@tangle-network/agent-eval 0.136.0 → 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 (231) hide show
  1. package/CHANGELOG.md +86 -1
  2. package/README.md +37 -2
  3. package/dist/{agent-profile-cell-OhuTee9n.js → agent-profile-cell-CbfBm2g6.js} +2 -2
  4. package/dist/{agent-profile-cell-OhuTee9n.js.map → agent-profile-cell-CbfBm2g6.js.map} +1 -1
  5. package/dist/{agent-profile-cell-CCm3l2v2.d.ts → agent-profile-cell-Cw0PVwDr.d.ts} +2 -2
  6. package/dist/{agent-profile-cell-CCm3l2v2.d.ts.map → agent-profile-cell-Cw0PVwDr.d.ts.map} +1 -1
  7. package/dist/analyst/index.d.ts +574 -18
  8. package/dist/analyst/index.d.ts.map +1 -1
  9. package/dist/analyst/index.js +25 -5
  10. package/dist/analyst/index.js.map +1 -1
  11. package/dist/{analyze-runs-jjCmF8pU.js → analyze-runs-BScZvqMV.js} +6 -6
  12. package/dist/{analyze-runs-jjCmF8pU.js.map → analyze-runs-BScZvqMV.js.map} +1 -1
  13. package/dist/{analyze-runs-Cda5Xkj1.d.ts → analyze-runs-CPYxfPWT.d.ts} +6 -6
  14. package/dist/{analyze-runs-Cda5Xkj1.d.ts.map → analyze-runs-CPYxfPWT.d.ts.map} +1 -1
  15. package/dist/{baseline-BUeFcgrn.js → baseline-C-GocmIW.js} +2 -2
  16. package/dist/{baseline-BUeFcgrn.js.map → baseline-C-GocmIW.js.map} +1 -1
  17. package/dist/benchmark-D8dkki-J.js +554 -0
  18. package/dist/benchmark-D8dkki-J.js.map +1 -0
  19. package/dist/benchmark-DlQgU_XI.d.ts +236 -0
  20. package/dist/benchmark-DlQgU_XI.d.ts.map +1 -0
  21. package/dist/benchmark-command-CMqVqReF.js +4332 -0
  22. package/dist/benchmark-command-CMqVqReF.js.map +1 -0
  23. package/dist/benchmarks/index.d.ts +1 -1
  24. package/dist/benchmarks/index.js +1 -1
  25. package/dist/{benchmarks-Dfgm9ts5.js → benchmarks-BJ_xK5rQ.js} +4 -3
  26. package/dist/{benchmarks-Dfgm9ts5.js.map → benchmarks-BJ_xK5rQ.js.map} +1 -1
  27. package/dist/builder-eval/index.js +2 -2
  28. package/dist/campaign/index.d.ts +6 -6
  29. package/dist/campaign/index.js +4 -4
  30. package/dist/{campaign-Dz8uQnhC.js → campaign-BIBS-NHV.js} +219 -78
  31. package/dist/campaign-BIBS-NHV.js.map +1 -0
  32. package/dist/cli.js +9 -2
  33. package/dist/cli.js.map +1 -1
  34. package/dist/client-BwPKohkJ.d.ts +202 -0
  35. package/dist/client-BwPKohkJ.d.ts.map +1 -0
  36. package/dist/completion-verifier-B4-IMYcS.d.ts +240 -0
  37. package/dist/completion-verifier-B4-IMYcS.d.ts.map +1 -0
  38. package/dist/contract/index.d.ts +10 -9
  39. package/dist/contract/index.d.ts.map +1 -1
  40. package/dist/contract/index.js +13 -13
  41. package/dist/control.d.ts +2 -2
  42. package/dist/control.js +1 -1
  43. package/dist/{cost-ledger-fGS_u_O1.d.ts → cost-ledger-B1D3COAc.d.ts} +6 -5
  44. package/dist/{cost-ledger-fGS_u_O1.d.ts.map → cost-ledger-B1D3COAc.d.ts.map} +1 -1
  45. package/dist/{cost-ledger-DHAjwNj7.js → cost-ledger-CHDLA0Ss.js} +91 -46
  46. package/dist/cost-ledger-CHDLA0Ss.js.map +1 -0
  47. package/dist/{dataset-BvtnC8Dc.d.ts → dataset-v_Y5902-.d.ts} +2 -2
  48. package/dist/{dataset-BvtnC8Dc.d.ts.map → dataset-v_Y5902-.d.ts.map} +1 -1
  49. package/dist/{default-registry-Brxr728w.d.ts → default-registry-PUhIVRWz.d.ts} +77 -138
  50. package/dist/default-registry-PUhIVRWz.d.ts.map +1 -0
  51. package/dist/{default-registry-CHmdy2An.js → default-registry-lp5R0lve.js} +1617 -291
  52. package/dist/default-registry-lp5R0lve.js.map +1 -0
  53. package/dist/{errors-8YnH8WlF.js → errors-D-LKuDhb.js} +8 -2
  54. package/dist/errors-D-LKuDhb.js.map +1 -0
  55. package/dist/{errors-CEk209JS.d.ts → errors-DkfjIDvD.d.ts} +9 -3
  56. package/dist/errors-DkfjIDvD.d.ts.map +1 -0
  57. package/dist/{eval-campaign-Cc8WZJ6b.js → eval-campaign-9MozgKL7.js} +6 -6
  58. package/dist/{eval-campaign-Cc8WZJ6b.js.map → eval-campaign-9MozgKL7.js.map} +1 -1
  59. package/dist/exact-types-Dpw2LeHA.d.ts +234 -0
  60. package/dist/exact-types-Dpw2LeHA.d.ts.map +1 -0
  61. package/dist/{extract-usage-DIQpN-ww.js → extract-usage-CS391dOE.js} +3 -3
  62. package/dist/{extract-usage-DIQpN-ww.js.map → extract-usage-CS391dOE.js.map} +1 -1
  63. package/dist/{feedback-trajectory-CVaeREXV.d.ts → feedback-trajectory-CoNep7rl.d.ts} +91 -3
  64. package/dist/feedback-trajectory-CoNep7rl.d.ts.map +1 -0
  65. package/dist/fuzz.d.ts +1 -1
  66. package/dist/fuzz.js +2 -2
  67. package/dist/hosted/index.d.ts +3 -2
  68. package/dist/hosted/index.d.ts.map +1 -1
  69. package/dist/{index-AbhwHp0V.d.ts → index-B2-IxCMB.d.ts} +2 -2
  70. package/dist/{index-AbhwHp0V.d.ts.map → index-B2-IxCMB.d.ts.map} +1 -1
  71. package/dist/index-BipJlj-C.d.ts +316 -0
  72. package/dist/index-BipJlj-C.d.ts.map +1 -0
  73. package/dist/{index-CQsJcqch.d.ts → index-CjVYlVBK.d.ts} +5 -5
  74. package/dist/{index-CQsJcqch.d.ts.map → index-CjVYlVBK.d.ts.map} +1 -1
  75. package/dist/{index-B4Fjfo5U.d.ts → index-D0cxAdaV.d.ts} +89 -317
  76. package/dist/index-D0cxAdaV.d.ts.map +1 -0
  77. package/dist/{index-DuhJaaiH.d.ts → index-DEb46kc6.d.ts} +2 -2
  78. package/dist/index-DEb46kc6.d.ts.map +1 -0
  79. package/dist/{index-C2fkZhv_.d.ts → index-sMN_hI4E.d.ts} +3 -3
  80. package/dist/{index-C2fkZhv_.d.ts.map → index-sMN_hI4E.d.ts.map} +1 -1
  81. package/dist/index.d.ts +30 -70
  82. package/dist/index.d.ts.map +1 -1
  83. package/dist/index.js +175 -35
  84. package/dist/index.js.map +1 -1
  85. package/dist/{client-DcvgkaZi.d.ts → insight-report-CXd8VBDR.d.ts} +5 -203
  86. package/dist/insight-report-CXd8VBDR.d.ts.map +1 -0
  87. package/dist/{integrity-rmVhXWA7.d.ts → integrity-B-MLFz0I.d.ts} +3 -3
  88. package/dist/{integrity-rmVhXWA7.d.ts.map → integrity-B-MLFz0I.d.ts.map} +1 -1
  89. package/dist/integrity-CCXTftiL.js +1360 -0
  90. package/dist/integrity-CCXTftiL.js.map +1 -0
  91. package/dist/{integrity-BzRbCHzi.js → integrity-fdt8XPAv.js} +2 -2
  92. package/dist/{integrity-BzRbCHzi.js.map → integrity-fdt8XPAv.js.map} +1 -1
  93. package/dist/ledger-core/index.d.ts +1 -1
  94. package/dist/ledger-core/index.js +1 -1
  95. package/dist/{ledger-core-DAKFKRzi.js → ledger-core-C0Yx1I14.js} +303 -110
  96. package/dist/ledger-core-C0Yx1I14.js.map +1 -0
  97. package/dist/{llm-client-DHx8pzyJ.js → llm-client-Cj3c7PEm.js} +6 -6
  98. package/dist/llm-client-Cj3c7PEm.js.map +1 -0
  99. package/dist/meta-eval/index.d.ts +2 -2
  100. package/dist/meta-eval/index.js +3 -3
  101. package/dist/{mint-DyRUc9k6.js → mint-Ctwk079K.js} +4 -4
  102. package/dist/{mint-DyRUc9k6.js.map → mint-Ctwk079K.js.map} +1 -1
  103. package/dist/multishot/index.d.ts +2 -2
  104. package/dist/openapi.json +1 -1
  105. package/dist/{paired-arms-BbFKrAU-.js → paired-arms-iZ08VFMN.js} +3 -3
  106. package/dist/{paired-arms-BbFKrAU-.js.map → paired-arms-iZ08VFMN.js.map} +1 -1
  107. package/dist/pipelines/index.js +2 -2
  108. package/dist/profile-cell.d.ts +1 -1
  109. package/dist/profile-cell.js +1 -1
  110. package/dist/{proposal-findings-DCawte-y.js → proposal-findings-2GIUo1et.js} +2 -68
  111. package/dist/proposal-findings-2GIUo1et.js.map +1 -0
  112. package/dist/{propose-review-control-SQ-n9-We.js → propose-review-control-DLXz4FCX.js} +2 -2
  113. package/dist/{propose-review-control-SQ-n9-We.js.map → propose-review-control-DLXz4FCX.js.map} +1 -1
  114. package/dist/registry-C4yJTza7.d.ts +178 -0
  115. package/dist/registry-C4yJTza7.d.ts.map +1 -0
  116. package/dist/{release-report-DooPguBc.js → release-report-B5XPBvAU.js} +4 -4
  117. package/dist/{release-report-DooPguBc.js.map → release-report-B5XPBvAU.js.map} +1 -1
  118. package/dist/{release-report-DpBxGGI1.d.ts → release-report-CoyvyLBs.d.ts} +4 -4
  119. package/dist/{release-report-DpBxGGI1.d.ts.map → release-report-CoyvyLBs.d.ts.map} +1 -1
  120. package/dist/{replay-C6wRg47C.js → replay-Cb-4Vf0k.js} +249 -8
  121. package/dist/replay-Cb-4Vf0k.js.map +1 -0
  122. package/dist/{replay-BRfMIs81.d.ts → replay-DbIYwso6.d.ts} +227 -52
  123. package/dist/replay-DbIYwso6.d.ts.map +1 -0
  124. package/dist/reporting.d.ts +4 -4
  125. package/dist/reporting.js +4 -4
  126. package/dist/{researcher-Doo95b50.d.ts → researcher-BCeOEjtR.d.ts} +6 -7
  127. package/dist/researcher-BCeOEjtR.d.ts.map +1 -0
  128. package/dist/{reward-hacking-a-kYs0-i.js → reward-hacking-GyN0kMd8.js} +3 -3
  129. package/dist/{reward-hacking-a-kYs0-i.js.map → reward-hacking-GyN0kMd8.js.map} +1 -1
  130. package/dist/{reward-hacking-D-QqXvg-.d.ts → reward-hacking-sE2l_NV6.d.ts} +2 -2
  131. package/dist/{reward-hacking-D-QqXvg-.d.ts.map → reward-hacking-sE2l_NV6.d.ts.map} +1 -1
  132. package/dist/rl.d.ts +6 -6
  133. package/dist/rl.js +9 -9
  134. package/dist/rollout/index.d.ts +1 -1
  135. package/dist/rollout/index.js +3 -3
  136. package/dist/{rollout-DLSUIWLu.js → rollout-DQFl0UXA.js} +2 -2
  137. package/dist/{rollout-DLSUIWLu.js.map → rollout-DQFl0UXA.js.map} +1 -1
  138. package/dist/{rubric-predictive-validity-BJf-8ejY.js → rubric-predictive-validity-BRR632r1.js} +2 -2
  139. package/dist/{rubric-predictive-validity-BJf-8ejY.js.map → rubric-predictive-validity-BRR632r1.js.map} +1 -1
  140. package/dist/{rubric-predictive-validity-C1dCLcvb.d.ts → rubric-predictive-validity-w2klGv1u.d.ts} +2 -2
  141. package/dist/{rubric-predictive-validity-C1dCLcvb.d.ts.map → rubric-predictive-validity-w2klGv1u.d.ts.map} +1 -1
  142. package/dist/{run-evidence-DokQtX0-.d.ts → run-evidence-CbE0A8Xg.d.ts} +3 -3
  143. package/dist/{run-evidence-DokQtX0-.d.ts.map → run-evidence-CbE0A8Xg.d.ts.map} +1 -1
  144. package/dist/{run-record-DcObtIGh.d.ts → run-record-DwHMk1Ai.d.ts} +4 -4
  145. package/dist/{run-record-DcObtIGh.d.ts.map → run-record-DwHMk1Ai.d.ts.map} +1 -1
  146. package/dist/{run-record-BIwU2wdV.js → run-record-vRgqWmJw.js} +3 -3
  147. package/dist/{run-record-BIwU2wdV.js.map → run-record-vRgqWmJw.js.map} +1 -1
  148. package/dist/{semantic-concept-judge-Btozx3Vc.js → semantic-concept-judge-DYXDPZW0.js} +12 -6
  149. package/dist/semantic-concept-judge-DYXDPZW0.js.map +1 -0
  150. package/dist/{server-Bz3WQJs6.js → server-DLEvyW2z.js} +3 -3
  151. package/dist/{server-Bz3WQJs6.js.map → server-DLEvyW2z.js.map} +1 -1
  152. package/dist/single-run-lock-D_bS5xhj.js +318 -0
  153. package/dist/single-run-lock-D_bS5xhj.js.map +1 -0
  154. package/dist/{skill-usage-BDQVPIG1.d.ts → skill-usage-Bv3G4VkA.d.ts} +36 -48
  155. package/dist/skill-usage-Bv3G4VkA.d.ts.map +1 -0
  156. package/dist/{skillopt-optimization-method-0UmPD6aP.js → skillopt-optimization-method-CjKMZy0d.js} +10 -185
  157. package/dist/skillopt-optimization-method-CjKMZy0d.js.map +1 -0
  158. package/dist/{skillopt-optimization-method-CwSYkv35.d.ts → skillopt-optimization-method-CzfnA8O-.d.ts} +11 -12
  159. package/dist/skillopt-optimization-method-CzfnA8O-.d.ts.map +1 -0
  160. package/dist/{statistics-CnGCLLqc.js → statistics-ByxzSiOM.js} +2 -2
  161. package/dist/{statistics-CnGCLLqc.js.map → statistics-ByxzSiOM.js.map} +1 -1
  162. package/dist/{statistics-CKOqre5S.d.ts → statistics-mf70aXKp.d.ts} +2 -2
  163. package/dist/{statistics-CKOqre5S.d.ts.map → statistics-mf70aXKp.d.ts.map} +1 -1
  164. package/dist/store-otlp-BenKynPE.js +1688 -0
  165. package/dist/store-otlp-BenKynPE.js.map +1 -0
  166. package/dist/{summary-report-BEk8OFLs.js → summary-report-9A5y7EsK.js} +4 -4
  167. package/dist/{summary-report-BEk8OFLs.js.map → summary-report-9A5y7EsK.js.map} +1 -1
  168. package/dist/{summary-report-CPMINBqs.d.ts → summary-report-BKinV4yD.d.ts} +3 -3
  169. package/dist/{summary-report-CPMINBqs.d.ts.map → summary-report-BKinV4yD.d.ts.map} +1 -1
  170. package/dist/supervisor-run/index.d.ts +3 -2
  171. package/dist/supervisor-run/index.js +3 -2
  172. package/dist/{supervisor-run-Dr5HnTup.js → supervisor-run-B2EWUmQY.js} +28 -454
  173. package/dist/supervisor-run-B2EWUmQY.js.map +1 -0
  174. package/dist/{test-graded-scenario-BsqWLmPt.js → test-graded-scenario-JHcKQNpq.js} +2 -2
  175. package/dist/{test-graded-scenario-BsqWLmPt.js.map → test-graded-scenario-JHcKQNpq.js.map} +1 -1
  176. package/dist/tools-DZGdROtG.js +255 -0
  177. package/dist/tools-DZGdROtG.js.map +1 -0
  178. package/dist/traces.d.ts +6 -7
  179. package/dist/traces.js +6 -6
  180. package/dist/types-5q2T25iW.d.ts +804 -0
  181. package/dist/types-5q2T25iW.d.ts.map +1 -0
  182. package/dist/{types-DVjczBM9.d.ts → types-BtJhn8v6.d.ts} +260 -6
  183. package/dist/types-BtJhn8v6.d.ts.map +1 -0
  184. package/dist/{index-CyC1BTmn.d.ts → types-Dea6tiVI.d.ts} +16 -238
  185. package/dist/types-Dea6tiVI.d.ts.map +1 -0
  186. package/dist/{types-DiWLru6Z.d.ts → types-zFYez3PK.d.ts} +5 -5
  187. package/dist/{types-DiWLru6Z.d.ts.map → types-zFYez3PK.d.ts.map} +1 -1
  188. package/dist/wire/index.d.ts +3 -3
  189. package/dist/wire/index.js +1 -1
  190. package/docs/feedback-trajectories.md +100 -1
  191. package/docs/trace-analysis.md +494 -58
  192. package/package.json +9 -3
  193. package/dist/analyst-BkTS3C58.d.ts +0 -89
  194. package/dist/analyst-BkTS3C58.d.ts.map +0 -1
  195. package/dist/analyst-j5je5J7c.js +0 -152
  196. package/dist/analyst-j5je5J7c.js.map +0 -1
  197. package/dist/campaign-Dz8uQnhC.js.map +0 -1
  198. package/dist/client-DcvgkaZi.d.ts.map +0 -1
  199. package/dist/concurrency-MUjT7VjM.js +0 -109
  200. package/dist/concurrency-MUjT7VjM.js.map +0 -1
  201. package/dist/cost-ledger-DHAjwNj7.js.map +0 -1
  202. package/dist/default-registry-Brxr728w.d.ts.map +0 -1
  203. package/dist/default-registry-CHmdy2An.js.map +0 -1
  204. package/dist/errors-8YnH8WlF.js.map +0 -1
  205. package/dist/errors-CEk209JS.d.ts.map +0 -1
  206. package/dist/feedback-trajectory-CVaeREXV.d.ts.map +0 -1
  207. package/dist/index-B4Fjfo5U.d.ts.map +0 -1
  208. package/dist/index-CyC1BTmn.d.ts.map +0 -1
  209. package/dist/index-DuhJaaiH.d.ts.map +0 -1
  210. package/dist/ledger-core-DAKFKRzi.js.map +0 -1
  211. package/dist/llm-client-BiK4HW0u.d.ts +0 -290
  212. package/dist/llm-client-BiK4HW0u.d.ts.map +0 -1
  213. package/dist/llm-client-DHx8pzyJ.js.map +0 -1
  214. package/dist/proposal-findings-DCawte-y.js.map +0 -1
  215. package/dist/raw-provider-sink-BU29Sh8h.d.ts +0 -134
  216. package/dist/raw-provider-sink-BU29Sh8h.d.ts.map +0 -1
  217. package/dist/replay-BRfMIs81.d.ts.map +0 -1
  218. package/dist/replay-C6wRg47C.js.map +0 -1
  219. package/dist/researcher-Doo95b50.d.ts.map +0 -1
  220. package/dist/semantic-concept-judge-Btozx3Vc.js.map +0 -1
  221. package/dist/skill-usage-BDQVPIG1.d.ts.map +0 -1
  222. package/dist/skillopt-optimization-method-0UmPD6aP.js.map +0 -1
  223. package/dist/skillopt-optimization-method-CwSYkv35.d.ts.map +0 -1
  224. package/dist/store-CxJry_cs.d.ts +0 -229
  225. package/dist/store-CxJry_cs.d.ts.map +0 -1
  226. package/dist/supervisor-run-Dr5HnTup.js.map +0 -1
  227. package/dist/tools-D8yTtNSN.js +0 -1190
  228. package/dist/tools-D8yTtNSN.js.map +0 -1
  229. package/dist/types-Cc3qbqzj.d.ts +0 -387
  230. package/dist/types-Cc3qbqzj.d.ts.map +0 -1
  231. package/dist/types-DVjczBM9.d.ts.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.