@tangle-network/agent-eval 0.197.0 → 0.198.1

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 (150) hide show
  1. package/CHANGELOG.md +55 -0
  2. package/README.md +3 -1
  3. package/dist/active-curriculum-B_Lc9kfO.js +61 -0
  4. package/dist/active-curriculum-B_Lc9kfO.js.map +1 -0
  5. package/dist/adapters/http.d.ts +2 -2
  6. package/dist/analyst/index.d.ts +5 -5
  7. package/dist/analyst/index.js +3 -3
  8. package/dist/{analyze-runs-B6gv7vAT.js → analyze-runs-DFbp2gB8.js} +5 -5
  9. package/dist/{analyze-runs-B6gv7vAT.js.map → analyze-runs-DFbp2gB8.js.map} +1 -1
  10. package/dist/{benchmark-command-DB7pxlks.js → benchmark-command-DKQuLrrD.js} +6 -5
  11. package/dist/{benchmark-command-DB7pxlks.js.map → benchmark-command-DKQuLrrD.js.map} +1 -1
  12. package/dist/benchmarks/index.d.ts +4 -3
  13. package/dist/benchmarks/index.d.ts.map +1 -1
  14. package/dist/benchmarks/index.js +3 -3
  15. package/dist/campaign/index.d.ts +5 -4
  16. package/dist/campaign/index.js +13 -11
  17. package/dist/{campaign-BUFSOI36.js → campaign-DRdKwxm-.js} +13 -12
  18. package/dist/{campaign-BUFSOI36.js.map → campaign-DRdKwxm-.js.map} +1 -1
  19. package/dist/{campaign-evidence-DJc60F9C.js → campaign-evidence-jL_U7Ikv.js} +2 -2
  20. package/dist/{campaign-evidence-DJc60F9C.js.map → campaign-evidence-jL_U7Ikv.js.map} +1 -1
  21. package/dist/cli.js +247 -13
  22. package/dist/cli.js.map +1 -1
  23. package/dist/contract/index.d.ts +7 -6
  24. package/dist/contract/index.js +9 -9
  25. package/dist/{default-registry-D2csUBBQ.d.ts → default-registry-oK9hHfX_.d.ts} +3 -3
  26. package/dist/{default-registry-D2csUBBQ.d.ts.map → default-registry-oK9hHfX_.d.ts.map} +1 -1
  27. package/dist/{define-agent-eval-ulRlLvse.d.ts → define-agent-eval-9JYoCkDI.d.ts} +5 -4
  28. package/dist/define-agent-eval-9JYoCkDI.d.ts.map +1 -0
  29. package/dist/{define-agent-eval-4J02MdF7.js → define-agent-eval-DkfcqaCF.js} +6 -6
  30. package/dist/{define-agent-eval-4J02MdF7.js.map → define-agent-eval-DkfcqaCF.js.map} +1 -1
  31. package/dist/diagnosis/index.js +1 -1
  32. package/dist/{dspy-rlm-engine-k_QdEBZo.js → dspy-rlm-engine-B5T43BkZ.js} +2 -2
  33. package/dist/{dspy-rlm-engine-k_QdEBZo.js.map → dspy-rlm-engine-B5T43BkZ.js.map} +1 -1
  34. package/dist/{engine-De2hfuiQ.d.ts → engine-Dc996kAg.d.ts} +2 -2
  35. package/dist/{engine-De2hfuiQ.d.ts.map → engine-Dc996kAg.d.ts.map} +1 -1
  36. package/dist/{eval-campaign-CXT2WYUe.js → eval-campaign-GapmPHIA.js} +2 -2
  37. package/dist/{eval-campaign-CXT2WYUe.js.map → eval-campaign-GapmPHIA.js.map} +1 -1
  38. package/dist/evaluation.d.ts +1 -1
  39. package/dist/experiment/index.d.ts +1 -1
  40. package/dist/experiment/index.js +8 -6
  41. package/dist/experiment/index.js.map +1 -1
  42. package/dist/{external-optimizer-process-_YIECYJ7.js → external-optimizer-process-CEXcCKqd.js} +2 -2
  43. package/dist/{external-optimizer-process-_YIECYJ7.js.map → external-optimizer-process-CEXcCKqd.js.map} +1 -1
  44. package/dist/{external-optimizer-subprocess-BrghTvEp.js → external-optimizer-subprocess-laM1-UDV.js} +2 -61
  45. package/dist/external-optimizer-subprocess-laM1-UDV.js.map +1 -0
  46. package/dist/fuzz.d.ts.map +1 -1
  47. package/dist/fuzz.js +2 -3
  48. package/dist/fuzz.js.map +1 -1
  49. package/dist/hosted/index.js +1 -1
  50. package/dist/{index-DJKZEldg.d.ts → index-BXJHJ_jE.d.ts} +12 -947
  51. package/dist/index-BXJHJ_jE.d.ts.map +1 -0
  52. package/dist/{index-CRsmcAGl.d.ts → index-DzQ6T34s.d.ts} +6 -6
  53. package/dist/{index-CRsmcAGl.d.ts.map → index-DzQ6T34s.d.ts.map} +1 -1
  54. package/dist/{index-kKECJfib.d.ts → index-lbwvO9vJ.d.ts} +3 -3
  55. package/dist/{index-kKECJfib.d.ts.map → index-lbwvO9vJ.d.ts.map} +1 -1
  56. package/dist/index.d.ts +9 -9
  57. package/dist/index.js +15 -13
  58. package/dist/index.js.map +1 -1
  59. package/dist/jev.d.ts +1 -1
  60. package/dist/{llm-judge-fhkFQL1N.js → llm-judge-3ncNcWNT.js} +415 -1981
  61. package/dist/llm-judge-3ncNcWNT.js.map +1 -0
  62. package/dist/{matrix-C1X-fIVX.d.ts → matrix-BnksRaDD.d.ts} +2 -2
  63. package/dist/{matrix-C1X-fIVX.d.ts.map → matrix-BnksRaDD.d.ts.map} +1 -1
  64. package/dist/multiplicity-D9cjmStq.js +101 -0
  65. package/dist/multiplicity-D9cjmStq.js.map +1 -0
  66. package/dist/multishot/golden/index.d.ts +1 -1
  67. package/dist/multishot/golden/index.js +1 -1
  68. package/dist/multishot/index.d.ts +2 -2
  69. package/dist/multishot/index.js +1 -1
  70. package/dist/openapi.json +1 -1
  71. package/dist/{paired-arms-JSDcs2zx.js → paired-arms-DKZFVPt8.js} +4 -398
  72. package/dist/paired-arms-DKZFVPt8.js.map +1 -0
  73. package/dist/paired-binary-fzkwENI4.js +399 -0
  74. package/dist/paired-binary-fzkwENI4.js.map +1 -0
  75. package/dist/{paired-promotion-decision-DTKl6-G8.js → paired-promotion-decision-D5B1Cxc2.js} +78 -5
  76. package/dist/paired-promotion-decision-D5B1Cxc2.js.map +1 -0
  77. package/dist/{power-and-mde-BJOpt6pq.js → power-and-mde-K_CmO3dc.js} +3 -101
  78. package/dist/power-and-mde-K_CmO3dc.js.map +1 -0
  79. package/dist/{produced-state-1RnbLrSa.js → produced-state-qIhqN3V5.js} +3 -3
  80. package/dist/{produced-state-1RnbLrSa.js.map → produced-state-qIhqN3V5.js.map} +1 -1
  81. package/dist/{promotion-policy-Cy5OV8BV.js → promotion-policy-C6FAJvmZ.js} +3 -3
  82. package/dist/{promotion-policy-Cy5OV8BV.js.map → promotion-policy-C6FAJvmZ.js.map} +1 -1
  83. package/dist/reporting.js +3 -3
  84. package/dist/rl.d.ts +17 -39
  85. package/dist/rl.d.ts.map +1 -1
  86. package/dist/rl.js +5 -5
  87. package/dist/search/index.d.ts +1187 -0
  88. package/dist/search/index.d.ts.map +1 -0
  89. package/dist/search/index.js +187 -0
  90. package/dist/search/index.js.map +1 -0
  91. package/dist/search-kernel-CumYAjA3.js +2427 -0
  92. package/dist/search-kernel-CumYAjA3.js.map +1 -0
  93. package/dist/search-kernel-TLoiMMcq.d.ts +1185 -0
  94. package/dist/search-kernel-TLoiMMcq.d.ts.map +1 -0
  95. package/dist/{search-ledger-9W0g5FP6.js → search-ledger-BnUytR8X.js} +3 -1
  96. package/dist/search-ledger-BnUytR8X.js.map +1 -0
  97. package/dist/{search-shipper-CYbmJQx8.js → search-shipper-Cn8cxcyp.js} +2 -2
  98. package/dist/{search-shipper-CYbmJQx8.js.map → search-shipper-Cn8cxcyp.js.map} +1 -1
  99. package/dist/search-summary-dJOaZ3Dw.js +133 -0
  100. package/dist/search-summary-dJOaZ3Dw.js.map +1 -0
  101. package/dist/{semantic-concept-judge-Bh5lvKGg.js → semantic-concept-judge-2SE_kXGF.js} +2 -2
  102. package/dist/{semantic-concept-judge-Bh5lvKGg.js.map → semantic-concept-judge-2SE_kXGF.js.map} +1 -1
  103. package/dist/{sequential-C21_PP7F.js → sequential-Yz3OSskl.js} +2 -2
  104. package/dist/{sequential-C21_PP7F.js.map → sequential-Yz3OSskl.js.map} +1 -1
  105. package/dist/single-run-lock-fVu3MZWH.js +62 -0
  106. package/dist/single-run-lock-fVu3MZWH.js.map +1 -0
  107. package/dist/{skillopt-optimization-method-CHUcZ8w6.js → skillopt-optimization-method-BL_j6mX8.js} +8 -7
  108. package/dist/{skillopt-optimization-method-CHUcZ8w6.js.map → skillopt-optimization-method-BL_j6mX8.js.map} +1 -1
  109. package/dist/{statistical-heldout-DANVmyug.js → statistical-heldout-BAFDCo07.js} +2 -2
  110. package/dist/{statistical-heldout-DANVmyug.js.map → statistical-heldout-BAFDCo07.js.map} +1 -1
  111. package/dist/{statistical-heldout-BedVSZb2.d.ts → statistical-heldout-CMpxMjlQ.d.ts} +2 -2
  112. package/dist/{statistical-heldout-BedVSZb2.d.ts.map → statistical-heldout-CMpxMjlQ.d.ts.map} +1 -1
  113. package/dist/{store-tool-spans-CawP-WxM.d.ts → store-tool-spans-CUwWSXoj.d.ts} +3 -3
  114. package/dist/{store-tool-spans-CawP-WxM.d.ts.map → store-tool-spans-CUwWSXoj.d.ts.map} +1 -1
  115. package/dist/{summary-report-BMvou2oZ.js → summary-report-BeYnvddy.js} +4 -3
  116. package/dist/{summary-report-BMvou2oZ.js.map → summary-report-BeYnvddy.js.map} +1 -1
  117. package/dist/{tool-groups-B4JVrH3g.d.ts → tool-groups-DVJAR1GE.d.ts} +2 -2
  118. package/dist/tool-groups-DVJAR1GE.d.ts.map +1 -0
  119. package/dist/trace-repair/index.d.ts +1 -1
  120. package/dist/traces.d.ts +2 -2
  121. package/dist/tree-DxGfhISA.js +4100 -0
  122. package/dist/tree-DxGfhISA.js.map +1 -0
  123. package/dist/{types-B3jzCp0p.js → types-B3jzCp0p2.js} +1 -1
  124. package/dist/types-B3jzCp0p2.js.map +1 -0
  125. package/dist/{types-CjFDKMDe.d.ts → types-D94EanDL.d.ts} +2 -2
  126. package/dist/{types-CjFDKMDe.d.ts.map → types-D94EanDL.d.ts.map} +1 -1
  127. package/dist/{types-B2673PBj.d.ts → types-EBUav9Bu.d.ts} +8 -4
  128. package/dist/types-EBUav9Bu.d.ts.map +1 -0
  129. package/docs/campaign-proposers.md +2 -0
  130. package/docs/design/statistics-decisions.md +1 -1
  131. package/docs/search-ledger.md +145 -8
  132. package/docs/trace-contracts.md +1 -3
  133. package/package.json +6 -1
  134. package/dist/active-curriculum-OjIWgrUJ.js +0 -204
  135. package/dist/active-curriculum-OjIWgrUJ.js.map +0 -1
  136. package/dist/define-agent-eval-ulRlLvse.d.ts.map +0 -1
  137. package/dist/external-optimizer-subprocess-BrghTvEp.js.map +0 -1
  138. package/dist/index-DJKZEldg.d.ts.map +0 -1
  139. package/dist/llm-judge-fhkFQL1N.js.map +0 -1
  140. package/dist/paired-arms-JSDcs2zx.js.map +0 -1
  141. package/dist/paired-delta-test-BF-FEP8V.js +0 -78
  142. package/dist/paired-delta-test-BF-FEP8V.js.map +0 -1
  143. package/dist/paired-promotion-decision-DTKl6-G8.js.map +0 -1
  144. package/dist/power-and-mde-BJOpt6pq.js.map +0 -1
  145. package/dist/search-ledger-9W0g5FP6.js.map +0 -1
  146. package/dist/search-summary-CcavvYLe.js +0 -378
  147. package/dist/search-summary-CcavvYLe.js.map +0 -1
  148. package/dist/tool-groups-B4JVrH3g.d.ts.map +0 -1
  149. package/dist/types-B2673PBj.d.ts.map +0 -1
  150. package/dist/types-B3jzCp0p.js.map +0 -1
package/dist/jev.d.ts CHANGED
@@ -1,6 +1,6 @@
1
1
  import { b as CustomTokenPricing, g as CostReceiptInput } from "./cost-ledger-DbQdN3nO.js";
2
2
  import { i as AnalystFinding, n as AnalystContext, t as Analyst } from "./types-CeDfCRXp.js";
3
- import { R as Scenario, S as JudgeConfig, w as JudgeScore } from "./types-B2673PBj.js";
3
+ import { R as Scenario, S as JudgeConfig, w as JudgeScore } from "./types-EBUav9Bu.js";
4
4
  import { EvaluationAnalystOptions, EvaluationContext, EvaluationJudgeOptions, EvaluationResult, Evaluator, EvaluatorOptions, asAnalyst, asJudge, createEvaluator } from "./evaluation.js";
5
5
  import { JevAnswer, JevAnswerFor, JevDescription, JevJson, JevQuestion, JevQuestions, JevRequest, JevResponseError, JevResult, JevScoreCriteria, JevState, jevUsage, parseJevQuestions, parseJevRequest, parseJevResult } from "./jev-protocol.js";
6
6
  import { z } from "zod";