@tangle-network/agent-eval 0.170.0 → 0.172.0

package/docs/public-api.md

@@ -7,11 +7,11 @@ Generated by `pnpm api:census` on demand — this is a dated reading, not a gate
 | measure | count |
 | --- | --- |
 | export subpaths | 28 |
-| published value exports (subpath x symbol) | 1353 |
-| distinct symbols | 1184 |
-| production | 926 |
-| planned | 210 |
-| none | 217 |
+| published value exports (subpath x symbol) | 1378 |
+| distinct symbols | 1209 |
+| production | 931 |
+| planned | 216 |
+| none | 231 |
 
 Type-only exports are not listed: a type binds no runtime surface, and removing one cannot break a caller at run time.
 
@@ -84,11 +84,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `.`
 
-318 value exports — 267 production, 32 planned, 19 none.
+338 value exports — 271 production, 34 planned, 33 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `acquisitionPlansForKnowledgeGaps` | production | agent-builder:src/lib/.server/eval/loops/data-acquisition-engine.ts |
+| `admitPolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `AGENT_PROFILE_KINDS` | production | blueprint-agent:scripts/experiments/lib/agent-profile-cell.ts |
 | `AgentEvalError` | production | agent-runtime:src/errors.ts |
 | `agentProfileCellHashMaterial` | planned | consumer tests: blueprint-agent:scripts/experiments/lib/__tests__/agent-profile-cell.test.ts |
@@ -106,11 +107,13 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `analyzeRuns` | production | agent-builder:eval/scripts/insight-report.ts |
 | `analyzeSeries` | production | agent-dev-container:products/sandbox/evals/run.ts |
 | `analyzeTraces` | production | agent-builder:src/lib/.server/eval/analysts/canonical-trace-analyst.ts |
+| `applyPolicyEditToSurface` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `argHash` | production | agent-runtime:src/runtime/supervise/detector-monitor.ts |
 | `assertCapabilityHeadroom` | production | blueprint-agent:scripts/experiments/lib/validity-gates.ts |
 | `assertCrossFamily` | production | agent-builder:frontier/judges/artifact-head-to-head.ts |
 | `assertCrossFamilyServed` | planned | doc: docs/building-doctrine.md |
 | `assertNoHiddenLeak` | planned | doc: docs/design/statistics-decisions.md |
+| `assertNoJudgeVerdict` | production | this package: src/analyst/policy-edit.ts:6 |
 | `assertProductBenchmarkRun` | production | creative-agent:eval/research-package.ts |
 | `assertRealBackend` | production | blueprint-agent:scripts/experiments/lib/canonical/assert-real-backend.ts |
 | `assertRunCaptured` | production | creative-agent:eval/canonical-runner.ts |
@@ -118,6 +121,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertServedModels` | planned | doc: docs/building-doctrine.md |
 | `assertSingleBackend` | planned | consumer tests: gtm-agent:tests/agent-eval.smoke.test.ts |
 | `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 |
 | `BackendIntegrityError` | production | creative-agent:eval/leaderboard.ts |
 | `benjaminiHochberg` | production | agent-runtime:bench/src/corpus-report.mts |
 | `blendHeldout` | production | blueprint-agent:scripts/experiments/lib/qa-grader.ts |
@@ -153,6 +158,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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 |
+| `computePolicyEditId` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `computeToolUseMetrics` | production | traces:src/pipelines.ts |
 | `confidenceInterval` | production | agent-runtime:src/runtime/benchmark-report.ts |
 | `ConfigError` | production | agent-runtime:src/errors.ts |
@@ -256,6 +262,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `isJudgeSpan` | production | this package: src/trace/query.ts:13 |
 | `isLlmSpan` | production | agent-runtime:src/candidate-execution/finalize.ts |
 | `isModelPriced` | production | agent-dev-container:products/intelligence/api/src/lib/optimization-engine.ts |
+| `isPolicyEdit` | none | — |
 | `isRunRecord` | production | this package: src/eval-trace-store.ts:21 |
 | `isToolSpan` | production | agent-runtime:src/runtime/supervise/trace-evidence.ts |
 | `isTransientLlmError` | production | supervisor-lab:bench/comms/judges.ts |
@@ -274,6 +281,8 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `loadScorecard` | production | ai-trading-blueprint:evals/src/trading/scorecard-integration.ts |
 | `localCommandRunner` | production | blueprint-agent:scripts/experiments/lib/command-runner.ts |
 | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
+| `makePolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
+| `makePolicyEditCandidateRecord` | planned | doc: docs/campaign-proposers.md |
 | `makeProposalFinding` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
 | `manifestContentDigest` | production | this package: src/campaign/gates/sequential.ts:34 |
 | `MANN_WHITNEY_EXACT_MAX_STATES` | none | — |
@@ -322,6 +331,12 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `partitionHeldOut` | production | blueprint-agent:scripts/experiments/calibrate-instrument.ts |
 | `passAtK` | planned | doc: docs/design/statistics-decisions.md |
 | `pearsonR` | production | this package: src/builder-eval/correlation.ts:18 |
+| `POLICY_EDIT_AXES` | none | — |
+| `POLICY_EDIT_CANDIDATE_RECORD_SCHEMA` | none | — |
+| `POLICY_EDIT_TARGET_SURFACES` | none | — |
+| `policyEditFromFinding` | none | — |
+| `policyEditsFromFindings` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
+| `PolicyEditValidationError` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `preflightModels` | production | loops:src/preflight.ts |
 | `productBenchmarkRepoIdentity` | production | creative-agent:eval/research-package.ts |
 | `ProductClient` | production | creative-agent:eval/e2e/creative-product-harness.ts |
@@ -347,6 +362,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `roundTripRunRecord` | none | only this package's tests: tests/run-record.test.ts:3 |
 | `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/sandbox-harness.ts:16 |
 | `runCampaign` | production | agent-app:src/eval-campaign/index.ts |
 | `runCanaries` | production | agent-builder:src/lib/.server/eval/loops/canary-cron.ts |
 | `runCounterfactual` | production | traces:src/replay-batch.ts |
@@ -363,6 +379,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `runsForScenario` | production | phony:products/builder/api/src/eval/gate.ts |
 | `runTaskScore` | production | discovery-lab:tools/strict-screen.mjs |
 | `scoreKnowledgeReadiness` | production | agent-builder:src/lib/.server/runtime/agent-task-readiness.ts |
+| `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 |
 | `seatPresets` | production | supervisor-lab:bench/comms/judges.ts |
@@ -374,7 +391,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `stripFencedJson` | production | blueprint-agent:scripts/experiments/compare-analysis-reports.ts |
 | `subjectiveEval` | production | creative-agent:eval/control/creative-onboarding.ts |
 | `summarizeBackendIntegrity` | production | agent-dev-container:products/intelligence/api/src/lib/run-provenance.ts |
-| `summarizeNumberSeries` | production | this package: src/supervisor-run/analyze.ts:8 |
+| `summarizeNumberSeries` | production | this package: src/campaign/cell-aggregates.ts:12 |
 | `summarizePreferenceMemory` | production | agent-builder:src/lib/.server/eval/loops/auto-research-runner.ts |
 | `summaryTable` | production | blueprint-agent:scripts/experiments/vb-runrecord-analysis.ts |
 | `textInSnapshot` | none | only this package's tests: src/oracle.test.ts:2 |
@@ -389,12 +406,15 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `UNKNOWN_MODEL` | production | this package: src/campaign/presets/run-profile-matrix.ts:54 |
 | `urlContains` | none | only this package's tests: src/oracle.test.ts:2 |
 | `userQuestionsForKnowledgeGaps` | production | agent-dev-container:products/intelligence/api/src/routes/project-engines.ts |
+| `validatePolicyEdit` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
+| `validatePolicyEditCandidateRecord` | none | only this package's tests: src/analyst/policy-edit.test.ts:2 |
 | `validateRunRecord` | production | agent-builder:src/lib/.server/eval/stores/run-record-store.ts |
 | `ValidationError` | production | agent-runtime:src/errors.ts |
 | `verbosityBias` | production | blueprint-agent:scripts/experiments/calibration/judge-agreement.ts |
 | `VERIFICATION_STRATEGIES` | planned | example: examples/verify-without-an-answer-key/index.ts:13 |
 | `VERIFICATION_STRATEGY_SOURCES` | none | only this package's tests: src/verification-strategy.test.ts:11 |
 | `verifyAgentProfileCell` | production | this package: src/eval-campaign.ts:39 |
+| `verifyAttestation` | production | this package: src/experiment/evidence-receipt.ts:14 |
 | `verifyCompletion` | production | agent-app:src/eval/index.ts |
 | `viteDeployRunner` | production | blueprint-agent:scripts/experiments/lib/deploy-runner.ts |
 | `weightedComposite` | production | agent-app:src/eval/index.ts |
@@ -424,7 +444,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | --- | --- | --- |
 | `adaptPublicBenchmarkFindings` | production | this package: scripts/gepa-analyst-campaign.ts:59 |
 | `AGENT_RX_UPSTREAM_REVISION` | production | this package: src/analyst/benchmark-command-result.ts:2 |
-| `agentRxBenchmarkCase` | production | this package: src/analyst/benchmark-public-data.ts:11 |
+| `agentRxBenchmarkCase` | production | this package: src/analyst/benchmark-public-data.ts:12 |
 | `agentRxPredictionsToFindings` | production | this package: src/analyst/benchmark-public-adapters.ts:3 |
 | `ANALYST_BENCHMARK_COST_LEDGER_FILE` | production | this package: src/analyst/benchmark-command-persistence.ts:9 |
 | `ANALYST_BENCHMARK_DEPENDENCY_LOCK_DIGEST_ALGORITHM` | none | only this package's tests: src/analyst/benchmark-implementation.test.ts:7 |
@@ -446,7 +466,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `analystInstructionsOverrideFromText` | none | only this package's tests: src/analyst/benchmark-instructions-override.test.ts:5 |
 | `AnalystRegistry` | production | blueprint-agent:scripts/experiments/vb-multi-analyst.ts |
 | `analystUsageReceiptFromPrimeUsage` | production | this package: src/analyst/benchmark-runner-prime.ts:19 |
-| `appendVerificationArtifactsToOtlp` | production | this package: src/analyst/benchmark-public-data.ts:31 |
+| `appendVerificationArtifactsToOtlp` | production | this package: src/analyst/benchmark-public-data.ts:32 |
 | `assertProposalFindings` | production | agent-runtime:src/improvement/code-execution.ts |
 | `behavioralAnalyst` | production | agent-dev-container:products/intelligence/api/src/lib/deep-trace-analyst.ts |
 | `bindAnalyst` | planned | doc: docs/trace-analysis.md |
@@ -497,7 +517,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `KIND_EXPECTED_SUBJECTS` | production | this package: src/analyst/kind-factory.ts:14 |
 | `KNOWLEDGE_GAP_KIND_SPEC` | none | only this package's tests: src/analyst/finding-subject.test.ts:13 |
 | `KNOWLEDGE_POISONING_KIND_SPEC` | none | only this package's tests: src/analyst/finding-subject.test.ts:13 |
-| `loadCodeTraceVerificationArtifacts` | production | this package: src/analyst/benchmark-public-data.ts:31 |
+| `loadCodeTraceVerificationArtifacts` | production | this package: src/analyst/benchmark-public-data.ts:32 |
 | `loadPublicBenchmarkRows` | production | this package: scripts/gepa-analyst-campaign.ts:64 |
 | `makeFinding` | production | agent-dev-container:products/intelligence/api/src/lib/consultant/candidates.ts |
 | `makeProposalFinding` | production | agent-runtime:bench/src/swe-arena/outer-loop.mts |
@@ -596,7 +616,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./campaign`
 
-117 value exports — 76 production, 15 planned, 26 none.
+118 value exports — 77 production, 15 planned, 26 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -608,6 +628,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `assertCompleteSearchHistory` | production | this package: src/campaign/presets/compare-optimization-methods.ts:31 |
 | `assertSearchHistoryMatchesReplay` | planned | doc: docs/search-history-receipts.md |
 | `autoevalsScorerJudge` | none | only this package's tests: src/campaign/upstream-evaluators.test.ts:6 |
+| `buildCellSchedule` | production | this package: src/campaign/plan-campaign-run.ts:9 |
 | `buildEvidenceVector` | planned | doc: docs/experiment.md |
 | `buildLoopProvenanceRecord` | none | only this package's tests: src/campaign/provenance-integrity.test.ts:5 |
 | `buildTraceAnalystSurfaceDispatch` | none | only this package's tests: src/campaign/analyst-surface.test.ts:4 |
@@ -624,7 +645,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `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:29 |
-| `componentSurfaceIdentityMaterial` | none | — |
+| `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 |
 | `createProfileMatrixPlan` | production | discovery-lab:tools/run-profile-confirmation.mjs |
@@ -653,7 +674,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `isProposedCandidate` | production | supervisor-lab:bench/sequential-arena.ts |
 | `isTransientTransportFailure` | production | gtm-agent:eval/suites/persona.ts |
 | `LabeledScenarioStoreError` | none | only this package's tests: tests/campaign/run-campaign.test.ts:6 |
-| `labelTrustRank` | production | this package: src/campaign/labeled-store/fs-adapter.ts:39 |
+| `labelTrustRank` | production | this package: src/campaign/labeled-store/fs-adapter.ts:40 |
 | `llmJudge` | production | agent-runtime:examples/agentic-data-creation/offline-fixtures.ts |
 | `loadEvalFixture` | planned | doc: docs/eval-fixtures.md |
 | `loadEvalFixtureScenarios` | planned | example: examples/eval-fixtures-quickstart/index.ts:11 |
@@ -902,7 +923,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./hosted`
 
-11 value exports — 7 production, 2 planned, 2 none.
+11 value exports — 7 production, 3 planned, 1 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -914,7 +935,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `IngestEvalRunsRequestSchema` | production | this package: src/hosted/client.ts:19 |
 | `IngestResponseSchema` | production | this package: src/hosted/client.ts:19 |
 | `IngestTracesRequestSchema` | production | this package: src/hosted/client.ts:19 |
-| `InsightReportSchema` | none | — |
+| `InsightReportSchema` | planned | doc: docs/insight-report.md |
 | `TraceSpanEventSchema` | planned | example: examples/hosted-ingest-server/server.ts:33 |
 | `UnixNanoTimestampSchema` | none | — |
 
@@ -953,12 +974,14 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./meta-eval`
 
-13 value exports — 10 production, 1 planned, 2 none.
+16 value exports — 10 production, 4 planned, 2 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
 | `calibrationCurve` | none | only this package's tests: tests/meta-eval.test.ts:2 |
+| `catchRate` | planned | doc: README.md |
 | `correlationStudy` | production | phony:products/builder/api/src/eval/outcomes.ts |
+| `definePlant` | planned | doc: docs/plants.md |
 | `evalHealthStamp` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `fileSentinelStore` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `FileSystemOutcomeStore` | production | phony:products/builder/api/src/eval/outcomes.ts |
@@ -966,6 +989,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `inMemorySentinelStore` | none | only this package's tests: tests/judge-sentinel.test.ts:7 |
 | `judgeSentinelReport` | production | creative-agent:eval/lib/judge-sentinel.ts |
 | `rubricPredictiveValidity` | production | physim:apps/server/src/scripts/agent-eval/validate-rubrics.ts |
+| `seedPlants` | planned | doc: README.md |
 | `snapshotFromAgreement` | production | physim:apps/server/src/scripts/agent-eval/judge-sentinel.ts |
 | `snapshotFromCalibration` | production | gtm-agent:eval/calibrate-judges.ts |
 | `snapshotFromSentinelSet` | production | creative-agent:eval/lib/judge-sentinel.ts |
@@ -1408,7 +1432,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `SUITE_REWARD_UNIT` | none | only this package's tests: tests/trace-repair/oracle-determinism.test.ts:4 |
 | `taskOracleRegistry` | none | only this package's tests: src/trace-repair/admission-report.test.ts:7 |
 | `TB_REPAIR_ADMISSION_CRITERIA` | production | this package: scripts/tb-repair-milestone1.ts:41 |
-| `TestOracleError` | none | only this package's tests: tests/trace-repair/test-oracle.test.ts:3 |
+| `TestOracleError` | none | only this package's tests: tests/trace-repair/test-oracle.test.ts:4 |
 | `testSuiteDigest` | production | this package: scripts/tb-gated-stop-ab.ts:62 |
 | `TestSuiteTamperedError` | planned | doc: docs/trace-repair-grader.md |
 | `toRecordedSteps` | none | only this package's tests: src/trace-repair/continuation-policy.test.ts:25 |
@@ -1596,7 +1620,7 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 
 ### `./wire`
 
-30 value exports — 25 production, 3 planned, 2 none.
+31 value exports — 25 production, 3 planned, 3 none.
 
 | symbol | consumer | evidence |
 | --- | --- | --- |
@@ -1618,8 +1642,9 @@ The `none` set was reviewed symbol by symbol on 2026-08-21. Four rules decided m
 | `JudgeResultSchema` | production | this package: src/wire/openapi.ts:15 |
 | `listBuiltinRubrics` | production | this package: src/wire/handlers.ts:21 |
 | `ListRubricsResponseSchema` | production | this package: src/wire/openapi.ts:15 |
-| `RubricDimensionSchema` | none | only this package's tests: tests/wire/schemas.test.ts:11 |
-| `RubricSchema` | none | only this package's tests: tests/wire/schemas.test.ts:11 |
+| `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:21 |
 | `runRpcOnce` | production | this package: src/cli.ts:21 |
 | `startServer` | production | creative-agent:eval/ingestion-server.ts |

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tangle-network/agent-eval",
-  "version": "0.170.0",
+  "version": "0.172.0",
   "description": "Evaluate and improve AI agents from runs, traces, judges, and feedback. Compare candidates, cluster failures, measure lift, and gate releases.",
   "homepage": "https://github.com/tangle-network/agent-eval#readme",
   "repository": {
@@ -197,33 +197,33 @@
   },
   "dependencies": {
     "@asteasolutions/zod-to-openapi": "^9.1.0",
-    "@hono/node-server": "^2.0.12",
-    "@tangle-network/agent-core": "^0.9.4",
-    "@tangle-network/agent-interface": "^1.4.0",
+    "@hono/node-server": "^2.1.1",
+    "@tangle-network/agent-core": "^0.9.6",
+    "@tangle-network/agent-interface": "^2.0.0",
     "@tangle-network/agent-trace-contract": "^1.0.2",
-    "hono": "^4.12.32",
+    "hono": "^4.13.5",
     "linear-sum-assignment": "1.0.9",
     "re2js": "2.8.6",
-    "zod": "^4.4.3"
+    "zod": "4.5.4"
   },
   "devDependencies": {
     "@arethetypeswrong/cli": "^0.18.5",
-    "@arizeai/phoenix-evals": "^2.1.0",
-    "@biomejs/biome": "^2.5.5",
-    "@types/node": "^26.1.1",
+    "@arizeai/phoenix-evals": "^2.3.0",
+    "@biomejs/biome": "^2.5.11",
+    "@types/node": "^26.4.0",
     "autoevals": "^0.3.0",
-    "esbuild": "^0.28.1",
+    "esbuild": "^0.28.2",
     "fast-check": "^4.9.0",
     "husky": "^9.1.7",
     "lib-r-math.js": "^3.0.2",
-    "lint-staged": "^17.2.0",
-    "openapi3-ts": "^4.6.0",
-    "oxc-parser": "^0.141.0",
-    "publint": "^0.3.22",
+    "lint-staged": "^17.4.1",
+    "openapi3-ts": "^4.6.1",
+    "oxc-parser": "^0.147.0",
+    "publint": "^0.3.24",
     "tsdown": "^0.22.14",
-    "tsx": "^4.23.1",
+    "tsx": "^4.23.12",
     "typescript": "^7.0.2",
-    "vitest": "^4.1.10",
+    "vitest": "^4.1.11",
     "yaml": "2.9.0"
   },
   "pnpm": {
@@ -231,7 +231,8 @@
     "minimumReleaseAgeExclude": [
       "@tangle-network/*",
       "esbuild",
-      "vite"
+      "vite",
+      "zod@4.5.4"
     ],
     "overrides": {
       "@arizeai/openinference-core>@opentelemetry/core": "^2.10.0",
@@ -242,7 +243,7 @@
     }
   },
   "engines": {
-    "node": ">=20"
+    "node": ">=20.19.0"
   },
   "lint-staged": {
     "src/**/*.{ts,tsx}": [

package/dist/experiment-tracker-BKEumQug.js.map

@@ -1 +0,0 @@
-{"version":3,"file":"experiment-tracker-BKEumQug.js","names":[],"sources":["../src/experiment-tracker.ts"],"sourcesContent":["/**\n * Experiment tracker — git-provenanced experiment log with N-rep stats and a\n * KEEP / REGRESSION / NOISE verdict against a parent.\n *\n * Every loop the fleet runs reduces to the same question: \"I ran the candidate\n * N times — is the median measurably better than the parent, or is the delta\n * inside the noise band?\" The hand-rolled copies bake a fixed score scale\n * (percentage points), a fixed store path (`.evolve/experiments-v2.json`), and\n * `execSync('git …')` straight into the module. This is the canonical version:\n * provenance and persistence are injected, thresholds are configurable, and the\n * stats + verdict are pure functions you can unit-test without a git repo or a\n * filesystem.\n *\n * Stats per experiment: median / mean / min / max / iqr / stddev / passRate /\n * n, plus a `stable` flag (`iqr < iqrUnstableAbove && stddev < stddevUnstableAbove`).\n *\n * Verdict against a parent (both must have `n >= minRepsForVerdict`):\n *   - NOISE       — the candidate is too unstable to judge (`!stable`)\n *   - KEEP        — `medianDelta >  keepThreshold`\n *   - REGRESSION  — `medianDelta < -regressionThreshold`\n *   - NOISE       — otherwise (delta inside the band)\n * With no parent (or insufficient reps) the verdict is the neutral ITERATE.\n */\n\nimport { execSync } from 'node:child_process'\nimport type { EvidenceRef } from './analyst/types'\nimport { iqr } from './baseline'\nimport { ValidationError } from './errors'\n\n/** Verdict for one experiment relative to its parent. ITERATE is the neutral\n *  \"keep collecting reps / no parent to compare against\" state. */\nexport type ExperimentVerdict = 'KEEP' | 'ITERATE' | 'NOISE' | 'REGRESSION'\n\n/** Git provenance for the working tree an experiment was run from. */\nexport interface ExperimentProvenance {\n  /** Commit sha (short or full — the tracker does not interpret it). */\n  commit: string\n  /** First line of the commit message. */\n  message: string\n  /** Files changed vs the parent commit, or a marker like 'uncommitted'. */\n  changedFiles: string[]\n}\n\n/** A single repetition of an experiment, carrying the score the verdict is\n *  computed on plus any free-form per-rep metrics the consumer wants kept. */\nexport interface ExperimentRep {\n  /** 0-indexed repetition number within the experiment. */\n  rep: number\n  /** The score this rep is judged on (same scale as the thresholds). */\n  score: number\n  /** ISO timestamp the rep completed. */\n  timestamp: string\n  /** Stable execution/run identity that produced this score. */\n  runId?: string\n  /** Mechanically resolvable trace, artifact, metric, or finding evidence. */\n  evidence?: EvidenceRef[]\n  /** Whether this rep passed the consumer's own gate — folded into `passRate`. */\n  passed?: boolean\n  /** Free-form numeric metrics retained for later analysis. */\n  metrics?: Record<string, number>\n}\n\nexport interface ExperimentStats {\n  median: number\n  mean: number\n  min: number\n  max: number\n  /** Inter-quartile range of the rep scores. */\n  iqr: number\n  /** Population standard deviation of the rep scores. */\n  stddev: number\n  /** Fraction of reps with `passed === true`, over reps that set `passed`.\n   *  null when no rep declared a pass/fail outcome. */\n  passRate: number | null\n  /** Number of reps. */\n  n: number\n  /** True when the sample is tight enough to trust for a verdict. */\n  stable: boolean\n}\n\nexport interface Experiment {\n  /** Stable id for the experiment. */\n  id: string\n  /** Free-form label / config descriptor. */\n  label: string\n  /** Git provenance captured when the experiment was created. */\n  provenance: ExperimentProvenance\n  /** Parent experiment id this candidate is compared against, if any. */\n  parentId?: string\n  /** One-line summary of what changed from the parent. */\n  changeSummary: string\n  reps: ExperimentRep[]\n  stats: ExperimentStats\n  verdict: ExperimentVerdict\n  /** ISO timestamp the experiment was created. */\n  createdAt: string\n}\n\nexport interface ImprovementThresholds {\n  /** medianDelta strictly above this ⇒ KEEP. Default 5. */\n  keepThreshold?: number\n  /** medianDelta strictly below the negative of this ⇒ REGRESSION. Default 5. */\n  regressionThreshold?: number\n  /** iqr at or above this ⇒ unstable. Default 10. */\n  iqrUnstableAbove?: number\n  /** stddev at or above this ⇒ unstable. Default Infinity (iqr-only stability). */\n  stddevUnstableAbove?: number\n  /** Reps required on BOTH candidate and parent before a verdict is rendered.\n   *  Default 3. */\n  minRepsForVerdict?: number\n}\n\nexport interface ImprovementVerdictResult {\n  verdict: ExperimentVerdict\n  /** candidate.median − parent.median; null when no parent or insufficient reps. */\n  medianDelta: number | null\n  /** Human-readable reason for the verdict — for dashboards and logs. */\n  reason: string\n}\n\nconst DEFAULTS: Required<ImprovementThresholds> = {\n  keepThreshold: 5,\n  regressionThreshold: 5,\n  iqrUnstableAbove: 10,\n  stddevUnstableAbove: Number.POSITIVE_INFINITY,\n  minRepsForVerdict: 3,\n}\n\nfunction resolveThresholds(t: ImprovementThresholds | undefined): Required<ImprovementThresholds> {\n  const r = { ...DEFAULTS, ...(t ?? {}) }\n  if (r.keepThreshold < 0) {\n    throw new ValidationError(\n      `experiment-tracker: keepThreshold must be >= 0, got ${r.keepThreshold}`,\n    )\n  }\n  if (r.regressionThreshold < 0) {\n    throw new ValidationError(\n      `experiment-tracker: regressionThreshold must be >= 0, got ${r.regressionThreshold}`,\n    )\n  }\n  if (r.minRepsForVerdict < 1) {\n    throw new ValidationError(\n      `experiment-tracker: minRepsForVerdict must be >= 1, got ${r.minRepsForVerdict}`,\n    )\n  }\n  return r\n}\n\nfunction median(sorted: number[]): number {\n  const n = sorted.length\n  if (n === 0) return 0\n  const mid = Math.floor(n / 2)\n  return n % 2 === 0 ? (sorted[mid - 1]! + sorted[mid]!) / 2 : sorted[mid]!\n}\n\n/** Population standard deviation (÷n). 0 for fewer than 2 values. */\nfunction stddev(values: number[], mean: number): number {\n  if (values.length < 2) return 0\n  const variance = values.reduce((acc, v) => acc + (v - mean) ** 2, 0) / values.length\n  return Math.sqrt(variance)\n}\n\n/**\n * Compute the N-rep statistics for a set of reps. Pure — no I/O. The `stable`\n * flag is the trust gate the verdict depends on: a sample whose spread exceeds\n * the configured bounds can't distinguish a real delta from run-to-run noise.\n */\nexport function computeExperimentStats(\n  reps: ExperimentRep[],\n  thresholds?: ImprovementThresholds,\n): ExperimentStats {\n  const t = resolveThresholds(thresholds)\n  const n = reps.length\n  if (n === 0) {\n    return {\n      median: 0,\n      mean: 0,\n      min: 0,\n      max: 0,\n      iqr: 0,\n      stddev: 0,\n      passRate: null,\n      n: 0,\n      stable: false,\n    }\n  }\n  const scores = reps.map((r) => {\n    if (!Number.isFinite(r.score)) {\n      throw new ValidationError(`experiment-tracker: rep ${r.rep} has non-finite score ${r.score}`)\n    }\n    return r.score\n  })\n  const sorted = [...scores].sort((a, b) => a - b)\n  const mean = scores.reduce((s, v) => s + v, 0) / n\n  const sd = stddev(scores, mean)\n  const spread = iqr(scores)\n  const rated = reps.filter((r) => typeof r.passed === 'boolean')\n  const passRate = rated.length === 0 ? null : rated.filter((r) => r.passed).length / rated.length\n  const stable = spread < t.iqrUnstableAbove && sd < t.stddevUnstableAbove\n  return {\n    median: median(sorted),\n    mean,\n    min: sorted[0]!,\n    max: sorted[n - 1]!,\n    iqr: spread,\n    stddev: sd,\n    passRate,\n    n,\n    stable,\n  }\n}\n\n/**\n * Verdict for a candidate against its parent. Pure — operates on already-computed\n * stats. KEEP/REGRESSION require both sides to have `>= minRepsForVerdict` reps\n * AND the candidate to be `stable`; otherwise the result is NOISE (unstable) or\n * ITERATE (not enough reps / no parent).\n */\nexport function improvementVerdict(\n  candidate: ExperimentStats,\n  parent: ExperimentStats | null,\n  thresholds?: ImprovementThresholds,\n): ImprovementVerdictResult {\n  const t = resolveThresholds(thresholds)\n  if (!parent) {\n    return {\n      verdict: 'ITERATE',\n      medianDelta: null,\n      reason: 'no parent experiment to compare against',\n    }\n  }\n  if (candidate.n < t.minRepsForVerdict || parent.n < t.minRepsForVerdict) {\n    return {\n      verdict: 'ITERATE',\n      medianDelta: null,\n      reason: `need >= ${t.minRepsForVerdict} reps on both sides (candidate n=${candidate.n}, parent n=${parent.n})`,\n    }\n  }\n  if (!candidate.stable) {\n    return {\n      verdict: 'NOISE',\n      medianDelta: candidate.median - parent.median,\n      reason: `candidate unstable (iqr=${candidate.iqr}, stddev=${candidate.stddev.toFixed(2)})`,\n    }\n  }\n  const medianDelta = candidate.median - parent.median\n  if (medianDelta > t.keepThreshold) {\n    return { verdict: 'KEEP', medianDelta, reason: `median +${medianDelta} > +${t.keepThreshold}` }\n  }\n  if (medianDelta < -t.regressionThreshold) {\n    return {\n      verdict: 'REGRESSION',\n      medianDelta,\n      reason: `median ${medianDelta} < -${t.regressionThreshold}`,\n    }\n  }\n  return {\n    verdict: 'NOISE',\n    medianDelta,\n    reason: `median delta ${medianDelta} inside noise band [-${t.regressionThreshold}, +${t.keepThreshold}]`,\n  }\n}\n\n// ── Provenance + persistence seams ───────────────────────────────────\n\n/** Reads git provenance for the working tree. Inject a fake in tests; the\n *  default implementation shells out to `git`. */\nexport type ProvenanceReader = () => ExperimentProvenance | Promise<ExperimentProvenance>\n\n/** Persistence seam for the experiment log. Inject in-memory in tests; the\n *  filesystem implementation is `fileExperimentStore`. */\nexport interface ExperimentStore {\n  load(): Promise<Experiment[]>\n  save(experiments: Experiment[]): Promise<void>\n}\n\n/**\n * Default provenance reader: `git rev-parse HEAD`, the subject line, and the\n * files changed vs `HEAD~1`. Fail-loud — a tracker that silently logs\n * `commit: 'unknown'` corrupts the provenance the whole point of the log is to\n * carry. When the working tree genuinely has no parent commit, pass an override.\n */\nexport const gitProvenanceReader: ProvenanceReader = () => {\n  const run = (cmd: string): string => execSync(cmd, { encoding: 'utf8' }).trim()\n  const commit = run('git rev-parse --short HEAD')\n  const message = run('git log -1 --format=%s')\n  const changedRaw = run('git diff --name-only HEAD~1')\n  const changedFiles = changedRaw.length === 0 ? [] : changedRaw.split('\\n').filter(Boolean)\n  return { commit, message, changedFiles }\n}\n\n/** In-memory store — the default when no persistence is wanted (tests, ephemeral\n *  runs). State lives on the instance. */\nexport function inMemoryExperimentStore(initial: Experiment[] = []): ExperimentStore {\n  let state = initial.map((e) => structuredClone(e))\n  return {\n    async load() {\n      return state.map((e) => structuredClone(e))\n    },\n    async save(experiments) {\n      state = experiments.map((e) => structuredClone(e))\n    },\n  }\n}\n\n/** Filesystem store — a single JSON array at `path`, created on first save. */\nexport function fileExperimentStore(path: string): ExperimentStore {\n  return {\n    async load() {\n      const fs = await import('node:fs/promises')\n      try {\n        const raw = await fs.readFile(path, 'utf8')\n        const parsed = JSON.parse(raw)\n        if (!Array.isArray(parsed)) {\n          throw new ValidationError(`experiment-tracker: store at ${path} is not a JSON array`)\n        }\n        return parsed as Experiment[]\n      } catch (err) {\n        if ((err as NodeJS.ErrnoException).code === 'ENOENT') return []\n        throw err\n      }\n    },\n    async save(experiments) {\n      const fs = await import('node:fs/promises')\n      const pathMod = await import('node:path')\n      await fs.mkdir(pathMod.dirname(path), { recursive: true })\n      await fs.writeFile(path, JSON.stringify(experiments, null, 2), 'utf8')\n    },\n  }\n}\n\nexport interface ExperimentTrackerOptions {\n  store?: ExperimentStore\n  provenanceReader?: ProvenanceReader\n  thresholds?: ImprovementThresholds\n  /** Clock seam for deterministic timestamps in tests. Default `Date.now`. */\n  now?: () => number\n}\n\nexport interface CreateExperimentInput {\n  id: string\n  label: string\n  changeSummary: string\n  parentId?: string\n  /** Override provenance instead of reading from git (e.g. CI metadata). */\n  provenance?: ExperimentProvenance\n}\n\n/**\n * Stateful tracker over an `ExperimentStore`. Create an experiment (provenance\n * is captured once), append reps as they complete (stats + verdict recompute on\n * every append), and read the log back for a dashboard. All persistence and git\n * access flow through the injected seams, so the tracker is fully testable\n * without a repo or disk.\n */\nexport class ExperimentTracker {\n  private readonly store: ExperimentStore\n  private readonly provenanceReader: ProvenanceReader\n  private readonly thresholds: Required<ImprovementThresholds>\n  private readonly now: () => number\n\n  constructor(options: ExperimentTrackerOptions = {}) {\n    this.store = options.store ?? inMemoryExperimentStore()\n    this.provenanceReader = options.provenanceReader ?? gitProvenanceReader\n    this.thresholds = resolveThresholds(options.thresholds)\n    this.now = options.now ?? Date.now\n  }\n\n  async create(input: CreateExperimentInput): Promise<Experiment> {\n    const experiments = await this.store.load()\n    if (experiments.some((e) => e.id === input.id)) {\n      throw new ValidationError(`experiment-tracker: experiment id \"${input.id}\" already exists`)\n    }\n    if (input.parentId && !experiments.some((e) => e.id === input.parentId)) {\n      throw new ValidationError(\n        `experiment-tracker: parent experiment \"${input.parentId}\" not found`,\n      )\n    }\n    const provenance = input.provenance ?? (await this.provenanceReader())\n    const experiment: Experiment = {\n      id: input.id,\n      label: input.label,\n      provenance,\n      parentId: input.parentId,\n      changeSummary: input.changeSummary,\n      reps: [],\n      stats: computeExperimentStats([], this.thresholds),\n      verdict: 'ITERATE',\n      createdAt: new Date(this.now()).toISOString(),\n    }\n    experiments.push(experiment)\n    await this.store.save(experiments)\n    return structuredClone(experiment)\n  }\n\n  /** Append a rep (its `rep` index defaults to the current rep count) and\n   *  recompute stats + verdict. Returns the updated experiment. */\n  async addRep(\n    experimentId: string,\n    rep: Omit<ExperimentRep, 'rep' | 'timestamp'> & { rep?: number; timestamp?: string },\n  ): Promise<Experiment> {\n    const experiments = await this.store.load()\n    const exp = experiments.find((e) => e.id === experimentId)\n    if (!exp)\n      throw new ValidationError(`experiment-tracker: experiment \"${experimentId}\" not found`)\n    if (rep.runId !== undefined && rep.runId.trim().length === 0) {\n      throw new ValidationError('experiment-tracker: rep runId must be non-empty when present')\n    }\n    const evidence = rep.evidence?.map((reference, index) => {\n      if (reference.uri.trim().length === 0) {\n        throw new ValidationError(\n          `experiment-tracker: rep evidence[${index}].uri must be non-empty`,\n        )\n      }\n      return {\n        kind: reference.kind,\n        uri: reference.uri,\n        ...(reference.excerpt === undefined ? {} : { excerpt: reference.excerpt }),\n      }\n    })\n    const fullRep: ExperimentRep = {\n      rep: rep.rep ?? exp.reps.length,\n      score: rep.score,\n      timestamp: rep.timestamp ?? new Date(this.now()).toISOString(),\n      ...(rep.runId === undefined ? {} : { runId: rep.runId }),\n      ...(evidence === undefined ? {} : { evidence }),\n      ...(rep.passed === undefined ? {} : { passed: rep.passed }),\n      ...(rep.metrics === undefined ? {} : { metrics: { ...rep.metrics } }),\n    }\n    exp.reps.push(fullRep)\n    exp.stats = computeExperimentStats(exp.reps, this.thresholds)\n    const parent = exp.parentId ? experiments.find((e) => e.id === exp.parentId) : undefined\n    exp.verdict = improvementVerdict(exp.stats, parent?.stats ?? null, this.thresholds).verdict\n    await this.store.save(experiments)\n    return structuredClone(exp)\n  }\n\n  async get(experimentId: string): Promise<Experiment | undefined> {\n    const experiments = await this.store.load()\n    const found = experiments.find((e) => e.id === experimentId)\n    return found ? structuredClone(found) : undefined\n  }\n\n  async list(): Promise<Experiment[]> {\n    return this.store.load()\n  }\n\n  /** Full verdict (not just the enum) for an experiment vs its parent. */\n  async verdictFor(experimentId: string): Promise<ImprovementVerdictResult> {\n    const experiments = await this.store.load()\n    const exp = experiments.find((e) => e.id === experimentId)\n    if (!exp)\n      throw new ValidationError(`experiment-tracker: experiment \"${experimentId}\" not found`)\n    const parent = exp.parentId ? experiments.find((e) => e.id === exp.parentId) : undefined\n    return improvementVerdict(exp.stats, parent?.stats ?? null, this.thresholds)\n  }\n}\n"],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;AAwHA,MAAM,WAA4C;CAChD,eAAe;CACf,qBAAqB;CACrB,kBAAkB;CAClB,qBAAqB,OAAO;CAC5B,mBAAmB;AACrB;AAEA,SAAS,kBAAkB,GAAuE;CAChG,MAAM,IAAI;EAAE,GAAG;EAAU,GAAI,KAAK,CAAC;CAAG;CACtC,IAAI,EAAE,gBAAgB,GACpB,MAAM,IAAI,gBACR,uDAAuD,EAAE,eAC3D;CAEF,IAAI,EAAE,sBAAsB,GAC1B,MAAM,IAAI,gBACR,6DAA6D,EAAE,qBACjE;CAEF,IAAI,EAAE,oBAAoB,GACxB,MAAM,IAAI,gBACR,2DAA2D,EAAE,mBAC/D;CAEF,OAAO;AACT;AAEA,SAAS,OAAO,QAA0B;CACxC,MAAM,IAAI,OAAO;CACjB,IAAI,MAAM,GAAG,OAAO;CACpB,MAAM,MAAM,KAAK,MAAM,IAAI,CAAC;CAC5B,OAAO,IAAI,MAAM,KAAK,OAAO,MAAM,KAAM,OAAO,QAAS,IAAI,OAAO;AACtE;;AAGA,SAAS,OAAO,QAAkB,MAAsB;CACtD,IAAI,OAAO,SAAS,GAAG,OAAO;CAC9B,MAAM,WAAW,OAAO,QAAQ,KAAK,MAAM,OAAO,IAAI,SAAS,GAAG,CAAC,IAAI,OAAO;CAC9E,OAAO,KAAK,KAAK,QAAQ;AAC3B;;;;;;AAOA,SAAgB,uBACd,MACA,YACiB;CACjB,MAAM,IAAI,kBAAkB,UAAU;CACtC,MAAM,IAAI,KAAK;CACf,IAAI,MAAM,GACR,OAAO;EACL,QAAQ;EACR,MAAM;EACN,KAAK;EACL,KAAK;EACL,KAAK;EACL,QAAQ;EACR,UAAU;EACV,GAAG;EACH,QAAQ;CACV;CAEF,MAAM,SAAS,KAAK,KAAK,MAAM;EAC7B,IAAI,CAAC,OAAO,SAAS,EAAE,KAAK,GAC1B,MAAM,IAAI,gBAAgB,2BAA2B,EAAE,IAAI,wBAAwB,EAAE,OAAO;EAE9F,OAAO,EAAE;CACX,CAAC;CACD,MAAM,SAAS,CAAC,GAAG,MAAM,CAAC,CAAC,MAAM,GAAG,MAAM,IAAI,CAAC;CAC/C,MAAM,OAAO,OAAO,QAAQ,GAAG,MAAM,IAAI,GAAG,CAAC,IAAI;CACjD,MAAM,KAAK,OAAO,QAAQ,IAAI;CAC9B,MAAM,SAAS,IAAI,MAAM;CACzB,MAAM,QAAQ,KAAK,QAAQ,MAAM,OAAO,EAAE,WAAW,SAAS;CAC9D,MAAM,WAAW,MAAM,WAAW,IAAI,OAAO,MAAM,QAAQ,MAAM,EAAE,MAAM,CAAC,CAAC,SAAS,MAAM;CAC1F,MAAM,SAAS,SAAS,EAAE,oBAAoB,KAAK,EAAE;CACrD,OAAO;EACL,QAAQ,OAAO,MAAM;EACrB;EACA,KAAK,OAAO;EACZ,KAAK,OAAO,IAAI;EAChB,KAAK;EACL,QAAQ;EACR;EACA;EACA;CACF;AACF;;;;;;;AAQA,SAAgB,mBACd,WACA,QACA,YAC0B;CAC1B,MAAM,IAAI,kBAAkB,UAAU;CACtC,IAAI,CAAC,QACH,OAAO;EACL,SAAS;EACT,aAAa;EACb,QAAQ;CACV;CAEF,IAAI,UAAU,IAAI,EAAE,qBAAqB,OAAO,IAAI,EAAE,mBACpD,OAAO;EACL,SAAS;EACT,aAAa;EACb,QAAQ,WAAW,EAAE,kBAAkB,mCAAmC,UAAU,EAAE,aAAa,OAAO,EAAE;CAC9G;CAEF,IAAI,CAAC,UAAU,QACb,OAAO;EACL,SAAS;EACT,aAAa,UAAU,SAAS,OAAO;EACvC,QAAQ,2BAA2B,UAAU,IAAI,WAAW,UAAU,OAAO,QAAQ,CAAC,EAAE;CAC1F;CAEF,MAAM,cAAc,UAAU,SAAS,OAAO;CAC9C,IAAI,cAAc,EAAE,eAClB,OAAO;EAAE,SAAS;EAAQ;EAAa,QAAQ,WAAW,YAAY,MAAM,EAAE;CAAgB;CAEhG,IAAI,cAAc,CAAC,EAAE,qBACnB,OAAO;EACL,SAAS;EACT;EACA,QAAQ,UAAU,YAAY,MAAM,EAAE;CACxC;CAEF,OAAO;EACL,SAAS;EACT;EACA,QAAQ,gBAAgB,YAAY,uBAAuB,EAAE,oBAAoB,KAAK,EAAE,cAAc;CACxG;AACF;;;;;;;AAqBA,MAAa,4BAA8C;CACzD,MAAM,OAAO,QAAwB,SAAS,KAAK,EAAE,UAAU,OAAO,CAAC,CAAC,CAAC,KAAK;CAC9E,MAAM,SAAS,IAAI,4BAA4B;CAC/C,MAAM,UAAU,IAAI,wBAAwB;CAC5C,MAAM,aAAa,IAAI,6BAA6B;CAEpD,OAAO;EAAE;EAAQ;EAAS,cADL,WAAW,WAAW,IAAI,CAAC,IAAI,WAAW,MAAM,IAAI,CAAC,CAAC,OAAO,OAAO;CAClD;AACzC;;;AAIA,SAAgB,wBAAwB,UAAwB,CAAC,GAAoB;CACnF,IAAI,QAAQ,QAAQ,KAAK,MAAM,gBAAgB,CAAC,CAAC;CACjD,OAAO;EACL,MAAM,OAAO;GACX,OAAO,MAAM,KAAK,MAAM,gBAAgB,CAAC,CAAC;EAC5C;EACA,MAAM,KAAK,aAAa;GACtB,QAAQ,YAAY,KAAK,MAAM,gBAAgB,CAAC,CAAC;EACnD;CACF;AACF;;AAGA,SAAgB,oBAAoB,MAA+B;CACjE,OAAO;EACL,MAAM,OAAO;GACX,MAAM,KAAK,MAAM,OAAO;GACxB,IAAI;IACF,MAAM,MAAM,MAAM,GAAG,SAAS,MAAM,MAAM;IAC1C,MAAM,SAAS,KAAK,MAAM,GAAG;IAC7B,IAAI,CAAC,MAAM,QAAQ,MAAM,GACvB,MAAM,IAAI,gBAAgB,gCAAgC,KAAK,qBAAqB;IAEtF,OAAO;GACT,SAAS,KAAK;IACZ,IAAK,IAA8B,SAAS,UAAU,OAAO,CAAC;IAC9D,MAAM;GACR;EACF;EACA,MAAM,KAAK,aAAa;GACtB,MAAM,KAAK,MAAM,OAAO;GACxB,MAAM,UAAU,MAAM,OAAO;GAC7B,MAAM,GAAG,MAAM,QAAQ,QAAQ,IAAI,GAAG,EAAE,WAAW,KAAK,CAAC;GACzD,MAAM,GAAG,UAAU,MAAM,KAAK,UAAU,aAAa,MAAM,CAAC,GAAG,MAAM;EACvE;CACF;AACF;;;;;;;;AA0BA,IAAa,oBAAb,MAA+B;CAC7B;CACA;CACA;CACA;CAEA,YAAY,UAAoC,CAAC,GAAG;EAClD,KAAK,QAAQ,QAAQ,SAAS,wBAAwB;EACtD,KAAK,mBAAmB,QAAQ,oBAAoB;EACpD,KAAK,aAAa,kBAAkB,QAAQ,UAAU;EACtD,KAAK,MAAM,QAAQ,OAAO,KAAK;CACjC;CAEA,MAAM,OAAO,OAAmD;EAC9D,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,IAAI,YAAY,MAAM,MAAM,EAAE,OAAO,MAAM,EAAE,GAC3C,MAAM,IAAI,gBAAgB,sCAAsC,MAAM,GAAG,iBAAiB;EAE5F,IAAI,MAAM,YAAY,CAAC,YAAY,MAAM,MAAM,EAAE,OAAO,MAAM,QAAQ,GACpE,MAAM,IAAI,gBACR,0CAA0C,MAAM,SAAS,YAC3D;EAEF,MAAM,aAAa,MAAM,cAAe,MAAM,KAAK,iBAAiB;EACpE,MAAM,aAAyB;GAC7B,IAAI,MAAM;GACV,OAAO,MAAM;GACb;GACA,UAAU,MAAM;GAChB,eAAe,MAAM;GACrB,MAAM,CAAC;GACP,OAAO,uBAAuB,CAAC,GAAG,KAAK,UAAU;GACjD,SAAS;GACT,WAAW,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,YAAY;EAC9C;EACA,YAAY,KAAK,UAAU;EAC3B,MAAM,KAAK,MAAM,KAAK,WAAW;EACjC,OAAO,gBAAgB,UAAU;CACnC;;;CAIA,MAAM,OACJ,cACA,KACqB;EACrB,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,MAAM,MAAM,YAAY,MAAM,MAAM,EAAE,OAAO,YAAY;EACzD,IAAI,CAAC,KACH,MAAM,IAAI,gBAAgB,mCAAmC,aAAa,YAAY;EACxF,IAAI,IAAI,UAAU,KAAA,KAAa,IAAI,MAAM,KAAK,CAAC,CAAC,WAAW,GACzD,MAAM,IAAI,gBAAgB,8DAA8D;EAE1F,MAAM,WAAW,IAAI,UAAU,KAAK,WAAW,UAAU;GACvD,IAAI,UAAU,IAAI,KAAK,CAAC,CAAC,WAAW,GAClC,MAAM,IAAI,gBACR,oCAAoC,MAAM,wBAC5C;GAEF,OAAO;IACL,MAAM,UAAU;IAChB,KAAK,UAAU;IACf,GAAI,UAAU,YAAY,KAAA,IAAY,CAAC,IAAI,EAAE,SAAS,UAAU,QAAQ;GAC1E;EACF,CAAC;EACD,MAAM,UAAyB;GAC7B,KAAK,IAAI,OAAO,IAAI,KAAK;GACzB,OAAO,IAAI;GACX,WAAW,IAAI,aAAa,IAAI,KAAK,KAAK,IAAI,CAAC,CAAC,CAAC,YAAY;GAC7D,GAAI,IAAI,UAAU,KAAA,IAAY,CAAC,IAAI,EAAE,OAAO,IAAI,MAAM;GACtD,GAAI,aAAa,KAAA,IAAY,CAAC,IAAI,EAAE,SAAS;GAC7C,GAAI,IAAI,WAAW,KAAA,IAAY,CAAC,IAAI,EAAE,QAAQ,IAAI,OAAO;GACzD,GAAI,IAAI,YAAY,KAAA,IAAY,CAAC,IAAI,EAAE,SAAS,EAAE,GAAG,IAAI,QAAQ,EAAE;EACrE;EACA,IAAI,KAAK,KAAK,OAAO;EACrB,IAAI,QAAQ,uBAAuB,IAAI,MAAM,KAAK,UAAU;EAC5D,MAAM,SAAS,IAAI,WAAW,YAAY,MAAM,MAAM,EAAE,OAAO,IAAI,QAAQ,IAAI,KAAA;EAC/E,IAAI,UAAU,mBAAmB,IAAI,OAAO,QAAQ,SAAS,MAAM,KAAK,UAAU,CAAC,CAAC;EACpF,MAAM,KAAK,MAAM,KAAK,WAAW;EACjC,OAAO,gBAAgB,GAAG;CAC5B;CAEA,MAAM,IAAI,cAAuD;EAE/D,MAAM,SAAQ,MADY,KAAK,MAAM,KAAK,EAAA,CAChB,MAAM,MAAM,EAAE,OAAO,YAAY;EAC3D,OAAO,QAAQ,gBAAgB,KAAK,IAAI,KAAA;CAC1C;CAEA,MAAM,OAA8B;EAClC,OAAO,KAAK,MAAM,KAAK;CACzB;;CAGA,MAAM,WAAW,cAAyD;EACxE,MAAM,cAAc,MAAM,KAAK,MAAM,KAAK;EAC1C,MAAM,MAAM,YAAY,MAAM,MAAM,EAAE,OAAO,YAAY;EACzD,IAAI,CAAC,KACH,MAAM,IAAI,gBAAgB,mCAAmC,aAAa,YAAY;EACxF,MAAM,SAAS,IAAI,WAAW,YAAY,MAAM,MAAM,EAAE,OAAO,IAAI,QAAQ,IAAI,KAAA;EAC/E,OAAO,mBAAmB,IAAI,OAAO,QAAQ,SAAS,MAAM,KAAK,UAAU;CAC7E;AACF"}

package/dist/experiment-tracker-Dm8yQMqb.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"experiment-tracker-Dm8yQMqb.d.ts","names":[],"sources":["../src/statistics/power-and-mde.ts","../src/statistics/random.ts","../src/experiment-tracker.ts"],"mappings":";;;;;;;;iBAWgB,mBAAmB;EACjC;EACA;EACA;EACA;;;;;;;;;;;iBAsBc,yBAAyB;EACvC;EACA;EACA;EACA;;;;;;;;iBAkBc,UAAU;EACxB;EACA;EACA;EACA;;;;;;;;;;;;;;;;iBAyBc,iBAAiB;EAC/B;EACA;EACA;EACA;EACA;;;;;;;iBAyBc,aAAa;EAC3B;EACA;EACA;EACA;EACA;;;;;;;;iBCrHc,WAAW;;;;;KCyBf;;UAGK;;EAEf;;EAEA;;EAEA;;;;UAKe;;EAEf;;EAEA;;EAEA;;EAEA;;EAEA,WAAW;;EAEX;;EAEA,UAAU;;UAGK;EACf;EACA;EACA;EACA;;EAEA;;EAEA;;;EAGA;;EAEA;;EAEA;;UAGe;;EAEf;;EAEA;;EAEA,YAAY;;EAEZ;;EAEA;EACA,MAAM;EACN,OAAO;EACP,SAAS;;EAET;;UAGe;;EAEf;;EAEA;;EAEA;;EAEA;;;EAGA;;UAGe;EACf,SAAS;;EAET;;EAEA;;;;;;;iBAkDc,uBACd,MAAM,iBACN,aAAa,wBACZ;;;;;;;iBAgDa,mBACd,WAAW,iBACX,QAAQ,wBACR,aAAa,wBACZ;;;KA6CS,yBAAyB,uBAAuB,QAAQ;;;UAInD;EACf,QAAQ,QAAQ;EAChB,KAAK,aAAa,eAAe;;;;iBAoBnB,wBAAwB,UAAS,eAAoB;;iBAarD,oBAAoB,eAAe;UAyBlC;EACf,QAAQ;EACR,mBAAmB;EACnB,aAAa;;EAEb;;UAGe;EACf;EACA;EACA;EACA;;EAEA,aAAa;;;;;;;;;cAUF;mBACM;mBACA;mBACA;mBACA;EAEjB,YAAY,UAAS;EAOf,OAAO,OAAO,wBAAwB,QAAQ;;;EA6B9C,OACJ,sBACA,KAAK,KAAK;IAAwC;IAAc;MAC/D,QAAQ;EAqCL,IAAI,uBAAuB,QAAQ;EAMnC,QAAQ,QAAQ;;EAKhB,WAAW,uBAAuB,QAAQ"}

package/dist/index-lfaSeKSD.d.ts.map

@@ -1 +0,0 @@
-{"version":3,"file":"index-lfaSeKSD.d.ts","names":[],"sources":["../src/ledger-core/atomic-file-lock.ts","../src/ledger-core/canonical.ts","../src/ledger-core/journal-file.ts","../src/ledger-core/trusted-head.ts","../src/ledger-core/journal.ts"],"mappings":";;;UAiBiB;WACN;WACA;WACA;;UAGM;WACN,OAAO;EAChB;;KAGU;WACG;WAA0B;WAAyB,QAAQ;;WAC3D;WAA0B;;KAE7B;WACG;WAAyB,MAAM;IAC1C;UAEa;WACN;WACA;;cAGE,4BAA4B;WACrB;;;iBASJ,oBACd,SAAS,wBACR;;;;;;;iBAea,yBACd,SAAS,wBACR;;;KCjDS;;cAGC,qBAAmB;;cAGnB,oCAAoC;;;;iBAKjC,gBAAgB;iBAQhB,cAAc,iBAAiB;;;;;;;;;;;;;;;;iBAuB/B,aAAa;;;;;UC7CZ;;EAEf;EACA,eAAe,iBAAiB;IAAY;MAAoB;;;;iBAKlD,iBAAiB,cAAc,cAAc,SAAS;;;;iBA6CtD,0BACd,cACA,kBACA,SAAS;iBAqCK,mBAAmB,GAAG,cAAc,SAAS,mBAAmB,WAAW,IAAI;KAQnF,eAAe;EAAO;EAAgB,OAAO;;EAAQ;;iBAEjD,sBAAsB,GACpC,cACA,SAAS,mBACT,WAAW,IACV,eAAe;;;;UCnED;EACf;EACA,WAAW;;;UAII;EACf;EACA,WAAW;;;;iBAKG,mBAAmB;;;;;iBAWnB,oBACd,cACA,SAAS,oBACR;;;;;;;KA2ES;EACN;EAAe,MAAM;EAAmB;;EACxC;EAAe;EAAY;EAAoB;;EAC/C;EAAgB;;;UAsCL;;EAEf;;;EAGA;;;;;iBAMc,gCACd,kBAAkB,uBAClB,MAAM,mBACN,SAAS,mBACT,QAAQ;;;;UCjLO;EACf;;;;;UAMe,kBAAkB,cAAc;EAC/C;EACA,cAAc;EACd,OAAO;EACP,WAAW;;KAGD,cAAc,uBAAuB,cAAc,mBAAmB,SAChF,kBAAkB;UAEH;EACf;EACA;;;;;UAMe,gBAAgB,OAAO;EACtC,MAAM,OAAO,OAAO;EACpB,OAAO,SAAS,UAAU;;UAGX,mBACf,uBACA,cAAc,iBACd,oBACQ;;EAER,QAAQ;EACR,cAAc,kBAAkB;;;;EAIhC,WAAW,cAAc,SAAS,oBAAoB,cAAc,QAAQ;;EAE5E,iBAAiB,OAAO,cAAc,QAAQ,QAAQ;EACtD,mBAAmB,gBAAgB,cAAc,QAAQ,QAAQ;;UAGlD,mBAAmB,OAAO;EACzC,SAAS;EACT,YAAY;;UAGG,mBAAmB,OAAO;EACzC,OAAO;;EAEP;EACA,YAAY;;UAGG;;;;;;;;;;;;;;EAcf;;UAGe;;;;;;;EAOf;;;;cAiBW,kBAAkB,uBAAuB,cAAc,iBAAiB;WAC1E;;WAEA;mBACQ;mBACA;mBACA;EAEjB,YACE,cACA,OAAO,mBAAmB,QAAQ,OAAO,aACzC,UAAS;EASL,UAAU,QAAQ,mBAAmB,cAAc,QAAQ,QAAQ;EAMnE,OACJ,OAAO,OACP,UAAS,sBACR,QAAQ,mBAAmB,cAAc,QAAQ,QAAQ;;EA8CtD,eAAe,QAAQ;;;;EAWvB,kBAAkB,QAAQ;;;;;;;;EA4B1B,oBAAoB,QAAQ;;;;;;;;;;;;;UAoB1B;UAiBA;UAUA;UAgBA;UAgDA"}