@tangle-network/agent-eval 0.220.2 → 0.221.1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (181) hide show
  1. package/CHANGELOG.md +64 -0
  2. package/dist/adapters/http.d.ts +2 -2
  3. package/dist/{agent-profile-D01Io2Xw.d.ts → agent-profile-Bc7ADJY4.d.ts} +2 -2
  4. package/dist/{agent-profile-D01Io2Xw.d.ts.map → agent-profile-Bc7ADJY4.d.ts.map} +1 -1
  5. package/dist/analyst/index.d.ts +77 -78
  6. package/dist/analyst/index.d.ts.map +1 -1
  7. package/dist/analyst/index.js +204 -25
  8. package/dist/analyst/index.js.map +1 -1
  9. package/dist/{analyze-runs-DqPJaJ4X.js → analyze-runs-CHmsykNJ.js} +4 -4
  10. package/dist/{analyze-runs-DqPJaJ4X.js.map → analyze-runs-CHmsykNJ.js.map} +1 -1
  11. package/dist/{analyze-runs-BWAHBDAw.d.ts → analyze-runs-D7In4c3z.d.ts} +2 -2
  12. package/dist/{analyze-runs-BWAHBDAw.d.ts.map → analyze-runs-D7In4c3z.d.ts.map} +1 -1
  13. package/dist/{benchmark-command-Dx0E4a6z.js → benchmark-command-DiGqnGUt.js} +13 -11
  14. package/dist/benchmark-command-DiGqnGUt.js.map +1 -0
  15. package/dist/benchmarks/index.d.ts +4 -4
  16. package/dist/benchmarks/index.js +3 -3
  17. package/dist/calibration-CTwxpJ-t.js +197 -0
  18. package/dist/calibration-CTwxpJ-t.js.map +1 -0
  19. package/dist/campaign/index.d.ts +6 -6
  20. package/dist/campaign/index.js +5 -5
  21. package/dist/{campaign-BVPC6ODQ.js → campaign-Bt6rbWIU.js} +9 -8
  22. package/dist/{campaign-BVPC6ODQ.js.map → campaign-Bt6rbWIU.js.map} +1 -1
  23. package/dist/cli.js +1 -1
  24. package/dist/{completion-verifier-Cigap8CG.js → completion-verifier-YwoeujPl.js} +2 -2
  25. package/dist/completion-verifier-YwoeujPl.js.map +1 -0
  26. package/dist/contract/index.d.ts +10 -10
  27. package/dist/contract/index.js +7 -7
  28. package/dist/decision-point-Co3u3W8k.js +831 -0
  29. package/dist/decision-point-Co3u3W8k.js.map +1 -0
  30. package/dist/default-registry-BMHqNR6_.d.ts +257 -0
  31. package/dist/default-registry-BMHqNR6_.d.ts.map +1 -0
  32. package/dist/{default-registry-ovrIBGmH.js → default-registry-BbFCkqvB.js} +607 -14
  33. package/dist/default-registry-BbFCkqvB.js.map +1 -0
  34. package/dist/{define-agent-eval-C2nFhHPu.d.ts → define-agent-eval-Bsoi2GUV.d.ts} +7 -7
  35. package/dist/{define-agent-eval-C2nFhHPu.d.ts.map → define-agent-eval-Bsoi2GUV.d.ts.map} +1 -1
  36. package/dist/{define-agent-eval-UQY3VbJ2.js → define-agent-eval-CJhECJNL.js} +4 -4
  37. package/dist/{define-agent-eval-UQY3VbJ2.js.map → define-agent-eval-CJhECJNL.js.map} +1 -1
  38. package/dist/diagnosis/index.d.ts +2 -2
  39. package/dist/diagnosis/index.js +1 -1
  40. package/dist/{dspy-rlm-engine-Bn_Mt_LW.js → dspy-rlm-engine-BTy7u0jQ.js} +3 -3
  41. package/dist/{dspy-rlm-engine-Bn_Mt_LW.js.map → dspy-rlm-engine-BTy7u0jQ.js.map} +1 -1
  42. package/dist/{engine-BpGGw6cd.d.ts → engine-BF95CWzH.d.ts} +2 -2
  43. package/dist/{engine-BpGGw6cd.d.ts.map → engine-BF95CWzH.d.ts.map} +1 -1
  44. package/dist/{eval-campaign-BUMIxKTE.js → eval-campaign-DoX5vz3E.js} +2 -2
  45. package/dist/{eval-campaign-BUMIxKTE.js.map → eval-campaign-DoX5vz3E.js.map} +1 -1
  46. package/dist/{evaluation-CBdQt_kr.d.ts → evaluation-D1PGzkPR.d.ts} +3 -3
  47. package/dist/{evaluation-CBdQt_kr.d.ts.map → evaluation-D1PGzkPR.d.ts.map} +1 -1
  48. package/dist/evaluation-wdGyZ7jV.js +147 -0
  49. package/dist/evaluation-wdGyZ7jV.js.map +1 -0
  50. package/dist/evaluation.d.ts +1 -1
  51. package/dist/evaluation.js +1 -136
  52. package/dist/{exact-types-BYFmYq44.d.ts → exact-types-CVn1QxFO.d.ts} +2 -2
  53. package/dist/{exact-types-BYFmYq44.d.ts.map → exact-types-CVn1QxFO.d.ts.map} +1 -1
  54. package/dist/experiment/index.d.ts +3 -3
  55. package/dist/experiment/index.js +2 -2
  56. package/dist/{external-optimizer-process-wOLfzsCC.js → external-optimizer-process-E5yY2SYS.js} +2 -2
  57. package/dist/{external-optimizer-process-wOLfzsCC.js.map → external-optimizer-process-E5yY2SYS.js.map} +1 -1
  58. package/dist/{external-optimizer-subprocess-D670Oxf2.js → external-optimizer-subprocess-DA02c_L6.js} +12 -19
  59. package/dist/{external-optimizer-subprocess-D670Oxf2.js.map → external-optimizer-subprocess-DA02c_L6.js.map} +1 -1
  60. package/dist/{feedback-trajectory-DhB9WzYg.d.ts → feedback-trajectory-BZhVCWuz.d.ts} +3 -3
  61. package/dist/{feedback-trajectory-DhB9WzYg.d.ts.map → feedback-trajectory-BZhVCWuz.d.ts.map} +1 -1
  62. package/dist/finding-composition-8n0fFgVI.js +131 -0
  63. package/dist/finding-composition-8n0fFgVI.js.map +1 -0
  64. package/dist/{findings-store-CvNo712L.js → findings-store-DRiFdoid.js} +4 -4
  65. package/dist/{findings-store-CvNo712L.js.map → findings-store-DRiFdoid.js.map} +1 -1
  66. package/dist/{index-CVFStrQD.d.ts → index-BJZ7s-sv.d.ts} +7 -58
  67. package/dist/index-BJZ7s-sv.d.ts.map +1 -0
  68. package/dist/{index-Q6DvdcwI.d.ts → index-BvX3CFNS.d.ts} +6 -6
  69. package/dist/{index-Q6DvdcwI.d.ts.map → index-BvX3CFNS.d.ts.map} +1 -1
  70. package/dist/index-DWd1gUwR.d.ts +1086 -0
  71. package/dist/index-DWd1gUwR.d.ts.map +1 -0
  72. package/dist/{index-DAXfpVf7.d.ts → index-y7i8l6Y_.d.ts} +8 -8
  73. package/dist/{index-DAXfpVf7.d.ts.map → index-y7i8l6Y_.d.ts.map} +1 -1
  74. package/dist/index.d.ts +18 -17
  75. package/dist/index.d.ts.map +1 -1
  76. package/dist/index.js +15 -15
  77. package/dist/{kind-factory-BhxbtUsQ.js → kind-factory-Dl0PmNQL.js} +2 -2
  78. package/dist/{kind-factory-BhxbtUsQ.js.map → kind-factory-Dl0PmNQL.js.map} +1 -1
  79. package/dist/{llm-judge-Cc8vDJh_.js → llm-judge-3uAeRawE.js} +4 -4
  80. package/dist/{llm-judge-Cc8vDJh_.js.map → llm-judge-3uAeRawE.js.map} +1 -1
  81. package/dist/{matrix-Cf-AGxGh.d.ts → matrix-BXo3PSqM.d.ts} +2 -2
  82. package/dist/{matrix-Cf-AGxGh.d.ts.map → matrix-BXo3PSqM.d.ts.map} +1 -1
  83. package/dist/meta-eval/index.d.ts +3 -638
  84. package/dist/meta-eval/index.js +3 -193
  85. package/dist/meta-eval/index.js.map +1 -1
  86. package/dist/multishot/golden/index.d.ts +1 -1
  87. package/dist/multishot/index.d.ts +2 -2
  88. package/dist/openapi.json +1 -1
  89. package/dist/outcome-observations-FLmRpgYa.js +78 -0
  90. package/dist/outcome-observations-FLmRpgYa.js.map +1 -0
  91. package/dist/{paired-arms-Ct4LTKc1.js → paired-arms-B2ttLc0_.js} +108 -31
  92. package/dist/paired-arms-B2ttLc0_.js.map +1 -0
  93. package/dist/{power-and-mde-N5nU4_Ly.js → power-and-mde-CQX-0weG.js} +2 -2
  94. package/dist/{power-and-mde-N5nU4_Ly.js.map → power-and-mde-CQX-0weG.js.map} +1 -1
  95. package/dist/{prime-protocol-CckHBxGu.d.ts → prime-protocol-BEaqBoQE.d.ts} +2 -2
  96. package/dist/{prime-protocol-CckHBxGu.d.ts.map → prime-protocol-BEaqBoQE.d.ts.map} +1 -1
  97. package/dist/{proposal-findings-E1aSC_cU.js → proposal-findings-D0_zkQ2l.js} +2 -2
  98. package/dist/{proposal-findings-E1aSC_cU.js.map → proposal-findings-D0_zkQ2l.js.map} +1 -1
  99. package/dist/{registry-B_yG-1jh.d.ts → registry-DDKaUrmM.d.ts} +3 -3
  100. package/dist/{registry-B_yG-1jh.d.ts.map → registry-DDKaUrmM.d.ts.map} +1 -1
  101. package/dist/reporting.d.ts +1 -1
  102. package/dist/reporting.js +3 -3
  103. package/dist/rl.d.ts +4 -5
  104. package/dist/rl.d.ts.map +1 -1
  105. package/dist/rl.js +5 -4
  106. package/dist/rl.js.map +1 -1
  107. package/dist/{rubric-predictive-validity-noY7uE03.d.ts → rubric-predictive-validity-Cd5SCtAf.d.ts} +58 -3
  108. package/dist/rubric-predictive-validity-Cd5SCtAf.d.ts.map +1 -0
  109. package/dist/{rubric-predictive-validity-D3_oI72N.js → rubric-predictive-validity-CeKW2GQN.js} +3 -77
  110. package/dist/rubric-predictive-validity-CeKW2GQN.js.map +1 -0
  111. package/dist/search/index.d.ts +2 -2
  112. package/dist/{search-kernel-Dloxd6gs.d.ts → search-kernel-C6__V0IS.d.ts} +2 -2
  113. package/dist/{search-kernel-Dloxd6gs.d.ts.map → search-kernel-C6__V0IS.d.ts.map} +1 -1
  114. package/dist/{skillopt-optimization-method-DLKqdhcR.js → skillopt-optimization-method-D21dH_Bh.js} +4 -4
  115. package/dist/{skillopt-optimization-method-DLKqdhcR.js.map → skillopt-optimization-method-D21dH_Bh.js.map} +1 -1
  116. package/dist/{statistical-heldout-3z3I-kJN.d.ts → statistical-heldout-pD1Yah-0.d.ts} +58 -8
  117. package/dist/statistical-heldout-pD1Yah-0.d.ts.map +1 -0
  118. package/dist/{store-otlp-dyWE3wAG.js → store-otlp-BVZfR168.js} +2 -2
  119. package/dist/{store-otlp-dyWE3wAG.js.map → store-otlp-BVZfR168.js.map} +1 -1
  120. package/dist/{store-tool-spans-DIUgZbzu.js → store-tool-spans-CjYiF4fF.js} +3 -3
  121. package/dist/{store-tool-spans-DIUgZbzu.js.map → store-tool-spans-CjYiF4fF.js.map} +1 -1
  122. package/dist/{store-tool-spans-DPwXHQkH.d.ts → store-tool-spans-DfnwWMFR.d.ts} +4 -4
  123. package/dist/{store-tool-spans-DPwXHQkH.d.ts.map → store-tool-spans-DfnwWMFR.d.ts.map} +1 -1
  124. package/dist/{summary-report-BsXJoYX5.js → summary-report-DHDWxe6p.js} +3 -3
  125. package/dist/{summary-report-BsXJoYX5.js.map → summary-report-DHDWxe6p.js.map} +1 -1
  126. package/dist/systemone-D3MrW63C.d.ts +400 -0
  127. package/dist/systemone-D3MrW63C.d.ts.map +1 -0
  128. package/dist/{systemone-protocol-DKoi1NdK.d.ts → systemone-protocol-Bl2EI2KQ.d.ts} +4 -2
  129. package/dist/{systemone-protocol-DKoi1NdK.d.ts.map → systemone-protocol-Bl2EI2KQ.d.ts.map} +1 -1
  130. package/dist/systemone-protocol.d.ts +2 -2
  131. package/dist/systemone-protocol.js +7 -7
  132. package/dist/systemone-protocol.js.map +1 -1
  133. package/dist/{systemone-review-CUBMuTLi.d.ts → systemone-review-C8DRiT_-.d.ts} +3 -3
  134. package/dist/{systemone-review-CUBMuTLi.d.ts.map → systemone-review-C8DRiT_-.d.ts.map} +1 -1
  135. package/dist/{systemone-review-DzdOJ8I6.js → systemone-review-DFGtIUcf.js} +2 -2
  136. package/dist/{systemone-review-DzdOJ8I6.js.map → systemone-review-DFGtIUcf.js.map} +1 -1
  137. package/dist/systemone.d.ts +5 -5
  138. package/dist/systemone.js +5 -343
  139. package/dist/{tool-groups-LISbBWCg.d.ts → tool-groups-DK1bu5TD.d.ts} +3 -3
  140. package/dist/tool-groups-DK1bu5TD.d.ts.map +1 -0
  141. package/dist/{trace-questions-C42fYEE4.d.ts → trace-questions-D_OKYZ6u.d.ts} +3 -3
  142. package/dist/{trace-questions-C42fYEE4.d.ts.map → trace-questions-D_OKYZ6u.d.ts.map} +1 -1
  143. package/dist/trace-repair/index.d.ts +1 -1
  144. package/dist/traces.d.ts +3 -3
  145. package/dist/traces.js +3 -3
  146. package/dist/{types-DqFMNTgK.js → types-CnWmj8NW.js} +19 -6
  147. package/dist/types-CnWmj8NW.js.map +1 -0
  148. package/dist/{types-CHfn1zg5.d.ts → types-DDKfH-N6.d.ts} +2 -2
  149. package/dist/{types-CHfn1zg5.d.ts.map → types-DDKfH-N6.d.ts.map} +1 -1
  150. package/dist/{types-8yQzNm8u.d.ts → types-DGImvHIr.d.ts} +150 -4
  151. package/dist/types-DGImvHIr.d.ts.map +1 -0
  152. package/dist/{types-D8GXK9Z5.d.ts → types-IERw_HxR.d.ts} +2 -2
  153. package/dist/{types-D8GXK9Z5.d.ts.map → types-IERw_HxR.d.ts.map} +1 -1
  154. package/dist/wire/index.d.ts +1 -1
  155. package/docs/behavioral-trace-questions.md +99 -0
  156. package/docs/experiment.md +27 -0
  157. package/docs/finding-layers.md +54 -1
  158. package/docs/systemone.md +107 -0
  159. package/package.json +4 -4
  160. package/dist/benchmark-command-Dx0E4a6z.js.map +0 -1
  161. package/dist/completion-verifier-Cigap8CG.js.map +0 -1
  162. package/dist/default-registry-Cwg_QN3d.d.ts +0 -70
  163. package/dist/default-registry-Cwg_QN3d.d.ts.map +0 -1
  164. package/dist/default-registry-ovrIBGmH.js.map +0 -1
  165. package/dist/evaluation.js.map +0 -1
  166. package/dist/index-CVFStrQD.d.ts.map +0 -1
  167. package/dist/judge-gate-Dc_mXQsL.d.ts +0 -453
  168. package/dist/judge-gate-Dc_mXQsL.d.ts.map +0 -1
  169. package/dist/meta-eval/index.d.ts.map +0 -1
  170. package/dist/outcome-store-CNt4iZ67.d.ts +0 -58
  171. package/dist/outcome-store-CNt4iZ67.d.ts.map +0 -1
  172. package/dist/paired-arms-Ct4LTKc1.js.map +0 -1
  173. package/dist/rubric-predictive-validity-D3_oI72N.js.map +0 -1
  174. package/dist/rubric-predictive-validity-noY7uE03.d.ts.map +0 -1
  175. package/dist/statistical-heldout-3z3I-kJN.d.ts.map +0 -1
  176. package/dist/systemone-DVA7t76V.d.ts +0 -135
  177. package/dist/systemone-DVA7t76V.d.ts.map +0 -1
  178. package/dist/systemone.js.map +0 -1
  179. package/dist/tool-groups-LISbBWCg.d.ts.map +0 -1
  180. package/dist/types-8yQzNm8u.d.ts.map +0 -1
  181. package/dist/types-DqFMNTgK.js.map +0 -1
@@ -10,19 +10,19 @@ import { r as projectCampaignCellQuality, t as campaignCellCostProvenance } from
10
10
  import { n as CostAccountingIncompleteError, t as CostLedger } from "./cost-ledger-BGZB6yY2.js";
11
11
  import { A as surfaceHashMatches, D as surfaceContentHash, E as renderSurfaceDiff, F as assertCampaignSplitIdentity, I as assertCompleteCampaign, L as campaignCoverage, O as surfaceDispatchRef, P as assertCampaignDesign, R as campaignScenarioIdentity, V as formatCoverageFailures, b as FinalEvidenceConflictError, f as campaignBreakdown, j as BackendIntegrityError, k as surfaceHash, m as campaignMeanCompositeOrNull, p as campaignMeanComposite, x as FinalEvidenceError, z as campaignSplitDigest } from "./campaign-evidence-DunzcJGv.js";
12
12
  import { t as deepFreezeCanonicalJson } from "./deep-freeze-CurcOQg3.js";
13
- import { M as fsCampaignStorage, h as isExternalTextCandidate, j as createRunCostLedger } from "./external-optimizer-subprocess-D670Oxf2.js";
13
+ import { M as fsCampaignStorage, h as isExternalTextCandidate, j as createRunCostLedger } from "./external-optimizer-subprocess-DA02c_L6.js";
14
14
  import { r as summarizeEvaluationUnits, t as defineEvaluationClaim } from "./claim-BPVuyHuy.js";
15
15
  import { d as detectPersonalData, s as redactText, t as REDACTION_VERSION, u as detectCredential } from "./redact-mtkTiJVk.js";
16
16
  import { t as detectRewardHacking } from "./reward-hacking-ByuETaIb.js";
17
- import { t as assertProposalFindings } from "./proposal-findings-E1aSC_cU.js";
17
+ import { t as assertProposalFindings } from "./proposal-findings-D0_zkQ2l.js";
18
18
  import { i as runSearch, m as searchExpansionIndex, n as paretoFrontier, o as searchPolicyView, p as SEARCH_KERNEL_SOURCE, r as paretoFrontierWithCrowding, s as EXPANSION_OPERATORS, w as estimateNode } from "./pareto-BiBnQXAE.js";
19
19
  import { a as validateSearchLedgerEvent, d as searchNodeId, f as searchTaskSetDigest, i as replaySearchLedgerText, n as openSearchLedger, u as searchCellId } from "./search-ledger-CZRqtFbW.js";
20
20
  import { n as searchProposerView, t as renderSearchSummary } from "./search-summary-D4bwYnAE.js";
21
21
  import { i as stripFencedJson, n as isRecord } from "./json-BhdsJaOQ.js";
22
22
  import { a as maximumChargeForLlmRequest, i as costReceiptFromLlmError, r as costReceiptFromLlm } from "./llm-client-DXuOTseU.js";
23
23
  import { createHash } from "node:crypto";
24
- import { writeFileSync } from "node:fs";
25
24
  import { z } from "zod";
25
+ import { writeFileSync } from "node:fs";
26
26
  import { basename, dirname, isAbsolute, join, relative, resolve, sep } from "node:path";
27
27
  import { homedir, tmpdir } from "node:os";
28
28
  import { execSync } from "node:child_process";
@@ -5933,4 +5933,4 @@ function firstString(value) {
5933
5933
  //#endregion
5934
5934
  export { planCampaignRun as $, verifySearchHistoryReceipt as A, defaultProductionGate as B, searchEdgeId as C, assertSearchHistoryMatchesState as D, assertSearchHistoryAdmissionOptions as E, asha as F, runCanaries as G, redTeamDataset as H, uniform as I, evaluationUnitMap as J, assertIndependentEvaluationSplit as K, runFinalComparison as L, searchModelIdentity as M, searchProposalExecution as N, createSearchHistoryReceipt as O, searchReceiptAccounting as P, runCampaign as Q, openAutoPr as R, developmentClaim as S, surfaceNode as T, redTeamReport as U, DEFAULT_RED_TEAM_CORPUS as V, scoreRedTeamOutput as W, reserveFinalEvidence as X, exposeFinalEvidence as Y, runEval as Z, beam as _, aggregateRunScore as a, incumbentWithOperatorBandit as b, assertGepaCandidatePopulationSummary as c, costFromLedgerSummary as d, resolveRunDir as et, optimizationTokenUsageFromSummary as f, aide as g, isProposedCandidate as h, transientDispatchFailure as i, campaignCellSearchResult as j, verifySearchHistoryArtifact as k, readGepaCandidatePopulationArtifact as l, runOptimization as m, JudgeParseError as n, cellCachePath as nt, clamp01 as o, runImprovementLoop as p, captureFinalEvidencePolicy as q, isTransientTransportFailure as r, computeManifestHash as rt, executeOptimizationMethod as s, llmJudge as t, buildCellSchedule as tt, combineComparisonCosts as u, crowdedFrontierParent as v, surfaceDiff as w, SearchRecorder as x, incumbent as y, captureJudge as z };
5935
5935
 
5936
- //# sourceMappingURL=llm-judge-Cc8vDJh_.js.map
5936
+ //# sourceMappingURL=llm-judge-3uAeRawE.js.map