@tangle-network/agent-eval 0.137.0 → 0.138.0

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 (150) hide show
  1. package/CHANGELOG.md +48 -0
  2. package/README.md +33 -0
  3. package/dist/analyst/index.d.ts +473 -39
  4. package/dist/analyst/index.d.ts.map +1 -1
  5. package/dist/analyst/index.js +11 -593
  6. package/dist/analyst/index.js.map +1 -1
  7. package/dist/{analyze-runs-PVtnfjvA.d.ts → analyze-runs-CPYxfPWT.d.ts} +5 -5
  8. package/dist/{analyze-runs-PVtnfjvA.d.ts.map → analyze-runs-CPYxfPWT.d.ts.map} +1 -1
  9. package/dist/{benchmark-YDrpumqB.js → benchmark-D8dkki-J.js} +299 -159
  10. package/dist/benchmark-D8dkki-J.js.map +1 -0
  11. package/dist/{benchmark-CHX4orG7.d.ts → benchmark-DlQgU_XI.d.ts} +67 -15
  12. package/dist/benchmark-DlQgU_XI.d.ts.map +1 -0
  13. package/dist/benchmark-command-CMqVqReF.js +4332 -0
  14. package/dist/benchmark-command-CMqVqReF.js.map +1 -0
  15. package/dist/benchmarks/index.d.ts +1 -1
  16. package/dist/benchmarks/index.js +1 -1
  17. package/dist/{benchmarks-DCLkQOmc.js → benchmarks-BJ_xK5rQ.js} +4 -3
  18. package/dist/{benchmarks-DCLkQOmc.js.map → benchmarks-BJ_xK5rQ.js.map} +1 -1
  19. package/dist/campaign/index.d.ts +5 -5
  20. package/dist/campaign/index.js +3 -3
  21. package/dist/{campaign-lgObcHFC.js → campaign-BIBS-NHV.js} +16 -9
  22. package/dist/campaign-BIBS-NHV.js.map +1 -0
  23. package/dist/cli.js +9 -2
  24. package/dist/cli.js.map +1 -1
  25. package/dist/{client-C8L6h6Wf.d.ts → client-BwPKohkJ.d.ts} +4 -4
  26. package/dist/{client-C8L6h6Wf.d.ts.map → client-BwPKohkJ.d.ts.map} +1 -1
  27. package/dist/{completion-verifier-DSyRNVzU.d.ts → completion-verifier-B4-IMYcS.d.ts} +3 -3
  28. package/dist/{completion-verifier-DSyRNVzU.d.ts.map → completion-verifier-B4-IMYcS.d.ts.map} +1 -1
  29. package/dist/contract/index.d.ts +10 -10
  30. package/dist/contract/index.js +8 -8
  31. package/dist/control.d.ts +2 -2
  32. package/dist/{cost-ledger-D2o6JOrL.d.ts → cost-ledger-B1D3COAc.d.ts} +5 -4
  33. package/dist/{cost-ledger-D2o6JOrL.d.ts.map → cost-ledger-B1D3COAc.d.ts.map} +1 -1
  34. package/dist/{cost-ledger-D-5_-dhi.js → cost-ledger-CHDLA0Ss.js} +90 -45
  35. package/dist/cost-ledger-CHDLA0Ss.js.map +1 -0
  36. package/dist/{default-registry-Dc5D_Loc.d.ts → default-registry-PUhIVRWz.d.ts} +18 -5
  37. package/dist/default-registry-PUhIVRWz.d.ts.map +1 -0
  38. package/dist/{default-registry-CLXbRt0f.js → default-registry-lp5R0lve.js} +1503 -258
  39. package/dist/default-registry-lp5R0lve.js.map +1 -0
  40. package/dist/{eval-campaign-CHqfLnff.js → eval-campaign-9MozgKL7.js} +2 -2
  41. package/dist/{eval-campaign-CHqfLnff.js.map → eval-campaign-9MozgKL7.js.map} +1 -1
  42. package/dist/exact-types-Dpw2LeHA.d.ts +234 -0
  43. package/dist/exact-types-Dpw2LeHA.d.ts.map +1 -0
  44. package/dist/{extract-usage-p-56bh8q.js → extract-usage-CS391dOE.js} +2 -2
  45. package/dist/{extract-usage-p-56bh8q.js.map → extract-usage-CS391dOE.js.map} +1 -1
  46. package/dist/{feedback-trajectory-N_F0PwHz.d.ts → feedback-trajectory-CoNep7rl.d.ts} +3 -2
  47. package/dist/feedback-trajectory-CoNep7rl.d.ts.map +1 -0
  48. package/dist/fuzz.d.ts +1 -1
  49. package/dist/fuzz.js +1 -1
  50. package/dist/hosted/index.d.ts +3 -3
  51. package/dist/{index-U3RHOShi.d.ts → index-B2-IxCMB.d.ts} +2 -2
  52. package/dist/{index-U3RHOShi.d.ts.map → index-B2-IxCMB.d.ts.map} +1 -1
  53. package/dist/{index-BnP1QJUv.d.ts → index-CjVYlVBK.d.ts} +5 -5
  54. package/dist/{index-BnP1QJUv.d.ts.map → index-CjVYlVBK.d.ts.map} +1 -1
  55. package/dist/{index-C-Pr4OWg.d.ts → index-D0cxAdaV.d.ts} +11 -10
  56. package/dist/index-D0cxAdaV.d.ts.map +1 -0
  57. package/dist/index-DEb46kc6.d.ts.map +1 -1
  58. package/dist/{index-DRNl6g_N.d.ts → index-sMN_hI4E.d.ts} +3 -3
  59. package/dist/{index-DRNl6g_N.d.ts.map → index-sMN_hI4E.d.ts.map} +1 -1
  60. package/dist/index.d.ts +24 -23
  61. package/dist/index.d.ts.map +1 -1
  62. package/dist/index.js +19 -353
  63. package/dist/index.js.map +1 -1
  64. package/dist/{insight-report-B9ooYH_g.d.ts → insight-report-CXd8VBDR.d.ts} +4 -4
  65. package/dist/{insight-report-B9ooYH_g.d.ts.map → insight-report-CXd8VBDR.d.ts.map} +1 -1
  66. package/dist/{integrity-CKxosZ5Z.d.ts → integrity-B-MLFz0I.d.ts} +2 -2
  67. package/dist/{integrity-CKxosZ5Z.d.ts.map → integrity-B-MLFz0I.d.ts.map} +1 -1
  68. package/dist/ledger-core/index.js +1 -1
  69. package/dist/{ledger-core-t6sItivm.js → ledger-core-C0Yx1I14.js} +220 -27
  70. package/dist/ledger-core-C0Yx1I14.js.map +1 -0
  71. package/dist/{llm-client-DKB25jV8.js → llm-client-Cj3c7PEm.js} +5 -5
  72. package/dist/llm-client-Cj3c7PEm.js.map +1 -0
  73. package/dist/meta-eval/index.d.ts +2 -2
  74. package/dist/multishot/index.d.ts +2 -2
  75. package/dist/openapi.json +1 -1
  76. package/dist/{proposal-findings-DCawte-y.js → proposal-findings-2GIUo1et.js} +2 -68
  77. package/dist/proposal-findings-2GIUo1et.js.map +1 -0
  78. package/dist/{registry-BdM7SuTr.d.ts → registry-C4yJTza7.d.ts} +60 -6
  79. package/dist/registry-C4yJTza7.d.ts.map +1 -0
  80. package/dist/{release-report-CofgVNZt.d.ts → release-report-CoyvyLBs.d.ts} +3 -3
  81. package/dist/{release-report-CofgVNZt.d.ts.map → release-report-CoyvyLBs.d.ts.map} +1 -1
  82. package/dist/{replay-Bju0T8Ls.js → replay-Cb-4Vf0k.js} +8 -7
  83. package/dist/replay-Cb-4Vf0k.js.map +1 -0
  84. package/dist/{replay-K8FaC0CB.d.ts → replay-DbIYwso6.d.ts} +7 -7
  85. package/dist/{replay-K8FaC0CB.d.ts.map → replay-DbIYwso6.d.ts.map} +1 -1
  86. package/dist/reporting.d.ts +4 -4
  87. package/dist/{researcher-Da0Wj-bt.d.ts → researcher-BCeOEjtR.d.ts} +5 -5
  88. package/dist/{researcher-Da0Wj-bt.d.ts.map → researcher-BCeOEjtR.d.ts.map} +1 -1
  89. package/dist/{reward-hacking-CQ3hTCO3.d.ts → reward-hacking-sE2l_NV6.d.ts} +2 -2
  90. package/dist/{reward-hacking-CQ3hTCO3.d.ts.map → reward-hacking-sE2l_NV6.d.ts.map} +1 -1
  91. package/dist/rl.d.ts +5 -5
  92. package/dist/rl.js +1 -1
  93. package/dist/rollout/index.d.ts +1 -1
  94. package/dist/{rubric-predictive-validity-C4sztLR3.d.ts → rubric-predictive-validity-w2klGv1u.d.ts} +2 -2
  95. package/dist/{rubric-predictive-validity-C4sztLR3.d.ts.map → rubric-predictive-validity-w2klGv1u.d.ts.map} +1 -1
  96. package/dist/{run-evidence-BDIircdA.d.ts → run-evidence-CbE0A8Xg.d.ts} +3 -3
  97. package/dist/{run-evidence-BDIircdA.d.ts.map → run-evidence-CbE0A8Xg.d.ts.map} +1 -1
  98. package/dist/{run-record-BPCa2rQ8.d.ts → run-record-DwHMk1Ai.d.ts} +2 -2
  99. package/dist/{run-record-BPCa2rQ8.d.ts.map → run-record-DwHMk1Ai.d.ts.map} +1 -1
  100. package/dist/{semantic-concept-judge-Bz64IckK.js → semantic-concept-judge-DYXDPZW0.js} +11 -5
  101. package/dist/semantic-concept-judge-DYXDPZW0.js.map +1 -0
  102. package/dist/{server-KjXZZUDX.js → server-DLEvyW2z.js} +3 -3
  103. package/dist/{server-KjXZZUDX.js.map → server-DLEvyW2z.js.map} +1 -1
  104. package/dist/single-run-lock-D_bS5xhj.js +318 -0
  105. package/dist/single-run-lock-D_bS5xhj.js.map +1 -0
  106. package/dist/{skill-usage-CFDLLlhF.d.ts → skill-usage-Bv3G4VkA.d.ts} +18 -8
  107. package/dist/skill-usage-Bv3G4VkA.d.ts.map +1 -0
  108. package/dist/{skillopt-optimization-method-f4o9sUT4.js → skillopt-optimization-method-CjKMZy0d.js} +7 -182
  109. package/dist/skillopt-optimization-method-CjKMZy0d.js.map +1 -0
  110. package/dist/{skillopt-optimization-method-BpbnlvAZ.d.ts → skillopt-optimization-method-CzfnA8O-.d.ts} +10 -10
  111. package/dist/{skillopt-optimization-method-BpbnlvAZ.d.ts.map → skillopt-optimization-method-CzfnA8O-.d.ts.map} +1 -1
  112. package/dist/{statistics-_7P642CN.d.ts → statistics-mf70aXKp.d.ts} +2 -2
  113. package/dist/{statistics-_7P642CN.d.ts.map → statistics-mf70aXKp.d.ts.map} +1 -1
  114. package/dist/{tools-DZk2Jn64.js → store-otlp-BenKynPE.js} +4 -192
  115. package/dist/store-otlp-BenKynPE.js.map +1 -0
  116. package/dist/{summary-report-DHipz9Kx.d.ts → summary-report-BKinV4yD.d.ts} +3 -3
  117. package/dist/{summary-report-DHipz9Kx.d.ts.map → summary-report-BKinV4yD.d.ts.map} +1 -1
  118. package/dist/tools-DZGdROtG.js +255 -0
  119. package/dist/tools-DZGdROtG.js.map +1 -0
  120. package/dist/traces.d.ts +5 -5
  121. package/dist/traces.js +4 -3
  122. package/dist/{types-CTvKfr5F.d.ts → types-5q2T25iW.d.ts} +2 -2
  123. package/dist/{types-CTvKfr5F.d.ts.map → types-5q2T25iW.d.ts.map} +1 -1
  124. package/dist/{types-CKswbJGO.d.ts → types-BtJhn8v6.d.ts} +4 -4
  125. package/dist/{types-CKswbJGO.d.ts.map → types-BtJhn8v6.d.ts.map} +1 -1
  126. package/dist/{types-CTGbIm57.d.ts → types-zFYez3PK.d.ts} +5 -5
  127. package/dist/{types-CTGbIm57.d.ts.map → types-zFYez3PK.d.ts.map} +1 -1
  128. package/dist/wire/index.d.ts +3 -3
  129. package/dist/wire/index.js +1 -1
  130. package/docs/trace-analysis.md +123 -3
  131. package/package.json +5 -3
  132. package/dist/benchmark-CHX4orG7.d.ts.map +0 -1
  133. package/dist/benchmark-YDrpumqB.js.map +0 -1
  134. package/dist/campaign-lgObcHFC.js.map +0 -1
  135. package/dist/concurrency-MUjT7VjM.js +0 -109
  136. package/dist/concurrency-MUjT7VjM.js.map +0 -1
  137. package/dist/cost-ledger-D-5_-dhi.js.map +0 -1
  138. package/dist/default-registry-CLXbRt0f.js.map +0 -1
  139. package/dist/default-registry-Dc5D_Loc.d.ts.map +0 -1
  140. package/dist/feedback-trajectory-N_F0PwHz.d.ts.map +0 -1
  141. package/dist/index-C-Pr4OWg.d.ts.map +0 -1
  142. package/dist/ledger-core-t6sItivm.js.map +0 -1
  143. package/dist/llm-client-DKB25jV8.js.map +0 -1
  144. package/dist/proposal-findings-DCawte-y.js.map +0 -1
  145. package/dist/registry-BdM7SuTr.d.ts.map +0 -1
  146. package/dist/replay-Bju0T8Ls.js.map +0 -1
  147. package/dist/semantic-concept-judge-Bz64IckK.js.map +0 -1
  148. package/dist/skill-usage-CFDLLlhF.d.ts.map +0 -1
  149. package/dist/skillopt-optimization-method-f4o9sUT4.js.map +0 -1
  150. package/dist/tools-DZk2Jn64.js.map +0 -1

There are too many changes on this page to be displayed.


The amount of changes on this page would crash your brower.

You can still verify the content by downloading the package file manually.