@tangle-network/agent-eval 0.189.0 → 0.190.0

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 | 28 |
-| published value exports (subpath x symbol) | 1416 |
-| distinct symbols | 1240 |
-| production | 941 |
-| planned | 239 |
-| none | 236 |
+| export subpaths | 32 |
+| published value exports (subpath x symbol) | 1496 |
+| distinct symbols | 1309 |
+| production | 975 |
+| planned | 269 |
+| none | 252 |
 
 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
 
 ### `.`
 
-348 value exports — 273 production, 35 planned, 40 none.
+360 value exports — 277 production, 42 planned, 41 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -120,6 +120,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertServedModel` | production | creative-agent:eval/lib/persona-driver.ts |
 | `assertServedModels` | planned | doc: docs/building-doctrine.md |
 | `assertSingleBackend` | planned | consumer tests: gtm-agent:tests/agent-eval.smoke.test.ts |
+| `assessShareSafety` | production | this package: scripts/redaction-corpus.ts:9 |
 | `assignFeedbackSplit` | production | agent-builder:src/lib/.server/eval/feedback/feedback-capture.ts |
 | `attest` | production | this package: src/experiment/evidence-receipt.ts:14 |
 | `ATTESTATION_ALGORITHM` | planned | doc: docs/eval-surface-map.md |
@@ -151,11 +152,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `checkTraceContracts` | production | creative-agent:eval/lib/trace-contracts.ts |
 | `clamp01` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/executor.ts |
 | `classifyFailure` | production | phony:products/builder/api/src/eval/autoresearch/trace-analyst.ts |
-| `classifyFailureReason` | none | only this package's tests: tests/failure-taxonomy.test.ts:2 |
+| `classifyFailureReason` | production | this package: src/diagnosis/first-failure.ts:28 |
 | `cliffsDelta` | production | agent-builder:src/lib/.server/eval/loops/differential-eval.ts |
 | `CODING_HARNESSES` | production | agent-runtime:src/runtime/define-leaderboard.ts |
 | `cohensD` | production | starter-foundry:examples/recruiter-eval-workspace/eval/src/eval/regression/gate.ts |
 | `comparePairedArms` | production | agent-knowledge:src/memory/experiment/learning-metrics.ts |
+| `compileTraceContractSpec` | planned | doc: README.md |
 | `completionVerdict` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/scoreboard-core.ts |
 | `computeExperimentStats` | production | blueprint-agent:scripts/experiments/lib/vb-improve-harness.ts |
 | `computeFindingId` | production | agent-runtime:src/runtime/index.ts |
@@ -191,12 +193,11 @@ 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:19 |
+| `DECISION_PAIRED_DELTA_STATISTIC` | production | this package: src/campaign/estimate-node.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 | — |
 | `DEFAULT_RED_TEAM_CORPUS` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
-| `DEFAULT_REDACTION_RULES` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
 | `DEFAULT_TRACE_ANALYST_BUDGETS` | production | agent-builder:src/lib/.server/eval/stores/d1-trace-analysis-store-adapter.ts |
 | `DEFAULT_TRACE_ANALYST_KINDS` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
 | `DEFAULT_TRACE_ANALYST_OUTPUT_TOKENS` | production | this package: src/analyst/chat-trace-engine.ts:46 |
@@ -222,7 +223,9 @@ 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/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 |
 | `exportProductBenchmarkRuns` | production | creative-agent:eval/research-package.ts |
 | `exportRunAsOtlp` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
@@ -265,7 +268,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `InMemoryTraceStore` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
 | `interpretCliffs` | production | agent-builder:src/lib/.server/eval/loops/differential-eval.ts |
 | `interRaterReliability` | production | agent-app:src/eval-campaign/trust-gate.ts |
-| `iqr` | production | this package: src/experiment-tracker.ts:27 |
+| `iqr` | production | this package: src/improvement-verdict.ts:23 |
 | `isBinaryOutcomeVector` | none | only this package's tests: src/statistics/paired-binary.test.ts:2 |
 | `isJudgeSpan` | production | this package: src/trace/query.ts:13 |
 | `isLlmSpan` | production | agent-runtime:src/candidate-execution/finalize.ts |
@@ -283,6 +286,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `judgeSpans` | production | this package: src/builder-eval/three-layer-eval.ts:25 |
 | `knowledgeReadinessTracePayload` | production | agent-dev-container:products/intelligence/api/src/routes/project-engines.ts |
 | `leaderboard` | production | blueprint-agent:scripts/experiments/lib/cross-harness-leaderboard.ts |
+| `lintTraceContractSpec` | planned | doc: docs/trace-contracts.md |
 | `LlmCallError` | production | agent-dev-container:products/intelligence/api/src/lib/router-model-owner.ts |
 | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
 | `LlmResponseError` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
@@ -325,7 +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` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
+| `pairedPromotionPower` | planned | doc: docs/design/statistics-decisions.md |
 | `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 |
@@ -339,6 +343,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `parseRunRecordSafe` | production | gtm-agent:scripts/canonical-completeness/records.ts |
 | `partialCredit` | planned | doc: docs/design/statistics-decisions.md |
 | `partitionHeldOut` | production | blueprint-agent:scripts/experiments/calibrate-instrument.ts |
+| `partitionTrainSelectionTest` | none | only this package's tests: src/partition-held-out.test.ts:2 |
 | `passAtK` | planned | doc: docs/design/statistics-decisions.md |
 | `pearsonR` | production | this package: src/builder-eval/correlation.ts:18 |
 | `POLICY_EDIT_AXES` | none | — |
@@ -359,24 +364,27 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `readProductBenchmarkManifest` | production | creative-agent:eval/research-package.ts |
 | `recordRuns` | planned | consumer tests: tax-agent:tests/eval/benchmarks/taxcalc/analyze.mjs |
 | `recordRunsToScorecard` | production | ai-trading-blueprint:evals/src/trading/persona-agent-eval.ts |
+| `redact` | production | this package: scripts/redaction-corpus.ts:9 |
+| `redactForShare` | production | this package: scripts/redaction-corpus.ts:9 |
 | `REDACTION_VERSION` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
-| `redactString` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
+| `redactText` | production | this package: scripts/redaction-corpus.ts:9 |
 | `redTeamDataset` | production | creative-agent:eval/red-team.ts |
 | `redTeamReport` | production | creative-agent:eval/red-team.ts |
 | `regexMatches` | none | only this package's tests: src/oracle.test.ts:2 |
 | `renderPreferenceMemoryMarkdown` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
 | `repeatedActionDetector` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
 | `requiredPairedSampleSize` | production | discovery-lab:tools/design-gate.mjs |
-| `requiredPairsForPairedPromotion` | production | discovery:research/e1-topology-20260920/gate/gate.mjs |
+| `requiredPairsForPairedPromotion` | planned | doc: docs/design/statistics-decisions.md |
 | `requiredSampleSize` | planned | doc: docs/design/statistics-decisions.md |
 | `resolveModelPricing` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-primitives.ts |
 | `resolveSeat` | production | creative-agent:eval/agent.config.ts |
-| `roundTripRunRecord` | none | none |
+| `roundTripRunRecord` | none | — |
 | `routeFields` | none | only this package's tests: src/hidden-criteria-grading.test.ts:4 |
 | `runAgentControlLoop` | production | agent-runtime:src/run.ts |
 | `runBoundedProcess` | production | this package: src/command-runner.ts:28 |
 | `runCampaign` | production | agent-app:src/eval-campaign/index.ts |
 | `runCanaries` | production | agent-builder:src/lib/.server/eval/loops/canary-cron.ts |
+| `runCostFloorUsd` | none | — |
 | `runCounterfactual` | production | traces:src/replay-batch.ts |
 | `runEquivalenceCheck` | planned | example: examples/verify-without-an-answer-key/index.ts:13 |
 | `runEvalCampaign` | production | agent-builder:scripts/eval.ts |
@@ -394,11 +402,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `scorePolicyEditReadiness` | none | — |
 | `scoreRedTeamOutput` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-gate.ts |
 | `scoreTraceInsightReadiness` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
+| `searchCellRunId` | production | this package: src/campaign/search-ledger-recording.ts:24 |
 | `seatPresets` | production | supervisor-lab:bench/comms/judges.ts |
 | `selfImprove` | production | agent-app:src/eval-campaign/index.ts |
 | `SEMANTIC_CONCEPT_JUDGE_VERSION` | production | blueprint-agent:scripts/experiments/lib/semantic-audit.ts |
 | `ServedCrossFamilyError` | none | only this package's tests: src/integrity/served-model.test.ts:2 |
 | `servedModelAcceptable` | production | this package: src/integrity/preflight.ts:33 |
+| `shareAllowed` | planned | doc: docs/redaction.md |
 | `spearmanR` | production | blueprint-agent:scripts/experiments/lib/benchmark-validity-report.mjs |
 | `stripFencedJson` | production | blueprint-agent:scripts/experiments/compare-analysis-reports.ts |
 | `subjectiveEval` | production | creative-agent:eval/control/creative-onboarding.ts |
@@ -598,13 +608,14 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./benchmarks`
 
-12 value exports — 2 production, 9 planned, 1 none.
+14 value exports — 2 production, 10 planned, 2 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `BENCHMARK_SPLIT_SEED` | production | tuner-agent:src/lib/eval-benchmarks.ts |
 | `buildStandardRetrievalItems` | planned | doc: examples/benchmarks/README.md |
 | `calibrateBenchmarkMetric` | planned | doc: examples/benchmarks/README.md |
+| `createHarborBenchmarkAdapter` | planned | doc: examples/benchmarks/README.md |
 | `createRetrievalIdBenchmarkAdapter` | planned | doc: examples/benchmarks/README.md |
 | `deterministicSplit` | production | tuner-agent:src/lib/eval-benchmarks.ts |
 | `evaluateStandardRetrieval` | planned | doc: examples/benchmarks/README.md |
@@ -612,6 +623,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `parseBeirQueriesJsonl` | planned | doc: examples/benchmarks/README.md |
 | `parseJsonlRows` | none | only this package's tests: tests/benchmarks.test.ts:8 |
 | `parseQrels` | planned | doc: examples/benchmarks/README.md |
+| `readHarborTask` | none | — |
 | `routing` | planned | doc: docs/building-doctrine.md |
 | `runBenchmarkAdapter` | planned | doc: examples/benchmarks/README.md |
 
@@ -630,7 +642,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./campaign`
 
-124 value exports — 80 production, 18 planned, 26 none.
+143 value exports — 91 production, 26 planned, 26 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -640,7 +652,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertCampaignSplitIdentity` | production | agent-knowledge:src/memory/experiment/learning-pairs.ts |
 | `assertCodeSurfaceIdentity` | none | — |
 | `assertCompleteSearchHistory` | production | this package: src/campaign/optimization-method.ts:14 |
-| `assertSearchHistoryMatchesReplay` | planned | doc: docs/search-history-receipts.md |
+| `assertSearchHistoryMatchesState` | planned | doc: docs/search-ledger.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 |
 | `buildEvidenceVector` | planned | doc: docs/experiment.md |
@@ -665,18 +677,22 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `createProfileMatrixPlan` | production | discovery-lab:tools/run-profile-confirmation.mjs |
 | `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:21 |
+| `createSearchHistoryReceipt` | production | this package: src/campaign/search-ledger-recording.ts:26 |
 | `crowdedFrontierParent` | planned | doc: docs/campaign-proposers.md |
 | `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 |
 | `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 |
+| `externalSurface` | none | — |
 | `externalTextOptimizationMethod` | production | agent-app:src/eval-campaign/index.ts |
-| `FileSearchLedger` | none | — |
+| `FileSearchLedger` | planned | doc: docs/search-ledger.md |
 | `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) |
@@ -684,6 +700,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `gitWorktreeAdapter` | production | agent-runtime:src/improvement/code-execution.ts |
 | `heldOutGate` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-gate.ts |
 | `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 |
 | `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 |
@@ -699,7 +717,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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-optimization-method.ts:66 |
+| `openSearchLedger` | production | this package: src/campaign/gepa-search-import.ts:22 |
 | `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 |
@@ -715,10 +733,10 @@ 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 |
-| `recordCandidatePopulationSearch` | production | this package: src/campaign/gepa-optimization-method.ts:67 |
+| `recordGepaSearch` | production | this package: src/campaign/gepa-optimization-method.ts:58 |
 | `renderScoreboardMarkdown` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
 | `renderSurfaceDiff` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-evidence-packet.ts |
-| `replaySearchLedgerText` | production | this package: src/campaign/search-history-receipt.ts:9 |
+| `replaySearchLedgerText` | production | this package: src/campaign/search-history-receipt.ts:5 |
 | `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 |
@@ -734,29 +752,42 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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_ESTIMATOR` | planned | doc: docs/search-ledger.md |
+| `SEARCH_LEDGER_SCHEMA` | production | this package: src/campaign/search-ledger.ts:40 |
+| `searchCellId` | production | this package: src/campaign/search-ledger-recording.ts:56 |
+| `searchCellSetDigest` | planned | doc: docs/search-ledger.md |
+| `searchEdgeId` | planned | doc: docs/search-ledger.md |
 | `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 |
+| `SearchHistoryRequiredError` | none | — |
+| `SearchLedgerConflictError` | production | this package: src/campaign/search-ledger.ts:33 |
+| `SearchLedgerError` | production | this package: src/campaign/estimate-node.ts:20 |
 | `SearchLedgerIntegrityError` | production | this package: src/campaign/search-ledger-file.ts:10 |
-| `SearchRecorder` | production | this package: src/campaign/presets/run-optimization.ts:38 |
+| `searchNodeId` | production | this package: src/campaign/search-ledger-recording.ts:56 |
+| `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:47 |
+| `SearchStateView` | production | this package: src/campaign/estimate-node.ts:28 |
+| `searchTaskSetDigest` | production | this package: src/campaign/search-ledger-recording.ts:56 |
+| `searchUnitScores` | production | this package: src/campaign/estimate-node.ts:28 |
 | `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 |
+| `surfaceDiff` | production | this package: src/campaign/gepa-search-import.ts:23 |
 | `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 |
 | `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 |
 | `userStoryScoreboard` | production | blueprint-agent:scripts/experiments/eval/launch-scoreboard/run.ts |
-| `validateSearchLedgerEvent` | planned | consumer tests: discovery-lab:tools/search-ledger-planless.test.mjs |
+| `validateSearchLedgerEvent` | production | this package: src/campaign/search-ledger-recording.ts:27 |
 | `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:14 |
-| `verifySearchHistoryReceipt` | planned | doc: docs/search-history-receipts.md |
+| `verifySearchHistoryReceipt` | planned | doc: docs/search-ledger.md |
 | `WorktreeAdapterError` | none | only this package's tests: tests/campaign/worktree.test.ts:17 |
 
 ### `./contract`
@@ -831,9 +862,36 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `verifyCandidateExperiment` | production | agent-runtime:src/intelligence/improvement-cycle.ts |
 | `verifyCandidateExperimentComparison` | production | agent-runtime:src/intelligence/improvement-cycle.ts |
 
+### `./diagnosis`
+
+10 value exports — 4 production, 1 planned, 5 none.
+
+| symbol | consumer | evidence |
+| --- | --- | --- |
+| `DEFAULT_MAX_MODEL_TRACES` | none | — |
+| `diagnoseSpans` | planned | doc: docs/diagnosis.md |
+| `DIAGNOSIS_FINDINGS_SCHEMA_ID` | none | — |
+| `epochMillis` | none | only this package's tests: src/diagnosis/diagnosis.test.ts:4 |
+| `ingestSpans` | production | this package: src/diagnosis/engine.ts:38 |
+| `isContentAttribute` | none | — |
+| `MAX_FIRST_FAILURE_IDS` | none | — |
+| `nodeHttpPrimeBridgeTransport` | production | this package: src/analyst/benchmark-runner-prime.ts:18 |
+| `rankFirstFailure` | production | this package: src/diagnosis/deterministic.ts:22 |
+| `validateDiagnosisFindings` | production | this package: src/diagnosis/engine.ts:23 |
+
+### `./evaluation`
+
+3 value exports — 3 production, 0 planned, 0 none.
+
+| symbol | consumer | evidence |
+| --- | --- | --- |
+| `asAnalyst` | production | this package: src/jev.ts:5 |
+| `asJudge` | production | this package: src/jev.ts:5 |
+| `createEvaluator` | production | this package: src/jev.ts:5 |
+
 ### `./experiment`
 
-89 value exports — 55 production, 17 planned, 17 none.
+91 value exports — 53 production, 20 planned, 18 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -854,6 +912,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
+| `decideRandomizedCanary` | planned | doc: docs/experiment.md |
 | `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 |
@@ -873,8 +932,6 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `evidenceRegistryRecordSchema` | none | — |
 | `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 |
@@ -882,8 +939,8 @@ 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 |
 | `holm` | planned | doc: docs/design/statistics-decisions.md |
 | `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 |
+| `joinProspectiveCanaryReceipts` | planned | doc: docs/experiment.md |
 | `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 | blueprint-agent:scripts/experiments/analyze-convergence.ts |
@@ -906,6 +963,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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:20 |
+| `randomizedCanaryObservationDigest` | none | only this package's tests: src/experiment/prospective-canary-join.test.ts:2 |
+| `randomizedCanaryRosterDigest` | none | only this package's tests: src/experiment/prospective-canary-join.test.ts:2 |
 | `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 |
@@ -915,6 +974,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
+| `sealRandomizedCanaryRule` | planned | doc: docs/experiment.md |
 | `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 |
@@ -966,6 +1026,38 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `TraceSpanEventSchema` | planned | example: examples/hosted-ingest-server/server.ts:33 |
 | `UnixNanoTimestampSchema` | none | — |
 
+### `./jev`
+
+14 value exports — 6 production, 7 planned, 1 none.
+
+| symbol | consumer | evidence |
+| --- | --- | --- |
+| `asAnalyst` | production | this package: src/jev.ts:5 |
+| `asJudge` | production | this package: src/jev.ts:5 |
+| `assessJevReview` | planned | doc: docs/changes/jev-evidence-review.md |
+| `createEvaluator` | production | this package: src/jev.ts:5 |
+| `jevAnalyst` | planned | example: examples/jev-behavior-review.ts:3 |
+| `jevEvaluator` | planned | doc: docs/jev-behavior-review.md |
+| `jevJudge` | planned | example: examples/jev-product-integrity.ts:4 |
+| `JevResponseError` | none | — |
+| `jevReviewFindings` | planned | example: examples/jev-behavior-review.ts:3 |
+| `jevUsage` | production | this package: src/jev.ts:7 |
+| `normalizedJevScore` | planned | doc: docs/jev.md |
+| `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.
+
+| symbol | consumer | evidence |
+| --- | --- | --- |
+| `JevResponseError` | none | — |
+| `jevUsage` | 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`
 
 17 value exports — 16 production, 0 planned, 1 none.
@@ -974,19 +1066,19 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | --- | --- | --- |
 | `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.ts:5 |
-| `FileLedgerJournal` | production | this package: src/campaign/search-ledger.ts:22 |
+| `canonicalString` | production | this package: src/agent-profile-cell.ts:3 |
+| `FileLedgerJournal` | production | this package: src/campaign/search-ledger.ts:23 |
 | `hashCanonical` | production | discovery-lab:tools/provenance.mjs |
-| `jsonDocument` | production | this package: src/analyst/benchmark-command-artifact.ts:2 |
+| `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 |
 | `probeAtomicFileLock` | production | this package: src/campaign/single-run-lock.ts:17 |
-| `readTrustedHeadFile` | production | this package: src/ledger-core/journal.ts:29 |
-| `replayLedgerText` | production | this package: src/campaign/search-ledger.ts:22 |
-| `trustedHeadPathFor` | production | this package: src/ledger-core/journal.ts:29 |
+| `readTrustedHeadFile` | production | this package: src/ledger-core/journal.ts:40 |
+| `replayLedgerText` | production | this package: src/campaign/search-ledger.ts:23 |
+| `trustedHeadPathFor` | production | this package: src/ledger-core/journal.ts:40 |
 | `tryAcquireAtomicFileLock` | production | this package: src/campaign/single-run-lock.ts:17 |
 | `tryWithLedgerFileLock` | production | this package: src/campaign/search-ledger-file.ts:3 |
-| `verifyEntriesAgainstTrustedHead` | production | this package: src/ledger-core/journal.ts:29 |
+| `verifyEntriesAgainstTrustedHead` | production | this package: src/ledger-core/journal.ts:40 |
 | `withLedgerFileLock` | production | this package: src/analyst/benchmark-response-cache.ts:6 |
 | `writeLedgerFileAtomically` | production | this package: src/analyst/benchmark-response-cache.ts:6 |
 
@@ -1002,11 +1094,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./meta-eval`
 
-27 value exports — 13 production, 13 planned, 1 none.
+28 value exports — 13 production, 14 planned, 1 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `auditEvaluator` | planned | example: examples/evaluation-integrity/index.ts:15 |
+| `auditProbabilityPolicy` | planned | doc: docs/changes/probability-policy-audit.md |
 | `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 |
@@ -1089,14 +1182,16 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./pipelines`
 
-8 value exports — 6 production, 0 planned, 2 none.
+10 value exports — 6 production, 0 planned, 4 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `budgetBreachView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
 | `computeToolUseMetrics` | production | traces:src/pipelines.ts |
+| `diffSteps` | none | — |
+| `diffStepsFromSpans` | none | — |
 | `failureClusterView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
-| `firstDivergenceView` | none | only this package's tests: src/pipelines/first-divergence.test.ts:4 |
+| `firstDivergenceView` | none | only this package's tests: tests/pipelines.test.ts:2 |
 | `judgeAgreementView` | production | insurance-agent:scripts/analyze-agent-eval-evidence.ts |
 | `regressionView` | none | only this package's tests: src/pipelines/regression.test.ts:4 |
 | `stuckLoopView` | production | agent-runtime:src/runtime/supervise/trajectory-recorder.ts |
@@ -1104,14 +1199,14 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./profile-cell`
 
-12 value exports — 5 production, 3 planned, 4 none.
+12 value exports — 5 production, 4 planned, 3 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `AGENT_PROFILE_KINDS` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
 | `agentProfileCellHashMaterial` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/agent-profile-cell.test.ts |
 | `agentProfileCellKey` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/agent-profile-cell.test.ts |
-| `AgentProfileCellValidationError` | none | only this package's tests: tests/agent-profile-cell.test.ts:3 |
+| `AgentProfileCellValidationError` | planned | doc: docs/profile-json-identity.md |
 | `assertRunAgentProfileCell` | none | only this package's tests: tests/agent-profile-cell.test.ts:3 |
 | `buildAgentInterfaceProfileCell` | none | only this package's tests: tests/agent-profile-cell.test.ts:3 |
 | `buildAgentProfileCell` | production | ai-trading-blueprint:evals/src/trading/agent-profile-cell.ts |
@@ -1211,7 +1306,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `toTRLFormat` | production | blueprint-agent:scripts/experiments/lib/steering-dataset.ts |
 | `validateDatasetFormats` | planned | example: examples/publish-rl-dataset/build-dataset.ts:30 |
 | `varianceBasedCurriculum` | production | this package: src/fuzz/explorer.ts:18 |
-| `verificationReportToRunRecord` | none | none |
+| `verificationReportToRunRecord` | none | — |
 | `VERIFIED_FINDING_SCHEMA` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
 | `verifiedFindingsToJsonl` | none | only this package's tests: src/rl/verified-findings-dataset.test.ts:5 |
 
@@ -1270,7 +1365,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
+| `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 |
 | `scrubText` | none | only this package's tests: src/rollout/release/scrub.test.ts:4 |
@@ -1482,7 +1577,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./traces`
 
-115 value exports — 94 production, 7 planned, 14 none.
+126 value exports — 98 production, 8 planned, 20 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1493,23 +1588,26 @@ 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 |
 | `asNumber` | planned | named in agent-app (bind not in the import graph) |
 | `assertRunCaptured` | production | creative-agent:eval/canonical-runner.ts |
+| `assessShareSafety` | production | this package: scripts/redaction-corpus.ts:9 |
 | `asString` | planned | named in agent-app (bind not in the import graph) |
 | `buildTraceAnalysisToolDescriptors` | production | this package: src/analyst/tool-groups.ts:14 |
 | `buildTraceInsightContext` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
 | `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 |
 | `createBoundedTraceAnalysisStore` | production | braid:src/adapters/analysis/trace-store.ts |
-| `createOtelExporter` | planned | doc: docs/adapters-observability.md |
-| `createOtelTracingStore` | none | only this package's tests: tests/trace-contracts.test.ts:4 |
-| `DEFAULT_REDACTION_RULES` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
 | `DEFAULT_TRACE_ANALYST_BUDGETS` | production | agent-builder:src/lib/.server/eval/stores/d1-trace-analysis-store-adapter.ts |
 | `defaultProviderRedactor` | production | this package: src/llm-client.ts:53 |
 | `defaultTraceInsightPanel` | none | only this package's tests: src/trace-analyst/insights.test.ts:3 |
 | `describeTraceInsightScope` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html.ts |
+| `detectCredential` | production | this package: scripts/redaction-corpus.ts:9 |
+| `detectPersonalData` | production | this package: scripts/redaction-corpus.ts:9 |
 | `domainEvidencePattern` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/session-loader.ts |
+| `emptyRedactionReport` | production | this package: src/diagnosis/spans.ts:22 |
 | `exportRunAsOtlp` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
 | `extractOtlpAttributes` | production | this package: src/trace-analyst/store-otlp.ts:40 |
 | `extractUsage` | production | this package: src/contract/intake/code-agent-session.ts:12 |
@@ -1532,6 +1630,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 | — |
+| `isTraceInsightAttribution` | none | only this package's tests: src/trace-analyst/insights-attribution.test.ts:4 |
+| `isTraceInsightEvidence` | none | — |
 | `judgeSpans` | production | this package: src/builder-eval/three-layer-eval.ts:25 |
 | `LLM_CACHE_WRITE_TOKEN_ATTR_KEYS` | production | traces:src/file-export.ts |
 | `LLM_CACHE_WRITE_TOKENS` | production | traces:src/adapters/claude.ts |
@@ -1550,8 +1651,9 @@ 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 |
 | `llmSpans` | production | phony:products/builder/api/src/eval/replay.ts |
 | `NoopRawProviderSink` | production | agent-dev-container:products/intelligence/api/src/lib/eval-engine.ts |
+| `normalizeKey` | none | — |
 | `OPENINFERENCE_SPAN_KIND` | production | braid:src/adapters/analysis/trace-event-projection.ts |
-| `OTEL_AGENT_EVAL_SCOPE` | production | this package: src/trace/otel-export.ts:10 |
+| `OTEL_AGENT_EVAL_SCOPE` | none | — |
 | `OtlpFileTraceStore` | production | agent-builder:scripts/run-canonical-analyst-loop.ts |
 | `otlpRowsToRunRecords` | production | traces:src/execution.ts |
 | `otlpRowsToTraceRunRecords` | none | — |
@@ -1562,9 +1664,11 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
 | `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 |
-| `redactString` | production | agent-dev-container:products/intelligence/api/src/lib/redact.ts |
-| `redactValue` | production | traces:src/index.ts |
+| `redactText` | production | this package: scripts/redaction-corpus.ts:9 |
 | `RUN_COST_ATTR_KEYS` | production | this package: src/trace/execution-measurements.ts:2 |
 | `RUN_METRICS` | none | — |
 | `runFailureClass` | production | starter-foundry:registry/layers/agent-eval/redteam/files/src/eval/redteam/runner.ts |
@@ -1572,6 +1676,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `runMetricExtractor` | production | this package: src/meta-eval/calibration.ts:10 |
 | `runsForScenario` | production | phony:products/builder/api/src/eval/gate.ts |
 | `scoreTraceInsightReadiness` | production | blueprint-agent:scripts/experiments/lib/analyze-vb-run/report-html-sections.ts |
+| `shareAllowed` | planned | doc: docs/redaction.md |
 | `SPAN_KIND_ATTR_KEYS` | production | traces:src/run-span-tree.ts |
 | `SpanNotFoundError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
 | `stringField` | planned | named in agent-dev-container (bind not in the import graph) |
@@ -1587,24 +1692,25 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `TRACE_ANALYSIS_LIMITS` | production | this package: src/analyst/benchmark-evidence-validation.ts:1 |
 | `TRACE_ANALYST_ACTOR_DESCRIPTION` | production | this package: src/trace-analyst/analyst.ts:11 |
 | `TRACE_ANALYST_ACTOR_DESCRIPTION_VERSION` | production | this package: src/trace-analyst/analyst.ts:11 |
-| `TRACE_ANALYST_TOOL_NAMESPACE` | none | only this package's tests: src/trace-analyst/tools.test.ts:4 |
+| `TRACE_ANALYST_TOOL_NAMESPACE` | none | — |
 | `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-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 |
+| `traceAnalystFunctionGroup` | none | — |
 | `traceAnalystOnRunComplete` | planned | named in creative-agent (bind not in the import graph) |
 | `TraceEmitter` | production | agent-builder:src/lib/.server/runtime/trace-runtime.ts |
 | `TraceFileMalformedError` | production | this package: src/trace-analyst/store-otlp.ts:31 |
 | `TraceFileMissingError` | production | this package: src/trace-analyst/store-otlp.ts:31 |
 | `TraceFileTooLargeError` | production | this package: src/trace-analyst/store-otlp.ts:31 |
 | `TraceNotFoundError` | production | this package: src/trace-analyst/store-boundary.ts:1 |
-| `traceSpanKindToOpenInferenceKind` | production | this package: src/trace/otel-export.ts:11 |
+| `traceSpanKindToOpenInferenceKind` | production | this package: src/trace/otel.ts:12 |
+| `UNTRUSTED_TRACE_TEXT` | none | — |
 
 ### `./trajectory-replay`
 
-49 value exports — 28 production, 16 planned, 5 none.
+49 value exports — 29 production, 16 planned, 4 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1619,37 +1725,37 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `decodeRecordedTurns` | production | this package: scripts/tb-corpus-rows.ts:29 |
 | `derivedImageTag` | planned | named in traces (bind not in the import graph) |
 | `deriveFailureSignature` | production | this package: src/trace-repair/grade.ts:25 |
-| `dockerImagePreparer` | production | this package: src/trajectory-replay/batch.ts:42 |
-| `enumerateReplayableCases` | production | this package: src/trajectory-replay/batch.ts:33 |
+| `dockerImagePreparer` | production | this package: src/trajectory-replay/batch.ts:43 |
+| `enumerateReplayableCases` | production | this package: src/trajectory-replay/batch.ts:34 |
 | `extractFixCommand` | production | this package: src/trajectory-replay/fix-loop.ts:17 |
 | `finalRecordedOutcome` | production | this package: scripts/tb-corpus-rows.ts:29 |
 | `findingReplayStep` | planned | named in traces (bind not in the import graph) |
 | `findingTrajectoryId` | planned | named in traces (bind not in the import graph) |
 | `FORMAT_ERROR_OBSERVATION_PREFIX` | production | this package: src/trace-repair/mini-swe-scaffold.ts:17 |
-| `generateFixCommand` | production | this package: src/trajectory-replay/batch.ts:40 |
+| `generateFixCommand` | production | this package: src/trajectory-replay/batch.ts:41 |
 | `goldIncorrectSteps` | planned | named in traces (bind not in the import graph) |
-| `ingestRecordedTrajectory` | production | this package: src/trajectory-replay/batch.ts:43 |
+| `ingestRecordedTrajectory` | production | this package: src/trajectory-replay/batch.ts:44 |
 | `isElidedField` | none | only this package's tests: tests/trajectory-replay/steps.test.ts:7 |
 | `isRecordedTimeout` | production | this package: scripts/tb-repair-milestone1.ts:68 |
-| `isSubmitAction` | production | this package: src/trajectory-replay/corpus.ts:19 |
-| `isSubmitOnlyAction` | none | only this package's tests: tests/trajectory-replay/steps.test.ts:7 |
+| `isSubmitAction` | production | this package: src/trajectory-replay/findings.ts:39 |
+| `isSubmitOnlyAction` | production | this package: src/trajectory-replay/corpus.ts:19 |
 | `parseCorpusFlag` | planned | named in traces (bind not in the import graph) |
 | `parseIncorrectStepsSubject` | production | this package: src/trajectory-replay/findings.ts:41 |
 | `parseObservationOutput` | production | this package: src/trajectory-replay/corpus.ts:19 |
 | `parseRecordedReturncode` | production | this package: scripts/tb-gated-stop-ab.ts:77 |
-| `PREFIX_DIVERGENCE_TOLERANCE_PCT` | production | this package: src/trajectory-replay/batch.ts:43 |
+| `PREFIX_DIVERGENCE_TOLERANCE_PCT` | production | this package: src/trajectory-replay/batch.ts:44 |
 | `readFindingsFile` | planned | named in traces (bind not in the import graph) |
 | `readLabelEntries` | planned | named in traces (bind not in the import graph) |
 | `renderBatchReport` | planned | named in traces (bind not in the import graph) |
 | `renderVerifiedFindingsSection` | planned | named in traces (bind not in the import graph) |
-| `replayVerify` | production | this package: src/trajectory-replay/batch.ts:43 |
+| `replayVerify` | production | this package: src/trajectory-replay/batch.ts:44 |
 | `replayVerifyFinding` | planned | doc: docs/trajectory-replay.md |
 | `resolveCaseResources` | production | this package: src/trajectory-replay/findings.ts:36 |
 | `resolveFindingInvocation` | planned | named in traces (bind not in the import graph) |
 | `resolveFindingReplayability` | planned | named in traces (bind not in the import graph) |
-| `runFixLoop` | production | this package: src/trajectory-replay/batch.ts:41 |
+| `runFixLoop` | production | this package: src/trajectory-replay/batch.ts:42 |
 | `runReplayBatch` | planned | doc: docs/trajectory-replay.md |
-| `SandboxCounterfactualRunner` | production | this package: src/trajectory-replay/batch.ts:43 |
+| `SandboxCounterfactualRunner` | production | this package: src/trajectory-replay/batch.ts:44 |
 | `seededSample` | planned | named in traces (bind not in the import graph) |
 | `SUBMIT_ACTION_SIGNATURE` | production | this package: src/trace-repair/mini-swe-scaffold.ts:17 |
 | `summarizePrefixReplay` | none | only this package's tests: tests/trajectory-replay/verify.test.ts:14 |