@tangle-network/agent-eval 0.150.1 → 0.150.2

package/dist/cli.js

@@ -1,6 +1,6 @@
 #!/usr/bin/env node
 import { o as runRolloutReleaseCli } from "./hf-dataset-XggBupCr.js";
-import { n as runAnalystBenchmarkCommand } from "./benchmark-command-CAFwbH0L.js";
+import { n as runAnalystBenchmarkCommand } from "./benchmark-command-BU1Las59.js";
 import { a as runRpcBatch, o as runRpcOnce, p as handleVersion, r as startServerAsync, s as buildOpenApi } from "./server-dIWwF3j_.js";
 import { writeFileSync } from "node:fs";
 //#region src/cli-config.ts

package/dist/contract/index.js

@@ -1,21 +1,21 @@
 import { s as ValidationError } from "../errors-Dngq5h35.js";
 import { r as pairedBootstrap } from "../paired-tests-BHIhYVdu.js";
-import { a as summarizeExecution, i as analyzeRuns, n as SelfImproveRunError, r as selfImprove, t as defineAgentEval } from "../define-agent-eval-rqNyVhVV.js";
+import { a as summarizeExecution, i as analyzeRuns, n as SelfImproveRunError, r as selfImprove, t as defineAgentEval } from "../define-agent-eval-C8V8sMqP.js";
 import { a as parseRunRecordSafe } from "../run-record-D2lDdSAz.js";
-import { $ as runEval, et as runCampaign, f as runImprovementLoop, q as defaultProductionGate, t as llmJudge, ut as campaignSplitDigest, x as compareOptimizationMethods } from "../llm-judge-CVq33oz1.js";
+import { $ as runEval, et as runCampaign, f as runImprovementLoop, q as defaultProductionGate, t as llmJudge, ut as campaignSplitDigest, x as compareOptimizationMethods } from "../llm-judge-BqqMS8t7.js";
 import { i as isModelPriced, n as estimateCost } from "../metrics-Qv-cpptD.js";
 import { i as CostLedger } from "../cost-ledger-B1qx30B4.js";
 import { d as mapConcurrentRange } from "../ledger-core-DTae9rv_.js";
-import { S as inMemoryCampaignStorage, x as fsCampaignStorage } from "../external-optimizer-subprocess-Dn90UqN2.js";
+import { S as inMemoryCampaignStorage, x as fsCampaignStorage } from "../external-optimizer-subprocess-CKNb42oM.js";
 import { a as heldoutSignificance, s as decidePairedPromotion } from "../power-preflight-DEw-uC7q.js";
 import { r as makeProposalFinding } from "../types-BI4fT3HN.js";
 import { $ as classifyOtlpSpanRole, et as isOtlpModelCall } from "../kind-factory-DmAa0h3K.js";
-import { n as buildDefaultAnalystRegistry, t as createChatClient } from "../chat-client-2bVfrzhN.js";
+import { n as buildDefaultAnalystRegistry, t as createChatClient } from "../chat-client-Bvmxedyv.js";
 import { LLM_MODEL_ATTR_KEYS, SPAN_KIND_ATTR_KEYS } from "../trace-attributes.js";
 import { t as extractUsage } from "../extract-usage-BrQ8mCLX.js";
 import { n as InMemoryOutcomeStore, t as FileSystemOutcomeStore } from "../outcome-store-ChBKlTd_.js";
 import { i as summarizeTraceErrors, n as recordAggregateMeasurements, r as summarizeExecutionMeasurements, t as readTaskFailureLabels } from "../task-failure-attributes--ZTP3tYO.js";
-import { a as externalTextOptimizationMethod, c as REFERENCE_EQUIVALENCE_INPUT_LIMITS, d as runReferenceEquivalenceJudge, i as composeGate, l as REFERENCE_EQUIVALENCE_JUDGE_VERSION, n as gepaOptimizationMethod, r as heldOutGate, t as skillOptOptimizationMethod, u as createReferenceEquivalenceJudge } from "../skillopt-optimization-method-DLeUcK-K.js";
+import { a as externalTextOptimizationMethod, c as REFERENCE_EQUIVALENCE_INPUT_LIMITS, d as runReferenceEquivalenceJudge, i as composeGate, l as REFERENCE_EQUIVALENCE_JUDGE_VERSION, n as gepaOptimizationMethod, r as heldOutGate, t as skillOptOptimizationMethod, u as createReferenceEquivalenceJudge } from "../skillopt-optimization-method-CPBlTcj5.js";
 import { n as paretoPolicy, r as paretoSignificanceGate, t as buildEvidenceVector } from "../promotion-policy-xzA40Evo.js";
 import { createHash } from "node:crypto";
 import { agentCandidateBenchmarkSuiteSchema, agentCandidateBenchmarkTaskSchema, agentCandidateBundleSchema, agentCandidateEvaluationPolicySchema, agentCandidateExperimentSchema, agentImprovementMeasuredComparisonSchema, agentProfileImprovementExperimentSchema, agentProfileImprovementMeasuredComparisonSchema, agentProfileImprovementRunCellSchema, agentProfileImprovementRunReceiptSchema, agentProfileImprovementSuiteInputsSchema, agentProfileImprovementSuiteSchema, agentProfileImprovementTaskSchema, candidateExecutionEvidenceSchema, canonicalCandidateDigest, canonicalCandidateJson, numbersApproximatelyEqual, omitTopLevelDigest } from "@tangle-network/agent-interface";

package/dist/{define-agent-eval-rqNyVhVV.js → define-agent-eval-C8V8sMqP.js}

@@ -1,6 +1,6 @@
 import { s as ValidationError } from "./errors-Dngq5h35.js";
-import { a as spearmanR, r as pearsonR } from "./descriptive-B5MwKfbf.js";
-import { r as continuousAgreement } from "./judge-calibration-DZkWrm5H.js";
+import { a as spearmanR, r as pearsonR } from "./descriptive-jDOuI6mz.js";
+import { r as continuousAgreement } from "./judge-calibration-zZjLz8hr.js";
 import { i as pairedCohensDz } from "./effect-sizes-DiH8MGOH.js";
 import { i as requiredPairedSampleSize, r as pairedMde } from "./power-and-mde-CHIrXJll.js";
 import { r as pairRunRecords } from "./paired-arms-D-XRF_fy.js";
@@ -8,10 +8,10 @@ import { o as pairedTTest, r as pairedBootstrap } from "./paired-tests-BHIhYVdu.
 import { r as welchsTTest } from "./baseline-BhPRQBVn.js";
 import { r as observedSplitScore } from "./reward-nw2xZGZG.js";
 import { c as validateRunRecord, i as modelHasSnapshot } from "./run-record-D2lDdSAz.js";
-import { r as paretoChart } from "./summary-report-Blysd6Z2.js";
-import { $ as runEval, A as surfaceHash, f as runImprovementLoop, k as surfaceContentHash, nt as resolveRunDir, o as emitLoopProvenance, q as defaultProductionGate, s as loopProvenanceArgsFromResult, y as assertOptimizationResult } from "./llm-judge-CVq33oz1.js";
-import { c as campaignCellTaskScore, l as campaignCellToRunRecord, o as campaignCellExecutionEvidence, s as campaignCellJudgeDimensions } from "./reward-hacking-DKI9T52l.js";
-import { S as inMemoryCampaignStorage, b as createRunCostLedger, x as fsCampaignStorage } from "./external-optimizer-subprocess-Dn90UqN2.js";
+import { r as paretoChart } from "./summary-report-DW2bEpdB.js";
+import { $ as runEval, A as surfaceHash, f as runImprovementLoop, k as surfaceContentHash, nt as resolveRunDir, o as emitLoopProvenance, q as defaultProductionGate, s as loopProvenanceArgsFromResult, y as assertOptimizationResult } from "./llm-judge-BqqMS8t7.js";
+import { c as campaignCellTaskScore, l as campaignCellToRunRecord, o as campaignCellExecutionEvidence, s as campaignCellJudgeDimensions } from "./reward-hacking-C0x0xihA.js";
+import { S as inMemoryCampaignStorage, b as createRunCostLedger, x as fsCampaignStorage } from "./external-optimizer-subprocess-CKNb42oM.js";
 import { t as powerPreflight } from "./power-preflight-DEw-uC7q.js";
 import { t as createHostedClient } from "./client-LIuo-KPv.js";
 //#region src/contamination-guard.ts
@@ -1491,4 +1491,4 @@ function requirePositiveInteger(value, field) {
 //#endregion
 export { summarizeExecution as a, analyzeRuns as i, SelfImproveRunError as n, checkCanaries as o, selfImprove as r, defineAgentEval as t };
 
-//# sourceMappingURL=define-agent-eval-rqNyVhVV.js.map
+//# sourceMappingURL=define-agent-eval-C8V8sMqP.js.map