@tangle-network/agent-eval 0.222.0 → 0.223.0

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 (80) hide show
  1. package/CHANGELOG.md +177 -0
  2. package/dist/analyst/index.d.ts.map +1 -1
  3. package/dist/analyst/index.js +1 -1
  4. package/dist/{analyze-runs-CTheASYV.js → analyze-runs-Ck68mbgj.js} +7 -9
  5. package/dist/analyze-runs-Ck68mbgj.js.map +1 -0
  6. package/dist/{benchmark-command-jYWR2gya.js → benchmark-command-CH86twZj.js} +32 -37
  7. package/dist/benchmark-command-CH86twZj.js.map +1 -0
  8. package/dist/benchmarks/index.js +3 -3
  9. package/dist/campaign/index.js +9 -9
  10. package/dist/{campaign-ddr1N3yD.js → campaign-DdOgQfp8.js} +14 -19
  11. package/dist/campaign-DdOgQfp8.js.map +1 -0
  12. package/dist/{campaign-evidence-DN8rWuBj.js → campaign-evidence-MjCjkb5a.js} +3 -3
  13. package/dist/{campaign-evidence-DN8rWuBj.js.map → campaign-evidence-MjCjkb5a.js.map} +1 -1
  14. package/dist/cli.js +4 -4
  15. package/dist/contract/index.js +11 -10
  16. package/dist/contract/index.js.map +1 -1
  17. package/dist/{define-agent-eval-BLoP4Lf9.js → define-agent-eval-Cc15qGik.js} +5 -5
  18. package/dist/{define-agent-eval-BLoP4Lf9.js.map → define-agent-eval-Cc15qGik.js.map} +1 -1
  19. package/dist/diagnosis/index.js +1 -1
  20. package/dist/{eval-campaign-Cgixrvf7.js → eval-campaign-C_mNDshv.js} +2 -2
  21. package/dist/{eval-campaign-Cgixrvf7.js.map → eval-campaign-C_mNDshv.js.map} +1 -1
  22. package/dist/experiment/index.js +7 -7
  23. package/dist/index-B7v2QHlD.d.ts.map +1 -1
  24. package/dist/index-DAk2quYu.d.ts.map +1 -1
  25. package/dist/index-aDPVYBIM.d.ts.map +1 -1
  26. package/dist/index.js +13 -12
  27. package/dist/index.js.map +1 -1
  28. package/dist/{judge-gate-C2BCOt-M.js → judge-gate-Di_6bifh.js} +4 -4
  29. package/dist/judge-gate-Di_6bifh.js.map +1 -0
  30. package/dist/{llm-judge-cgbhTKQp.js → llm-judge-D6JtIqiU.js} +9 -9
  31. package/dist/{llm-judge-cgbhTKQp.js.map → llm-judge-D6JtIqiU.js.map} +1 -1
  32. package/dist/mean-BPuUNznQ.js +16 -0
  33. package/dist/mean-BPuUNznQ.js.map +1 -0
  34. package/dist/meta-eval/index.js +1 -1
  35. package/dist/openapi.json +1 -1
  36. package/dist/{paired-arms-D-54hO-k.js → paired-arms-D5H_58e8.js} +2 -2
  37. package/dist/{paired-arms-D-54hO-k.js.map → paired-arms-D5H_58e8.js.map} +1 -1
  38. package/dist/{paired-promotion-decision-FGvHA4p_.js → paired-promotion-decision-BiVumgvM.js} +2 -2
  39. package/dist/{paired-promotion-decision-FGvHA4p_.js.map → paired-promotion-decision-BiVumgvM.js.map} +1 -1
  40. package/dist/{mean-CdDYG-us.js → paired-tests-C2zUqgUW.js} +2 -7
  41. package/dist/paired-tests-C2zUqgUW.js.map +1 -0
  42. package/dist/{pareto-B9udAt2i.js → pareto-7_LEmYGG.js} +4 -3
  43. package/dist/{pareto-B9udAt2i.js.map → pareto-7_LEmYGG.js.map} +1 -1
  44. package/dist/{power-and-mde-ClI6RWw4.js → power-and-mde-CHvyDO_H.js} +2 -2
  45. package/dist/{power-and-mde-ClI6RWw4.js.map → power-and-mde-CHvyDO_H.js.map} +1 -1
  46. package/dist/{promotion-policy-CBYeD4zi.js → promotion-policy-D7B4_jEZ.js} +4 -4
  47. package/dist/{promotion-policy-CBYeD4zi.js.map → promotion-policy-D7B4_jEZ.js.map} +1 -1
  48. package/dist/reporting.js +3 -3
  49. package/dist/{reward-hacking-DZzHZlS1.js → reward-hacking-Bjk3MAjh.js} +7 -9
  50. package/dist/{reward-hacking-DZzHZlS1.js.map → reward-hacking-Bjk3MAjh.js.map} +1 -1
  51. package/dist/reward-hacking-C9hPVT0Q.d.ts.map +1 -1
  52. package/dist/rl.js +6 -6
  53. package/dist/{run-record-CZy4-TnZ.js → run-record-BUm-Jggo.js} +2 -2
  54. package/dist/{run-record-CZy4-TnZ.js.map → run-record-BUm-Jggo.js.map} +1 -1
  55. package/dist/search/index.js +2 -2
  56. package/dist/{search-summary-Ct7SrmVc.js → search-summary-Bt3uuK53.js} +4 -4
  57. package/dist/{search-summary-Ct7SrmVc.js.map → search-summary-Bt3uuK53.js.map} +1 -1
  58. package/dist/{sequential-B1I0tRfL.js → sequential-De7BTAlV.js} +2 -2
  59. package/dist/{sequential-B1I0tRfL.js.map → sequential-De7BTAlV.js.map} +1 -1
  60. package/dist/{skillopt-optimization-method-qB1M554K.js → skillopt-optimization-method-BKFbJEyz.js} +9 -12
  61. package/dist/skillopt-optimization-method-BKFbJEyz.js.map +1 -0
  62. package/dist/{statistical-heldout-TP6ndL0B.js → statistical-heldout-C9hz_AF9.js} +3 -3
  63. package/dist/{statistical-heldout-TP6ndL0B.js.map → statistical-heldout-C9hz_AF9.js.map} +1 -1
  64. package/dist/storyboard/index.d.ts +17 -0
  65. package/dist/storyboard/index.d.ts.map +1 -1
  66. package/dist/storyboard/index.js +154 -107
  67. package/dist/storyboard/index.js.map +1 -1
  68. package/dist/{summary-report-CPfsrLac.js → summary-report-BLnTyQKH.js} +5 -4
  69. package/dist/{summary-report-CPfsrLac.js.map → summary-report-BLnTyQKH.js.map} +1 -1
  70. package/dist/trace-repair/index.js +2 -1
  71. package/dist/trace-repair/index.js.map +1 -1
  72. package/dist/{tree-DrIChF4a.js → tree-DnBkWXun.js} +5 -4
  73. package/dist/{tree-DrIChF4a.js.map → tree-DnBkWXun.js.map} +1 -1
  74. package/package.json +2 -2
  75. package/dist/analyze-runs-CTheASYV.js.map +0 -1
  76. package/dist/benchmark-command-jYWR2gya.js.map +0 -1
  77. package/dist/campaign-ddr1N3yD.js.map +0 -1
  78. package/dist/judge-gate-C2BCOt-M.js.map +0 -1
  79. package/dist/mean-CdDYG-us.js.map +0 -1
  80. package/dist/skillopt-optimization-method-qB1M554K.js.map +0 -1
@@ -2,8 +2,9 @@ import { a as hashCanonical, i as compareCodeUnits, r as canonicalString } from
2
2
  import { t as mulberry32 } from "./random-DrzcgC7F.js";
3
3
  import { t as confidenceInterval } from "./descriptive-cPwITVfy.js";
4
4
  import { s as wilson } from "./paired-binary-BR0nwHOA.js";
5
- import { r as DECISION_PAIRED_DELTA_STATISTIC, t as mean } from "./mean-CdDYG-us.js";
6
- import { i as pairedDeltaTest, r as minimumPairsForPairedDeltaTest, t as decidePairedPromotion } from "./paired-promotion-decision-FGvHA4p_.js";
5
+ import { n as DECISION_PAIRED_DELTA_STATISTIC } from "./paired-tests-C2zUqgUW.js";
6
+ import { t as mean } from "./mean-BPuUNznQ.js";
7
+ import { i as pairedDeltaTest, r as minimumPairsForPairedDeltaTest, t as decidePairedPromotion } from "./paired-promotion-decision-BiVumgvM.js";
7
8
  import { a as SearchLedgerError } from "./search-ledger-file-DTBD6X-y.js";
8
9
  import { s as redactText } from "./redact-D6APJS1d.js";
9
10
  import { l as searchUnitScores, p as USD_TOLERANCE, t as FileSearchLedger, u as searchCellId } from "./search-ledger-BsVi-Ngv.js";
@@ -2608,4 +2609,4 @@ function paretoFrontierWithCrowding(candidates, objectives) {
2608
2609
  }
2609
2610
  export { normalizeSignedZero as A, SEARCH_ESTIMATOR as C, searchEstimateMethod as D, searchCellSetDigest as E, searchPosterior as O, requiredPairsForPairedPromotion as S, estimateNodeFromCells as T, planSearchClaim as _, searchDivergence as a, verifySearchClaim as b, MIN_OUTCOMES_FOR_WEIGHT as c, rankingSplit as d, summarizeSamples as f, decideSearchClaim as g, SEARCH_CLAIM_RULE as h, runSearch as i, seedFromDigest as k, operatorYield as l, searchExpansionIndex as m, paretoFrontier as n, searchPolicyView as o, SEARCH_KERNEL_SOURCE as p, paretoFrontierWithCrowding as r, EXPANSION_OPERATORS as s, dominates as t, INSUFFICIENT_FROM as u, searchClaimDecision as v, estimateNode as w, pairedPromotionPower as x, searchClaimReserveUsd as y };
2610
2611
 
2611
- //# sourceMappingURL=pareto-B9udAt2i.js.map
2612
+ //# sourceMappingURL=pareto-7_LEmYGG.js.map