ts:15 |
 | `JudgeRequestSchema` | production | this package: src/wire/openapi.ts:15 |
@@ -1806,10 +1872,10 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `RUBRIC_VERSION_SCHEME` | none | — |
 | `RubricDimensionSchema` | none | only this package's tests: tests/wire/schemas.test.ts:12 |
 | `RubricSchema` | none | only this package's tests: tests/wire/schemas.test.ts:12 |
-| `runRpcBatch` | production | this package: src/cli.ts:25 |
-| `runRpcOnce` | production | this package: src/cli.ts:25 |
+| `runRpcBatch` | production | this package: src/cli.ts:26 |
+| `runRpcOnce` | production | this package: src/cli.ts:26 |
 | `startServer` | production | creative-agent:eval/ingestion-server.ts |
-| `startServerAsync` | production | this package: src/cli.ts:26 |
+| `startServerAsync` | production | this package: src/cli.ts:27 |
 | `TraceEventSchema` | planned | named in insurance-agent (bind not in the import graph) |
 | `TracesIngestRequestSchema` | production | this package: src/wire/openapi.ts:15 |
 | `TracesIngestResponseSchema` | production | this package: src/wire/openapi.ts:15 |