@tangle-network/agent-eval 0.135.4 → 0.137.0

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 (211) hide show
  1. package/CHANGELOG.md +56 -0
  2. package/README.md +4 -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 +139 -17
  8. package/dist/analyst/index.d.ts.map +1 -1
  9. package/dist/analyst/index.js +606 -4
  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-PVtnfjvA.d.ts} +6 -6
  14. package/dist/{analyze-runs-Cda5Xkj1.d.ts.map → analyze-runs-PVtnfjvA.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-CHX4orG7.d.ts +184 -0
  18. package/dist/benchmark-CHX4orG7.d.ts.map +1 -0
  19. package/dist/benchmark-YDrpumqB.js +414 -0
  20. package/dist/benchmark-YDrpumqB.js.map +1 -0
  21. package/dist/benchmarks/index.d.ts +1 -1
  22. package/dist/benchmarks/index.js +1 -1
  23. package/dist/{benchmarks-Dfgm9ts5.js → benchmarks-DCLkQOmc.js} +3 -3
  24. package/dist/{benchmarks-Dfgm9ts5.js.map → benchmarks-DCLkQOmc.js.map} +1 -1
  25. package/dist/builder-eval/index.js +2 -2
  26. package/dist/campaign/index.d.ts +6 -6
  27. package/dist/campaign/index.js +3 -3
  28. package/dist/{campaign-Dz8uQnhC.js → campaign-lgObcHFC.js} +212 -78
  29. package/dist/campaign-lgObcHFC.js.map +1 -0
  30. package/dist/cli.js +1 -1
  31. package/dist/client-C8L6h6Wf.d.ts +202 -0
  32. package/dist/client-C8L6h6Wf.d.ts.map +1 -0
  33. package/dist/completion-verifier-DSyRNVzU.d.ts +240 -0
  34. package/dist/completion-verifier-DSyRNVzU.d.ts.map +1 -0
  35. package/dist/contract/index.d.ts +10 -9
  36. package/dist/contract/index.d.ts.map +1 -1
  37. package/dist/contract/index.js +10 -10
  38. package/dist/control.d.ts +2 -2
  39. package/dist/control.js +1 -1
  40. package/dist/{cost-ledger-DHAjwNj7.js → cost-ledger-D-5_-dhi.js} +2 -2
  41. package/dist/{cost-ledger-DHAjwNj7.js.map → cost-ledger-D-5_-dhi.js.map} +1 -1
  42. package/dist/{cost-ledger-fGS_u_O1.d.ts → cost-ledger-D2o6JOrL.d.ts} +2 -2
  43. package/dist/{cost-ledger-fGS_u_O1.d.ts.map → cost-ledger-D2o6JOrL.d.ts.map} +1 -1
  44. package/dist/{dataset-BvtnC8Dc.d.ts → dataset-v_Y5902-.d.ts} +2 -2
  45. package/dist/{dataset-BvtnC8Dc.d.ts.map → dataset-v_Y5902-.d.ts.map} +1 -1
  46. package/dist/{default-registry-CHmdy2An.js → default-registry-CLXbRt0f.js} +119 -38
  47. package/dist/default-registry-CLXbRt0f.js.map +1 -0
  48. package/dist/{default-registry-Brxr728w.d.ts → default-registry-Dc5D_Loc.d.ts} +63 -137
  49. package/dist/default-registry-Dc5D_Loc.d.ts.map +1 -0
  50. package/dist/{errors-8YnH8WlF.js → errors-D-LKuDhb.js} +8 -2
  51. package/dist/errors-D-LKuDhb.js.map +1 -0
  52. package/dist/{errors-CEk209JS.d.ts → errors-DkfjIDvD.d.ts} +9 -3
  53. package/dist/errors-DkfjIDvD.d.ts.map +1 -0
  54. package/dist/{eval-campaign-Cc8WZJ6b.js → eval-campaign-CHqfLnff.js} +6 -6
  55. package/dist/{eval-campaign-Cc8WZJ6b.js.map → eval-campaign-CHqfLnff.js.map} +1 -1
  56. package/dist/{extract-usage-DIQpN-ww.js → extract-usage-p-56bh8q.js} +3 -3
  57. package/dist/{extract-usage-DIQpN-ww.js.map → extract-usage-p-56bh8q.js.map} +1 -1
  58. package/dist/{feedback-trajectory-CVaeREXV.d.ts → feedback-trajectory-N_F0PwHz.d.ts} +90 -3
  59. package/dist/feedback-trajectory-N_F0PwHz.d.ts.map +1 -0
  60. package/dist/fuzz.d.ts +1 -1
  61. package/dist/fuzz.js +2 -2
  62. package/dist/hosted/index.d.ts +3 -2
  63. package/dist/hosted/index.d.ts.map +1 -1
  64. package/dist/index-BipJlj-C.d.ts +316 -0
  65. package/dist/index-BipJlj-C.d.ts.map +1 -0
  66. package/dist/{index-CQsJcqch.d.ts → index-BnP1QJUv.d.ts} +5 -5
  67. package/dist/{index-CQsJcqch.d.ts.map → index-BnP1QJUv.d.ts.map} +1 -1
  68. package/dist/{index-B4Fjfo5U.d.ts → index-C-Pr4OWg.d.ts} +88 -317
  69. package/dist/index-C-Pr4OWg.d.ts.map +1 -0
  70. package/dist/{index-DuhJaaiH.d.ts → index-DEb46kc6.d.ts} +2 -2
  71. package/dist/{index-DuhJaaiH.d.ts.map → index-DEb46kc6.d.ts.map} +1 -1
  72. package/dist/{index-C2fkZhv_.d.ts → index-DRNl6g_N.d.ts} +3 -3
  73. package/dist/{index-C2fkZhv_.d.ts.map → index-DRNl6g_N.d.ts.map} +1 -1
  74. package/dist/{index-AbhwHp0V.d.ts → index-U3RHOShi.d.ts} +2 -2
  75. package/dist/{index-AbhwHp0V.d.ts.map → index-U3RHOShi.d.ts.map} +1 -1
  76. package/dist/index.d.ts +29 -70
  77. package/dist/index.d.ts.map +1 -1
  78. package/dist/index.js +507 -33
  79. package/dist/index.js.map +1 -1
  80. package/dist/{client-DcvgkaZi.d.ts → insight-report-B9ooYH_g.d.ts} +5 -203
  81. package/dist/insight-report-B9ooYH_g.d.ts.map +1 -0
  82. package/dist/integrity-CCXTftiL.js +1360 -0
  83. package/dist/integrity-CCXTftiL.js.map +1 -0
  84. package/dist/{integrity-rmVhXWA7.d.ts → integrity-CKxosZ5Z.d.ts} +3 -3
  85. package/dist/{integrity-rmVhXWA7.d.ts.map → integrity-CKxosZ5Z.d.ts.map} +1 -1
  86. package/dist/{integrity-BzRbCHzi.js → integrity-fdt8XPAv.js} +2 -2
  87. package/dist/{integrity-BzRbCHzi.js.map → integrity-fdt8XPAv.js.map} +1 -1
  88. package/dist/ledger-core/index.d.ts +1 -1
  89. package/dist/ledger-core/index.js +1 -1
  90. package/dist/{ledger-core-DAKFKRzi.js → ledger-core-t6sItivm.js} +85 -85
  91. package/dist/{ledger-core-DAKFKRzi.js.map → ledger-core-t6sItivm.js.map} +1 -1
  92. package/dist/{llm-client-DHx8pzyJ.js → llm-client-DKB25jV8.js} +3 -3
  93. package/dist/{llm-client-DHx8pzyJ.js.map → llm-client-DKB25jV8.js.map} +1 -1
  94. package/dist/meta-eval/index.d.ts +2 -2
  95. package/dist/meta-eval/index.js +3 -3
  96. package/dist/{mint-DyRUc9k6.js → mint-Ctwk079K.js} +4 -4
  97. package/dist/{mint-DyRUc9k6.js.map → mint-Ctwk079K.js.map} +1 -1
  98. package/dist/multishot/index.d.ts +2 -2
  99. package/dist/openapi.json +1 -1
  100. package/dist/{paired-arms-BbFKrAU-.js → paired-arms-iZ08VFMN.js} +3 -3
  101. package/dist/{paired-arms-BbFKrAU-.js.map → paired-arms-iZ08VFMN.js.map} +1 -1
  102. package/dist/pipelines/index.js +2 -2
  103. package/dist/profile-cell.d.ts +1 -1
  104. package/dist/profile-cell.js +1 -1
  105. package/dist/{propose-review-control-SQ-n9-We.js → propose-review-control-DLXz4FCX.js} +2 -2
  106. package/dist/{propose-review-control-SQ-n9-We.js.map → propose-review-control-DLXz4FCX.js.map} +1 -1
  107. package/dist/registry-BdM7SuTr.d.ts +124 -0
  108. package/dist/registry-BdM7SuTr.d.ts.map +1 -0
  109. package/dist/{release-report-DooPguBc.js → release-report-B5XPBvAU.js} +4 -4
  110. package/dist/{release-report-DooPguBc.js.map → release-report-B5XPBvAU.js.map} +1 -1
  111. package/dist/{release-report-DpBxGGI1.d.ts → release-report-CofgVNZt.d.ts} +4 -4
  112. package/dist/{release-report-DpBxGGI1.d.ts.map → release-report-CofgVNZt.d.ts.map} +1 -1
  113. package/dist/{replay-C6wRg47C.js → replay-Bju0T8Ls.js} +248 -8
  114. package/dist/replay-Bju0T8Ls.js.map +1 -0
  115. package/dist/{replay-BRfMIs81.d.ts → replay-K8FaC0CB.d.ts} +227 -52
  116. package/dist/replay-K8FaC0CB.d.ts.map +1 -0
  117. package/dist/reporting.d.ts +4 -4
  118. package/dist/reporting.js +4 -4
  119. package/dist/{researcher-Doo95b50.d.ts → researcher-Da0Wj-bt.d.ts} +6 -7
  120. package/dist/researcher-Da0Wj-bt.d.ts.map +1 -0
  121. package/dist/{reward-hacking-D-QqXvg-.d.ts → reward-hacking-CQ3hTCO3.d.ts} +2 -2
  122. package/dist/{reward-hacking-D-QqXvg-.d.ts.map → reward-hacking-CQ3hTCO3.d.ts.map} +1 -1
  123. package/dist/{reward-hacking-a-kYs0-i.js → reward-hacking-GyN0kMd8.js} +3 -3
  124. package/dist/{reward-hacking-a-kYs0-i.js.map → reward-hacking-GyN0kMd8.js.map} +1 -1
  125. package/dist/rl.d.ts +6 -6
  126. package/dist/rl.js +9 -9
  127. package/dist/rollout/index.d.ts +1 -1
  128. package/dist/rollout/index.js +3 -3
  129. package/dist/{rollout-DLSUIWLu.js → rollout-DQFl0UXA.js} +2 -2
  130. package/dist/{rollout-DLSUIWLu.js.map → rollout-DQFl0UXA.js.map} +1 -1
  131. package/dist/{rubric-predictive-validity-BJf-8ejY.js → rubric-predictive-validity-BRR632r1.js} +2 -2
  132. package/dist/{rubric-predictive-validity-BJf-8ejY.js.map → rubric-predictive-validity-BRR632r1.js.map} +1 -1
  133. package/dist/{rubric-predictive-validity-C1dCLcvb.d.ts → rubric-predictive-validity-C4sztLR3.d.ts} +2 -2
  134. package/dist/{rubric-predictive-validity-C1dCLcvb.d.ts.map → rubric-predictive-validity-C4sztLR3.d.ts.map} +1 -1
  135. package/dist/{run-evidence-DokQtX0-.d.ts → run-evidence-BDIircdA.d.ts} +3 -3
  136. package/dist/{run-evidence-DokQtX0-.d.ts.map → run-evidence-BDIircdA.d.ts.map} +1 -1
  137. package/dist/{run-record-DcObtIGh.d.ts → run-record-BPCa2rQ8.d.ts} +4 -4
  138. package/dist/{run-record-DcObtIGh.d.ts.map → run-record-BPCa2rQ8.d.ts.map} +1 -1
  139. package/dist/{run-record-BIwU2wdV.js → run-record-vRgqWmJw.js} +3 -3
  140. package/dist/{run-record-BIwU2wdV.js.map → run-record-vRgqWmJw.js.map} +1 -1
  141. package/dist/{semantic-concept-judge-Btozx3Vc.js → semantic-concept-judge-Bz64IckK.js} +4 -4
  142. package/dist/{semantic-concept-judge-Btozx3Vc.js.map → semantic-concept-judge-Bz64IckK.js.map} +1 -1
  143. package/dist/{server-Bz3WQJs6.js → server-KjXZZUDX.js} +3 -3
  144. package/dist/{server-Bz3WQJs6.js.map → server-KjXZZUDX.js.map} +1 -1
  145. package/dist/{skill-usage-BDQVPIG1.d.ts → skill-usage-CFDLLlhF.d.ts} +25 -47
  146. package/dist/skill-usage-CFDLLlhF.d.ts.map +1 -0
  147. package/dist/{skillopt-optimization-method-CwSYkv35.d.ts → skillopt-optimization-method-BpbnlvAZ.d.ts} +11 -12
  148. package/dist/skillopt-optimization-method-BpbnlvAZ.d.ts.map +1 -0
  149. package/dist/{skillopt-optimization-method-0UmPD6aP.js → skillopt-optimization-method-f4o9sUT4.js} +7 -7
  150. package/dist/{skillopt-optimization-method-0UmPD6aP.js.map → skillopt-optimization-method-f4o9sUT4.js.map} +1 -1
  151. package/dist/{statistics-CnGCLLqc.js → statistics-ByxzSiOM.js} +2 -2
  152. package/dist/{statistics-CnGCLLqc.js.map → statistics-ByxzSiOM.js.map} +1 -1
  153. package/dist/{statistics-CKOqre5S.d.ts → statistics-_7P642CN.d.ts} +2 -2
  154. package/dist/{statistics-CKOqre5S.d.ts.map → statistics-_7P642CN.d.ts.map} +1 -1
  155. package/dist/{summary-report-BEk8OFLs.js → summary-report-9A5y7EsK.js} +4 -4
  156. package/dist/{summary-report-BEk8OFLs.js.map → summary-report-9A5y7EsK.js.map} +1 -1
  157. package/dist/{summary-report-CPMINBqs.d.ts → summary-report-DHipz9Kx.d.ts} +3 -3
  158. package/dist/{summary-report-CPMINBqs.d.ts.map → summary-report-DHipz9Kx.d.ts.map} +1 -1
  159. package/dist/supervisor-run/index.d.ts +3 -2
  160. package/dist/supervisor-run/index.js +3 -2
  161. package/dist/{supervisor-run-B7lUGoyZ.js → supervisor-run-B2EWUmQY.js} +221 -519
  162. package/dist/supervisor-run-B2EWUmQY.js.map +1 -0
  163. package/dist/{test-graded-scenario-BsqWLmPt.js → test-graded-scenario-JHcKQNpq.js} +2 -2
  164. package/dist/{test-graded-scenario-BsqWLmPt.js.map → test-graded-scenario-JHcKQNpq.js.map} +1 -1
  165. package/dist/tools-DZk2Jn64.js +1876 -0
  166. package/dist/tools-DZk2Jn64.js.map +1 -0
  167. package/dist/traces.d.ts +6 -7
  168. package/dist/traces.js +5 -6
  169. package/dist/{types-DVjczBM9.d.ts → types-CKswbJGO.d.ts} +260 -6
  170. package/dist/types-CKswbJGO.d.ts.map +1 -0
  171. package/dist/{types-DiWLru6Z.d.ts → types-CTGbIm57.d.ts} +5 -5
  172. package/dist/{types-DiWLru6Z.d.ts.map → types-CTGbIm57.d.ts.map} +1 -1
  173. package/dist/types-CTvKfr5F.d.ts +804 -0
  174. package/dist/types-CTvKfr5F.d.ts.map +1 -0
  175. package/dist/{index-C61Wi7yg.d.ts → types-Dea6tiVI.d.ts} +47 -235
  176. package/dist/types-Dea6tiVI.d.ts.map +1 -0
  177. package/dist/wire/index.d.ts +3 -3
  178. package/dist/wire/index.js +1 -1
  179. package/docs/feedback-trajectories.md +100 -1
  180. package/docs/trace-analysis.md +374 -58
  181. package/package.json +7 -3
  182. package/dist/analyst-BkTS3C58.d.ts +0 -89
  183. package/dist/analyst-BkTS3C58.d.ts.map +0 -1
  184. package/dist/analyst-j5je5J7c.js +0 -152
  185. package/dist/analyst-j5je5J7c.js.map +0 -1
  186. package/dist/campaign-Dz8uQnhC.js.map +0 -1
  187. package/dist/client-DcvgkaZi.d.ts.map +0 -1
  188. package/dist/default-registry-Brxr728w.d.ts.map +0 -1
  189. package/dist/default-registry-CHmdy2An.js.map +0 -1
  190. package/dist/errors-8YnH8WlF.js.map +0 -1
  191. package/dist/errors-CEk209JS.d.ts.map +0 -1
  192. package/dist/feedback-trajectory-CVaeREXV.d.ts.map +0 -1
  193. package/dist/index-B4Fjfo5U.d.ts.map +0 -1
  194. package/dist/index-C61Wi7yg.d.ts.map +0 -1
  195. package/dist/llm-client-BiK4HW0u.d.ts +0 -290
  196. package/dist/llm-client-BiK4HW0u.d.ts.map +0 -1
  197. package/dist/raw-provider-sink-BU29Sh8h.d.ts +0 -134
  198. package/dist/raw-provider-sink-BU29Sh8h.d.ts.map +0 -1
  199. package/dist/replay-BRfMIs81.d.ts.map +0 -1
  200. package/dist/replay-C6wRg47C.js.map +0 -1
  201. package/dist/researcher-Doo95b50.d.ts.map +0 -1
  202. package/dist/skill-usage-BDQVPIG1.d.ts.map +0 -1
  203. package/dist/skillopt-optimization-method-CwSYkv35.d.ts.map +0 -1
  204. package/dist/store-CxJry_cs.d.ts +0 -229
  205. package/dist/store-CxJry_cs.d.ts.map +0 -1
  206. package/dist/supervisor-run-B7lUGoyZ.js.map +0 -1
  207. package/dist/tools-D8yTtNSN.js +0 -1190
  208. package/dist/tools-D8yTtNSN.js.map +0 -1
  209. package/dist/types-Cc3qbqzj.d.ts +0 -387
  210. package/dist/types-Cc3qbqzj.d.ts.map +0 -1
  211. 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.