@meetkai/mka1 0.54.22 → 0.54.24

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 (497) hide show
  1. package/README.md +302 -285
  2. package/bin/mcp-server.js +5917 -3364
  3. package/bin/mcp-server.js.map +47 -18
  4. package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.d.ts +19 -0
  5. package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.d.ts.map +1 -0
  6. package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.js +136 -0
  7. package/dist/commonjs/funcs/llmEvalsAppendAgentTrials.js.map +1 -0
  8. package/dist/commonjs/funcs/llmEvalsGetRunOverview.d.ts +20 -0
  9. package/dist/commonjs/funcs/llmEvalsGetRunOverview.d.ts.map +1 -0
  10. package/dist/commonjs/funcs/llmEvalsGetRunOverview.js +138 -0
  11. package/dist/commonjs/funcs/llmEvalsGetRunOverview.js.map +1 -0
  12. package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.d.ts +19 -0
  13. package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
  14. package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.js +142 -0
  15. package/dist/commonjs/funcs/llmEvalsGetSampleTrajectory.js.map +1 -0
  16. package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.d.ts +20 -0
  17. package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
  18. package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.js +142 -0
  19. package/dist/commonjs/funcs/llmEvalsGetSuiteLeaderboard.js.map +1 -0
  20. package/dist/commonjs/funcs/llmEvalsImportAgentRun.d.ts +19 -0
  21. package/dist/commonjs/funcs/llmEvalsImportAgentRun.d.ts.map +1 -0
  22. package/dist/commonjs/funcs/llmEvalsImportAgentRun.js +130 -0
  23. package/dist/commonjs/funcs/llmEvalsImportAgentRun.js.map +1 -0
  24. package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.d.ts +20 -0
  25. package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
  26. package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.js +146 -0
  27. package/dist/commonjs/funcs/llmEvalsUploadSampleTrajectory.js.map +1 -0
  28. package/dist/commonjs/funcs/llmResponsesCreate.d.ts +25 -0
  29. package/dist/commonjs/funcs/llmResponsesCreate.d.ts.map +1 -0
  30. package/dist/commonjs/funcs/llmResponsesCreate.js +137 -0
  31. package/dist/commonjs/funcs/llmResponsesCreate.js.map +1 -0
  32. package/dist/commonjs/lib/config.d.ts +2 -2
  33. package/dist/commonjs/lib/config.js +2 -2
  34. package/dist/commonjs/mcp-server/mcp-server.js +1 -1
  35. package/dist/commonjs/mcp-server/server.d.ts.map +1 -1
  36. package/dist/commonjs/mcp-server/server.js +15 -1
  37. package/dist/commonjs/mcp-server/server.js.map +1 -1
  38. package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts +8 -0
  39. package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts.map +1 -0
  40. package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.js +64 -0
  41. package/dist/commonjs/mcp-server/tools/llmEvalsAppendAgentTrials.js.map +1 -0
  42. package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.d.ts +8 -0
  43. package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.d.ts.map +1 -0
  44. package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.js +64 -0
  45. package/dist/commonjs/mcp-server/tools/llmEvalsGetRunOverview.js.map +1 -0
  46. package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts +8 -0
  47. package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
  48. package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.js +64 -0
  49. package/dist/commonjs/mcp-server/tools/llmEvalsGetSampleTrajectory.js.map +1 -0
  50. package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts +8 -0
  51. package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
  52. package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js +64 -0
  53. package/dist/commonjs/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js.map +1 -0
  54. package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.d.ts +8 -0
  55. package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.d.ts.map +1 -0
  56. package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.js +64 -0
  57. package/dist/commonjs/mcp-server/tools/llmEvalsImportAgentRun.js.map +1 -0
  58. package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts +8 -0
  59. package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
  60. package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.js +64 -0
  61. package/dist/commonjs/mcp-server/tools/llmEvalsUploadSampleTrajectory.js.map +1 -0
  62. package/dist/commonjs/mcp-server/tools/llmResponsesCreate.d.ts +8 -0
  63. package/dist/commonjs/mcp-server/tools/llmResponsesCreate.d.ts.map +1 -0
  64. package/dist/commonjs/mcp-server/tools/llmResponsesCreate.js +64 -0
  65. package/dist/commonjs/mcp-server/tools/llmResponsesCreate.js.map +1 -0
  66. package/dist/commonjs/models/components/appendagenttrialsrequest.d.ts +111 -0
  67. package/dist/commonjs/models/components/appendagenttrialsrequest.d.ts.map +1 -0
  68. package/dist/commonjs/models/components/appendagenttrialsrequest.js +136 -0
  69. package/dist/commonjs/models/components/appendagenttrialsrequest.js.map +1 -0
  70. package/dist/commonjs/models/components/evalleaderboardrow.d.ts +85 -0
  71. package/dist/commonjs/models/components/evalleaderboardrow.d.ts.map +1 -0
  72. package/dist/commonjs/models/components/evalleaderboardrow.js +129 -0
  73. package/dist/commonjs/models/components/evalleaderboardrow.js.map +1 -0
  74. package/dist/commonjs/models/components/evalrunoverview.d.ts +101 -0
  75. package/dist/commonjs/models/components/evalrunoverview.d.ts.map +1 -0
  76. package/dist/commonjs/models/components/evalrunoverview.js +150 -0
  77. package/dist/commonjs/models/components/evalrunoverview.js.map +1 -0
  78. package/dist/commonjs/models/components/evalsampleobject.d.ts +32 -0
  79. package/dist/commonjs/models/components/evalsampleobject.d.ts.map +1 -1
  80. package/dist/commonjs/models/components/evalsampleobject.js +20 -0
  81. package/dist/commonjs/models/components/evalsampleobject.js.map +1 -1
  82. package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.d.ts +32 -0
  83. package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.d.ts.map +1 -0
  84. package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.js +87 -0
  85. package/dist/commonjs/models/components/evalsampletrajectoryuploadedobject.js.map +1 -0
  86. package/dist/commonjs/models/components/evalsuiteleaderboard.d.ts +35 -0
  87. package/dist/commonjs/models/components/evalsuiteleaderboard.d.ts.map +1 -0
  88. package/dist/commonjs/models/components/evalsuiteleaderboard.js +78 -0
  89. package/dist/commonjs/models/components/evalsuiteleaderboard.js.map +1 -0
  90. package/dist/commonjs/models/components/importagentrunrequest.d.ts +164 -0
  91. package/dist/commonjs/models/components/importagentrunrequest.d.ts.map +1 -0
  92. package/dist/commonjs/models/components/importagentrunrequest.js +182 -0
  93. package/dist/commonjs/models/components/importagentrunrequest.js.map +1 -0
  94. package/dist/commonjs/models/components/index.d.ts +8 -0
  95. package/dist/commonjs/models/components/index.d.ts.map +1 -1
  96. package/dist/commonjs/models/components/index.js +8 -0
  97. package/dist/commonjs/models/components/index.js.map +1 -1
  98. package/dist/commonjs/models/components/responsescreaterequest.d.ts +432 -0
  99. package/dist/commonjs/models/components/responsescreaterequest.d.ts.map +1 -0
  100. package/dist/commonjs/models/components/responsescreaterequest.js +455 -0
  101. package/dist/commonjs/models/components/responsescreaterequest.js.map +1 -0
  102. package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.d.ts +34 -0
  103. package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.d.ts.map +1 -0
  104. package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.js +71 -0
  105. package/dist/commonjs/models/components/uploadevalsampletrajectoryrequest.js.map +1 -0
  106. package/dist/commonjs/models/operations/appendagentevaltrials.d.ts +264 -0
  107. package/dist/commonjs/models/operations/appendagentevaltrials.d.ts.map +1 -0
  108. package/dist/commonjs/models/operations/appendagentevaltrials.js +371 -0
  109. package/dist/commonjs/models/operations/appendagentevaltrials.js.map +1 -0
  110. package/dist/commonjs/models/operations/cancelevalrun.d.ts +20 -0
  111. package/dist/commonjs/models/operations/cancelevalrun.d.ts.map +1 -1
  112. package/dist/commonjs/models/operations/cancelevalrun.js +16 -0
  113. package/dist/commonjs/models/operations/cancelevalrun.js.map +1 -1
  114. package/dist/commonjs/models/operations/createevalrun.d.ts +20 -0
  115. package/dist/commonjs/models/operations/createevalrun.d.ts.map +1 -1
  116. package/dist/commonjs/models/operations/createevalrun.js +16 -0
  117. package/dist/commonjs/models/operations/createevalrun.js.map +1 -1
  118. package/dist/commonjs/models/operations/createresponse.d.ts +64 -0
  119. package/dist/commonjs/models/operations/createresponse.d.ts.map +1 -0
  120. package/dist/commonjs/models/operations/createresponse.js +128 -0
  121. package/dist/commonjs/models/operations/createresponse.js.map +1 -0
  122. package/dist/commonjs/models/operations/getevalrun.d.ts +20 -0
  123. package/dist/commonjs/models/operations/getevalrun.d.ts.map +1 -1
  124. package/dist/commonjs/models/operations/getevalrun.js +16 -0
  125. package/dist/commonjs/models/operations/getevalrun.js.map +1 -1
  126. package/dist/commonjs/models/operations/getevalrunoverview.d.ts +24 -0
  127. package/dist/commonjs/models/operations/getevalrunoverview.d.ts.map +1 -0
  128. package/dist/commonjs/models/operations/getevalrunoverview.js +73 -0
  129. package/dist/commonjs/models/operations/getevalrunoverview.js.map +1 -0
  130. package/dist/commonjs/models/operations/getevalsampletrajectory.d.ts +75 -0
  131. package/dist/commonjs/models/operations/getevalsampletrajectory.d.ts.map +1 -0
  132. package/dist/commonjs/models/operations/getevalsampletrajectory.js +133 -0
  133. package/dist/commonjs/models/operations/getevalsampletrajectory.js.map +1 -0
  134. package/dist/commonjs/models/operations/getevalsuiteleaderboard.d.ts +32 -0
  135. package/dist/commonjs/models/operations/getevalsuiteleaderboard.d.ts.map +1 -0
  136. package/dist/commonjs/models/operations/getevalsuiteleaderboard.js +83 -0
  137. package/dist/commonjs/models/operations/getevalsuiteleaderboard.js.map +1 -0
  138. package/dist/commonjs/models/operations/importagentevalrun.d.ts +262 -0
  139. package/dist/commonjs/models/operations/importagentevalrun.d.ts.map +1 -0
  140. package/dist/commonjs/models/operations/importagentevalrun.js +367 -0
  141. package/dist/commonjs/models/operations/importagentevalrun.js.map +1 -0
  142. package/dist/commonjs/models/operations/index.d.ts +7 -0
  143. package/dist/commonjs/models/operations/index.d.ts.map +1 -1
  144. package/dist/commonjs/models/operations/index.js +7 -0
  145. package/dist/commonjs/models/operations/index.js.map +1 -1
  146. package/dist/commonjs/models/operations/listevalruns.d.ts +20 -0
  147. package/dist/commonjs/models/operations/listevalruns.d.ts.map +1 -1
  148. package/dist/commonjs/models/operations/listevalruns.js +16 -0
  149. package/dist/commonjs/models/operations/listevalruns.js.map +1 -1
  150. package/dist/commonjs/models/operations/listevalscheduleruns.d.ts +20 -0
  151. package/dist/commonjs/models/operations/listevalscheduleruns.d.ts.map +1 -1
  152. package/dist/commonjs/models/operations/listevalscheduleruns.js +16 -0
  153. package/dist/commonjs/models/operations/listevalscheduleruns.js.map +1 -1
  154. package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.d.ts +20 -0
  155. package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.d.ts.map +1 -1
  156. package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.js +16 -0
  157. package/dist/commonjs/models/operations/listevalsuiteleaderboardruns.js.map +1 -1
  158. package/dist/commonjs/models/operations/rerunfailedevalsamples.d.ts +20 -0
  159. package/dist/commonjs/models/operations/rerunfailedevalsamples.d.ts.map +1 -1
  160. package/dist/commonjs/models/operations/rerunfailedevalsamples.js +16 -0
  161. package/dist/commonjs/models/operations/rerunfailedevalsamples.js.map +1 -1
  162. package/dist/commonjs/models/operations/retryfailedevalrun.d.ts +20 -0
  163. package/dist/commonjs/models/operations/retryfailedevalrun.d.ts.map +1 -1
  164. package/dist/commonjs/models/operations/retryfailedevalrun.js +16 -0
  165. package/dist/commonjs/models/operations/retryfailedevalrun.js.map +1 -1
  166. package/dist/commonjs/models/operations/uploadevalsampletrajectory.d.ts +31 -0
  167. package/dist/commonjs/models/operations/uploadevalsampletrajectory.d.ts.map +1 -0
  168. package/dist/commonjs/models/operations/uploadevalsampletrajectory.js +86 -0
  169. package/dist/commonjs/models/operations/uploadevalsampletrajectory.js.map +1 -0
  170. package/dist/commonjs/react-query/index.d.ts +7 -0
  171. package/dist/commonjs/react-query/index.d.ts.map +1 -1
  172. package/dist/commonjs/react-query/index.js +7 -0
  173. package/dist/commonjs/react-query/index.js.map +1 -1
  174. package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.d.ts +28 -0
  175. package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.d.ts.map +1 -0
  176. package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.js +47 -0
  177. package/dist/commonjs/react-query/llmEvalsAppendAgentTrials.js.map +1 -0
  178. package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.d.ts +16 -0
  179. package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.d.ts.map +1 -0
  180. package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.js +37 -0
  181. package/dist/commonjs/react-query/llmEvalsGetRunOverview.core.js.map +1 -0
  182. package/dist/commonjs/react-query/llmEvalsGetRunOverview.d.ts +40 -0
  183. package/dist/commonjs/react-query/llmEvalsGetRunOverview.d.ts.map +1 -0
  184. package/dist/commonjs/react-query/llmEvalsGetRunOverview.js +60 -0
  185. package/dist/commonjs/react-query/llmEvalsGetRunOverview.js.map +1 -0
  186. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.d.ts +16 -0
  187. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.d.ts.map +1 -0
  188. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.js +45 -0
  189. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.core.js.map +1 -0
  190. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.d.ts +44 -0
  191. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
  192. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.js +65 -0
  193. package/dist/commonjs/react-query/llmEvalsGetSampleTrajectory.js.map +1 -0
  194. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts +20 -0
  195. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts.map +1 -0
  196. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.js +41 -0
  197. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.core.js.map +1 -0
  198. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.d.ts +48 -0
  199. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
  200. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.js +65 -0
  201. package/dist/commonjs/react-query/llmEvalsGetSuiteLeaderboard.js.map +1 -0
  202. package/dist/commonjs/react-query/llmEvalsImportAgentRun.d.ts +28 -0
  203. package/dist/commonjs/react-query/llmEvalsImportAgentRun.d.ts.map +1 -0
  204. package/dist/commonjs/react-query/llmEvalsImportAgentRun.js +47 -0
  205. package/dist/commonjs/react-query/llmEvalsImportAgentRun.js.map +1 -0
  206. package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.d.ts +29 -0
  207. package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
  208. package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.js +47 -0
  209. package/dist/commonjs/react-query/llmEvalsUploadSampleTrajectory.js.map +1 -0
  210. package/dist/commonjs/react-query/llmResponsesCreate.d.ts +34 -0
  211. package/dist/commonjs/react-query/llmResponsesCreate.d.ts.map +1 -0
  212. package/dist/commonjs/react-query/llmResponsesCreate.js +50 -0
  213. package/dist/commonjs/react-query/llmResponsesCreate.js.map +1 -0
  214. package/dist/commonjs/sdk/evals.d.ts +42 -0
  215. package/dist/commonjs/sdk/evals.d.ts.map +1 -1
  216. package/dist/commonjs/sdk/evals.js +60 -0
  217. package/dist/commonjs/sdk/evals.js.map +1 -1
  218. package/dist/commonjs/sdk/responses.d.ts +11 -0
  219. package/dist/commonjs/sdk/responses.d.ts.map +1 -1
  220. package/dist/commonjs/sdk/responses.js +13 -1
  221. package/dist/commonjs/sdk/responses.js.map +1 -1
  222. package/dist/esm/funcs/llmEvalsAppendAgentTrials.d.ts +19 -0
  223. package/dist/esm/funcs/llmEvalsAppendAgentTrials.d.ts.map +1 -0
  224. package/dist/esm/funcs/llmEvalsAppendAgentTrials.js +100 -0
  225. package/dist/esm/funcs/llmEvalsAppendAgentTrials.js.map +1 -0
  226. package/dist/esm/funcs/llmEvalsGetRunOverview.d.ts +20 -0
  227. package/dist/esm/funcs/llmEvalsGetRunOverview.d.ts.map +1 -0
  228. package/dist/esm/funcs/llmEvalsGetRunOverview.js +102 -0
  229. package/dist/esm/funcs/llmEvalsGetRunOverview.js.map +1 -0
  230. package/dist/esm/funcs/llmEvalsGetSampleTrajectory.d.ts +19 -0
  231. package/dist/esm/funcs/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
  232. package/dist/esm/funcs/llmEvalsGetSampleTrajectory.js +106 -0
  233. package/dist/esm/funcs/llmEvalsGetSampleTrajectory.js.map +1 -0
  234. package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.d.ts +20 -0
  235. package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
  236. package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.js +106 -0
  237. package/dist/esm/funcs/llmEvalsGetSuiteLeaderboard.js.map +1 -0
  238. package/dist/esm/funcs/llmEvalsImportAgentRun.d.ts +19 -0
  239. package/dist/esm/funcs/llmEvalsImportAgentRun.d.ts.map +1 -0
  240. package/dist/esm/funcs/llmEvalsImportAgentRun.js +94 -0
  241. package/dist/esm/funcs/llmEvalsImportAgentRun.js.map +1 -0
  242. package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.d.ts +20 -0
  243. package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
  244. package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.js +110 -0
  245. package/dist/esm/funcs/llmEvalsUploadSampleTrajectory.js.map +1 -0
  246. package/dist/esm/funcs/llmResponsesCreate.d.ts +25 -0
  247. package/dist/esm/funcs/llmResponsesCreate.d.ts.map +1 -0
  248. package/dist/esm/funcs/llmResponsesCreate.js +100 -0
  249. package/dist/esm/funcs/llmResponsesCreate.js.map +1 -0
  250. package/dist/esm/lib/config.d.ts +2 -2
  251. package/dist/esm/lib/config.js +2 -2
  252. package/dist/esm/mcp-server/mcp-server.js +1 -1
  253. package/dist/esm/mcp-server/server.d.ts.map +1 -1
  254. package/dist/esm/mcp-server/server.js +15 -1
  255. package/dist/esm/mcp-server/server.js.map +1 -1
  256. package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts +8 -0
  257. package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.d.ts.map +1 -0
  258. package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.js +28 -0
  259. package/dist/esm/mcp-server/tools/llmEvalsAppendAgentTrials.js.map +1 -0
  260. package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.d.ts +8 -0
  261. package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.d.ts.map +1 -0
  262. package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.js +28 -0
  263. package/dist/esm/mcp-server/tools/llmEvalsGetRunOverview.js.map +1 -0
  264. package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts +8 -0
  265. package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
  266. package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.js +28 -0
  267. package/dist/esm/mcp-server/tools/llmEvalsGetSampleTrajectory.js.map +1 -0
  268. package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts +8 -0
  269. package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
  270. package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js +28 -0
  271. package/dist/esm/mcp-server/tools/llmEvalsGetSuiteLeaderboard.js.map +1 -0
  272. package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.d.ts +8 -0
  273. package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.d.ts.map +1 -0
  274. package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.js +28 -0
  275. package/dist/esm/mcp-server/tools/llmEvalsImportAgentRun.js.map +1 -0
  276. package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts +8 -0
  277. package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
  278. package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.js +28 -0
  279. package/dist/esm/mcp-server/tools/llmEvalsUploadSampleTrajectory.js.map +1 -0
  280. package/dist/esm/mcp-server/tools/llmResponsesCreate.d.ts +8 -0
  281. package/dist/esm/mcp-server/tools/llmResponsesCreate.d.ts.map +1 -0
  282. package/dist/esm/mcp-server/tools/llmResponsesCreate.js +28 -0
  283. package/dist/esm/mcp-server/tools/llmResponsesCreate.js.map +1 -0
  284. package/dist/esm/models/components/appendagenttrialsrequest.d.ts +111 -0
  285. package/dist/esm/models/components/appendagenttrialsrequest.d.ts.map +1 -0
  286. package/dist/esm/models/components/appendagenttrialsrequest.js +96 -0
  287. package/dist/esm/models/components/appendagenttrialsrequest.js.map +1 -0
  288. package/dist/esm/models/components/evalleaderboardrow.d.ts +85 -0
  289. package/dist/esm/models/components/evalleaderboardrow.d.ts.map +1 -0
  290. package/dist/esm/models/components/evalleaderboardrow.js +89 -0
  291. package/dist/esm/models/components/evalleaderboardrow.js.map +1 -0
  292. package/dist/esm/models/components/evalrunoverview.d.ts +101 -0
  293. package/dist/esm/models/components/evalrunoverview.d.ts.map +1 -0
  294. package/dist/esm/models/components/evalrunoverview.js +108 -0
  295. package/dist/esm/models/components/evalrunoverview.js.map +1 -0
  296. package/dist/esm/models/components/evalsampleobject.d.ts +32 -0
  297. package/dist/esm/models/components/evalsampleobject.d.ts.map +1 -1
  298. package/dist/esm/models/components/evalsampleobject.js +20 -0
  299. package/dist/esm/models/components/evalsampleobject.js.map +1 -1
  300. package/dist/esm/models/components/evalsampletrajectoryuploadedobject.d.ts +32 -0
  301. package/dist/esm/models/components/evalsampletrajectoryuploadedobject.d.ts.map +1 -0
  302. package/dist/esm/models/components/evalsampletrajectoryuploadedobject.js +49 -0
  303. package/dist/esm/models/components/evalsampletrajectoryuploadedobject.js.map +1 -0
  304. package/dist/esm/models/components/evalsuiteleaderboard.d.ts +35 -0
  305. package/dist/esm/models/components/evalsuiteleaderboard.d.ts.map +1 -0
  306. package/dist/esm/models/components/evalsuiteleaderboard.js +40 -0
  307. package/dist/esm/models/components/evalsuiteleaderboard.js.map +1 -0
  308. package/dist/esm/models/components/importagentrunrequest.d.ts +164 -0
  309. package/dist/esm/models/components/importagentrunrequest.d.ts.map +1 -0
  310. package/dist/esm/models/components/importagentrunrequest.js +142 -0
  311. package/dist/esm/models/components/importagentrunrequest.js.map +1 -0
  312. package/dist/esm/models/components/index.d.ts +8 -0
  313. package/dist/esm/models/components/index.d.ts.map +1 -1
  314. package/dist/esm/models/components/index.js +8 -0
  315. package/dist/esm/models/components/index.js.map +1 -1
  316. package/dist/esm/models/components/responsescreaterequest.d.ts +432 -0
  317. package/dist/esm/models/components/responsescreaterequest.d.ts.map +1 -0
  318. package/dist/esm/models/components/responsescreaterequest.js +403 -0
  319. package/dist/esm/models/components/responsescreaterequest.js.map +1 -0
  320. package/dist/esm/models/components/uploadevalsampletrajectoryrequest.d.ts +34 -0
  321. package/dist/esm/models/components/uploadevalsampletrajectoryrequest.d.ts.map +1 -0
  322. package/dist/esm/models/components/uploadevalsampletrajectoryrequest.js +33 -0
  323. package/dist/esm/models/components/uploadevalsampletrajectoryrequest.js.map +1 -0
  324. package/dist/esm/models/operations/appendagentevaltrials.d.ts +264 -0
  325. package/dist/esm/models/operations/appendagentevaltrials.d.ts.map +1 -0
  326. package/dist/esm/models/operations/appendagentevaltrials.js +323 -0
  327. package/dist/esm/models/operations/appendagentevaltrials.js.map +1 -0
  328. package/dist/esm/models/operations/cancelevalrun.d.ts +20 -0
  329. package/dist/esm/models/operations/cancelevalrun.d.ts.map +1 -1
  330. package/dist/esm/models/operations/cancelevalrun.js +16 -0
  331. package/dist/esm/models/operations/cancelevalrun.js.map +1 -1
  332. package/dist/esm/models/operations/createevalrun.d.ts +20 -0
  333. package/dist/esm/models/operations/createevalrun.d.ts.map +1 -1
  334. package/dist/esm/models/operations/createevalrun.js +16 -0
  335. package/dist/esm/models/operations/createevalrun.js.map +1 -1
  336. package/dist/esm/models/operations/createresponse.d.ts +64 -0
  337. package/dist/esm/models/operations/createresponse.d.ts.map +1 -0
  338. package/dist/esm/models/operations/createresponse.js +86 -0
  339. package/dist/esm/models/operations/createresponse.js.map +1 -0
  340. package/dist/esm/models/operations/getevalrun.d.ts +20 -0
  341. package/dist/esm/models/operations/getevalrun.d.ts.map +1 -1
  342. package/dist/esm/models/operations/getevalrun.js +16 -0
  343. package/dist/esm/models/operations/getevalrun.js.map +1 -1
  344. package/dist/esm/models/operations/getevalrunoverview.d.ts +24 -0
  345. package/dist/esm/models/operations/getevalrunoverview.d.ts.map +1 -0
  346. package/dist/esm/models/operations/getevalrunoverview.js +35 -0
  347. package/dist/esm/models/operations/getevalrunoverview.js.map +1 -0
  348. package/dist/esm/models/operations/getevalsampletrajectory.d.ts +75 -0
  349. package/dist/esm/models/operations/getevalsampletrajectory.d.ts.map +1 -0
  350. package/dist/esm/models/operations/getevalsampletrajectory.js +93 -0
  351. package/dist/esm/models/operations/getevalsampletrajectory.js.map +1 -0
  352. package/dist/esm/models/operations/getevalsuiteleaderboard.d.ts +32 -0
  353. package/dist/esm/models/operations/getevalsuiteleaderboard.d.ts.map +1 -0
  354. package/dist/esm/models/operations/getevalsuiteleaderboard.js +45 -0
  355. package/dist/esm/models/operations/getevalsuiteleaderboard.js.map +1 -0
  356. package/dist/esm/models/operations/importagentevalrun.d.ts +262 -0
  357. package/dist/esm/models/operations/importagentevalrun.d.ts.map +1 -0
  358. package/dist/esm/models/operations/importagentevalrun.js +319 -0
  359. package/dist/esm/models/operations/importagentevalrun.js.map +1 -0
  360. package/dist/esm/models/operations/index.d.ts +7 -0
  361. package/dist/esm/models/operations/index.d.ts.map +1 -1
  362. package/dist/esm/models/operations/index.js +7 -0
  363. package/dist/esm/models/operations/index.js.map +1 -1
  364. package/dist/esm/models/operations/listevalruns.d.ts +20 -0
  365. package/dist/esm/models/operations/listevalruns.d.ts.map +1 -1
  366. package/dist/esm/models/operations/listevalruns.js +16 -0
  367. package/dist/esm/models/operations/listevalruns.js.map +1 -1
  368. package/dist/esm/models/operations/listevalscheduleruns.d.ts +20 -0
  369. package/dist/esm/models/operations/listevalscheduleruns.d.ts.map +1 -1
  370. package/dist/esm/models/operations/listevalscheduleruns.js +16 -0
  371. package/dist/esm/models/operations/listevalscheduleruns.js.map +1 -1
  372. package/dist/esm/models/operations/listevalsuiteleaderboardruns.d.ts +20 -0
  373. package/dist/esm/models/operations/listevalsuiteleaderboardruns.d.ts.map +1 -1
  374. package/dist/esm/models/operations/listevalsuiteleaderboardruns.js +16 -0
  375. package/dist/esm/models/operations/listevalsuiteleaderboardruns.js.map +1 -1
  376. package/dist/esm/models/operations/rerunfailedevalsamples.d.ts +20 -0
  377. package/dist/esm/models/operations/rerunfailedevalsamples.d.ts.map +1 -1
  378. package/dist/esm/models/operations/rerunfailedevalsamples.js +16 -0
  379. package/dist/esm/models/operations/rerunfailedevalsamples.js.map +1 -1
  380. package/dist/esm/models/operations/retryfailedevalrun.d.ts +20 -0
  381. package/dist/esm/models/operations/retryfailedevalrun.d.ts.map +1 -1
  382. package/dist/esm/models/operations/retryfailedevalrun.js +16 -0
  383. package/dist/esm/models/operations/retryfailedevalrun.js.map +1 -1
  384. package/dist/esm/models/operations/uploadevalsampletrajectory.d.ts +31 -0
  385. package/dist/esm/models/operations/uploadevalsampletrajectory.d.ts.map +1 -0
  386. package/dist/esm/models/operations/uploadevalsampletrajectory.js +48 -0
  387. package/dist/esm/models/operations/uploadevalsampletrajectory.js.map +1 -0
  388. package/dist/esm/react-query/index.d.ts +7 -0
  389. package/dist/esm/react-query/index.d.ts.map +1 -1
  390. package/dist/esm/react-query/index.js +7 -0
  391. package/dist/esm/react-query/index.js.map +1 -1
  392. package/dist/esm/react-query/llmEvalsAppendAgentTrials.d.ts +28 -0
  393. package/dist/esm/react-query/llmEvalsAppendAgentTrials.d.ts.map +1 -0
  394. package/dist/esm/react-query/llmEvalsAppendAgentTrials.js +42 -0
  395. package/dist/esm/react-query/llmEvalsAppendAgentTrials.js.map +1 -0
  396. package/dist/esm/react-query/llmEvalsGetRunOverview.core.d.ts +16 -0
  397. package/dist/esm/react-query/llmEvalsGetRunOverview.core.d.ts.map +1 -0
  398. package/dist/esm/react-query/llmEvalsGetRunOverview.core.js +32 -0
  399. package/dist/esm/react-query/llmEvalsGetRunOverview.core.js.map +1 -0
  400. package/dist/esm/react-query/llmEvalsGetRunOverview.d.ts +40 -0
  401. package/dist/esm/react-query/llmEvalsGetRunOverview.d.ts.map +1 -0
  402. package/dist/esm/react-query/llmEvalsGetRunOverview.js +50 -0
  403. package/dist/esm/react-query/llmEvalsGetRunOverview.js.map +1 -0
  404. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.d.ts +16 -0
  405. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.d.ts.map +1 -0
  406. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.js +40 -0
  407. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.core.js.map +1 -0
  408. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.d.ts +44 -0
  409. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.d.ts.map +1 -0
  410. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.js +55 -0
  411. package/dist/esm/react-query/llmEvalsGetSampleTrajectory.js.map +1 -0
  412. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts +20 -0
  413. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.d.ts.map +1 -0
  414. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.js +36 -0
  415. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.core.js.map +1 -0
  416. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.d.ts +48 -0
  417. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.d.ts.map +1 -0
  418. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.js +55 -0
  419. package/dist/esm/react-query/llmEvalsGetSuiteLeaderboard.js.map +1 -0
  420. package/dist/esm/react-query/llmEvalsImportAgentRun.d.ts +28 -0
  421. package/dist/esm/react-query/llmEvalsImportAgentRun.d.ts.map +1 -0
  422. package/dist/esm/react-query/llmEvalsImportAgentRun.js +42 -0
  423. package/dist/esm/react-query/llmEvalsImportAgentRun.js.map +1 -0
  424. package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.d.ts +29 -0
  425. package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.d.ts.map +1 -0
  426. package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.js +42 -0
  427. package/dist/esm/react-query/llmEvalsUploadSampleTrajectory.js.map +1 -0
  428. package/dist/esm/react-query/llmResponsesCreate.d.ts +34 -0
  429. package/dist/esm/react-query/llmResponsesCreate.d.ts.map +1 -0
  430. package/dist/esm/react-query/llmResponsesCreate.js +43 -0
  431. package/dist/esm/react-query/llmResponsesCreate.js.map +1 -0
  432. package/dist/esm/sdk/evals.d.ts +42 -0
  433. package/dist/esm/sdk/evals.d.ts.map +1 -1
  434. package/dist/esm/sdk/evals.js +60 -0
  435. package/dist/esm/sdk/evals.js.map +1 -1
  436. package/dist/esm/sdk/responses.d.ts +11 -0
  437. package/dist/esm/sdk/responses.d.ts.map +1 -1
  438. package/dist/esm/sdk/responses.js +11 -0
  439. package/dist/esm/sdk/responses.js.map +1 -1
  440. package/jsr.json +1 -1
  441. package/package.json +1 -1
  442. package/src/funcs/llmEvalsAppendAgentTrials.ts +188 -0
  443. package/src/funcs/llmEvalsGetRunOverview.ts +192 -0
  444. package/src/funcs/llmEvalsGetSampleTrajectory.ts +197 -0
  445. package/src/funcs/llmEvalsGetSuiteLeaderboard.ts +197 -0
  446. package/src/funcs/llmEvalsImportAgentRun.ts +181 -0
  447. package/src/funcs/llmEvalsUploadSampleTrajectory.ts +201 -0
  448. package/src/funcs/llmResponsesCreate.ts +188 -0
  449. package/src/lib/config.ts +2 -2
  450. package/src/mcp-server/mcp-server.ts +1 -1
  451. package/src/mcp-server/server.ts +15 -1
  452. package/src/mcp-server/tools/llmEvalsAppendAgentTrials.ts +37 -0
  453. package/src/mcp-server/tools/llmEvalsGetRunOverview.ts +37 -0
  454. package/src/mcp-server/tools/llmEvalsGetSampleTrajectory.ts +37 -0
  455. package/src/mcp-server/tools/llmEvalsGetSuiteLeaderboard.ts +37 -0
  456. package/src/mcp-server/tools/llmEvalsImportAgentRun.ts +37 -0
  457. package/src/mcp-server/tools/llmEvalsUploadSampleTrajectory.ts +38 -0
  458. package/src/mcp-server/tools/llmResponsesCreate.ts +37 -0
  459. package/src/models/components/appendagenttrialsrequest.ts +224 -0
  460. package/src/models/components/evalleaderboardrow.ts +200 -0
  461. package/src/models/components/evalrunoverview.ts +240 -0
  462. package/src/models/components/evalsampleobject.ts +48 -0
  463. package/src/models/components/evalsampletrajectoryuploadedobject.ts +98 -0
  464. package/src/models/components/evalsuiteleaderboard.ts +93 -0
  465. package/src/models/components/importagentrunrequest.ts +319 -0
  466. package/src/models/components/index.ts +8 -0
  467. package/src/models/components/responsescreaterequest.ts +1076 -0
  468. package/src/models/components/uploadevalsampletrajectoryrequest.ts +79 -0
  469. package/src/models/operations/appendagentevaltrials.ts +678 -0
  470. package/src/models/operations/cancelevalrun.ts +36 -0
  471. package/src/models/operations/createevalrun.ts +36 -0
  472. package/src/models/operations/createresponse.ts +198 -0
  473. package/src/models/operations/getevalrun.ts +36 -0
  474. package/src/models/operations/getevalrunoverview.ts +73 -0
  475. package/src/models/operations/getevalsampletrajectory.ts +199 -0
  476. package/src/models/operations/getevalsuiteleaderboard.ts +93 -0
  477. package/src/models/operations/importagentevalrun.ts +665 -0
  478. package/src/models/operations/index.ts +7 -0
  479. package/src/models/operations/listevalruns.ts +36 -0
  480. package/src/models/operations/listevalscheduleruns.ts +36 -0
  481. package/src/models/operations/listevalsuiteleaderboardruns.ts +36 -0
  482. package/src/models/operations/rerunfailedevalsamples.ts +36 -0
  483. package/src/models/operations/retryfailedevalrun.ts +36 -0
  484. package/src/models/operations/uploadevalsampletrajectory.ts +98 -0
  485. package/src/react-query/index.ts +7 -0
  486. package/src/react-query/llmEvalsAppendAgentTrials.ts +109 -0
  487. package/src/react-query/llmEvalsGetRunOverview.core.ts +77 -0
  488. package/src/react-query/llmEvalsGetRunOverview.ts +150 -0
  489. package/src/react-query/llmEvalsGetSampleTrajectory.core.ts +94 -0
  490. package/src/react-query/llmEvalsGetSampleTrajectory.ts +159 -0
  491. package/src/react-query/llmEvalsGetSuiteLeaderboard.core.ts +89 -0
  492. package/src/react-query/llmEvalsGetSuiteLeaderboard.ts +163 -0
  493. package/src/react-query/llmEvalsImportAgentRun.ts +109 -0
  494. package/src/react-query/llmEvalsUploadSampleTrajectory.ts +110 -0
  495. package/src/react-query/llmResponsesCreate.ts +113 -0
  496. package/src/sdk/evals.ts +108 -0
  497. package/src/sdk/responses.ts +23 -0
@@ -58,6 +58,13 @@ export declare class Evals extends ClientSDK {
58
58
  * Returns each ranking group's most recent completed runs for a suite in one request, with the group assignments in `groups`. A group is (model, targeted task) for task_ids-restricted runs and (model) for unrestricted runs (task_id null). Build boards from `groups`, not from run.models/run.task_ids — a returned run may name models or tasks whose groups it did not rank in. `truncated: true` means a server ceiling trimmed the aggregate; whole runs are kept in (best rank, first model, first task, id) order, so every group's newest runs survive before any group's fallbacks and no group is dropped for being old. Resume a truncated board by passing `next_cursor` back as `cursor` and unioning the responses. See the evals docs for grouping rationale and cost characteristics.
59
59
  */
60
60
  listSuiteLeaderboardRuns(request: operations.ListEvalSuiteLeaderboardRunsRequest, options?: RequestOptions): Promise<operations.ListEvalSuiteLeaderboardRunsResponseBody>;
61
+ /**
62
+ * Get the coding-agent leaderboard for an eval suite
63
+ *
64
+ * @remarks
65
+ * Ranks the suite's completed coding-agent runs, one row per (agent, model, effort). Only runs that recorded an `agent_name` participate — a QA or transcription run of the same suite has no agent to attribute a score to and is not a board row. `accuracy` is the mean of `metric` (default `reward`) over the row's scored trials, and `accuracy_ci` is the 95% Wald interval around it; both are derived per request rather than stored, so rerunning a failed trial moves them instead of leaving a stale copy behind. `agent_version` is reported but is not part of the row identity, so an agent upgrade does not split a row in two. Rows are ordered by accuracy descending, nulls last. Pass `suite_version` when the suite has more than one, otherwise the board mixes task sets.
66
+ */
67
+ getSuiteLeaderboard(request: operations.GetEvalSuiteLeaderboardRequest, options?: RequestOptions): Promise<components.EvalSuiteLeaderboard>;
61
68
  /**
62
69
  * Create an eval run
63
70
  *
@@ -107,6 +114,13 @@ export declare class Evals extends ClientSDK {
107
114
  * Queues a failed or cancelled eval run to retry in place. Completed samples keep their results, generated-but-unscored cancelled samples resume at scoring, unfinished samples are requeued, and runs with no persisted samples are prepared from scratch with the same run ID.
108
115
  */
109
116
  retryFailedRun(request: operations.RetryFailedEvalRunRequest, options?: RequestOptions): Promise<operations.RetryFailedEvalRunResponseBody>;
117
+ /**
118
+ * Get an eval run overview
119
+ *
120
+ * @remarks
121
+ * Aggregate header for one run's trials view: trial counts, average reward, cost, and the input/output/cached token split. Its own route rather than fields on the run object because it scans the run's samples — folding it into `GET /evals/runs/{run_id}` would charge that scan to every run list and to the status polling that runs for the whole length of an eval. `trials.errored` overlaps `trials.failed` instead of partitioning it: a coding-agent trial can carry an agent timeout in `error` and still be completed and scored. `trials.retried` counts trials rerun through rerun-failed, read from the pre-rerun snapshot, since a rerun overwrites the sample in place.
122
+ */
123
+ getRunOverview(request: operations.GetEvalRunOverviewRequest, options?: RequestOptions): Promise<components.EvalRunOverview>;
110
124
  /**
111
125
  * List eval samples
112
126
  *
@@ -121,6 +135,20 @@ export declare class Evals extends ClientSDK {
121
135
  * Returns `{ object, audio, sample_index, task_id, model }` for a single transcription sample — the clip reference (a base64 `data:` URI or a URL) read from the un-redacted `dataset_row` (list responses redact inline `data:` blobs), plus the resolved task/model. Prefers the task's configured `audio_column`, falling back to a heuristic scan. The clip differs across tasks, so pass `task_id` when a run has more than one transcription task; if the index spans multiple tasks and `task_id` is omitted, returns 400 rather than guessing. `model` is optional (the clip is identical across models) and only extends the index prefix. Returns 404 when the sample or its audio is absent, 413 when the inline clip is too large. Returns 503 when object storage is briefly unreachable, as distinct from 404 for a clip that is genuinely gone.
122
136
  */
123
137
  getSampleAudio(request: operations.GetEvalSampleAudioRequest, options?: RequestOptions): Promise<components.EvalSampleAudioObject>;
138
+ /**
139
+ * Get an eval sample trajectory
140
+ *
141
+ * @remarks
142
+ * Returns one coding-agent trial's session — the steps the agent took, verbatim in the harness's interchange format (see `schema_version`, e.g. `ATIF-v1.7`). Deliberately not part of the samples list: a trajectory averages ~92 KB and that list pages up to 500 rows. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one; an index that matches several trials returns 400 rather than guessing, and never falls back to another trial's session. Returns 404 when the sample does not exist or recorded no trajectory.
143
+ */
144
+ getSampleTrajectory(request: operations.GetEvalSampleTrajectoryRequest, options?: RequestOptions): Promise<operations.GetEvalSampleTrajectoryResponseBody>;
145
+ /**
146
+ * Upload an eval sample trajectory
147
+ *
148
+ * @remarks
149
+ * Stores one coding-agent trial's session, in whatever interchange format the harness produced (record it in `schema_version`, e.g. `ATIF-v1.7`). `steps` is stored verbatim and never validated, so a harness format change needs no gateway release. Separate from the run import because a trajectory averages ~92 KB and a whole run's worth would not fit in one request. Upserts, so re-sending after a timeout replaces the trajectory rather than failing. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one — an ambiguous index returns 400 rather than writing to the wrong trial. Rejects a payload whose `steps` and `logs` together exceed 16 MiB with 413.
150
+ */
151
+ uploadSampleTrajectory(request: operations.UploadEvalSampleTrajectoryRequest, options?: RequestOptions): Promise<components.EvalSampleTrajectoryUploadedObject>;
124
152
  /**
125
153
  * Get eval run artifacts
126
154
  *
@@ -128,6 +156,20 @@ export declare class Evals extends ClientSDK {
128
156
  * Returns generated result and sample artifact file IDs for a completed eval run.
129
157
  */
130
158
  getArtifacts(request: operations.GetEvalArtifactsRequest, options?: RequestOptions): Promise<components.EvalArtifactsObject>;
159
+ /**
160
+ * Import a finished coding-agent run
161
+ *
162
+ * @remarks
163
+ * Uploads one completed harness job — the run and its trials — directly, so results never round-trip through external storage the way the Hugging Face importer does. Every `task_id` must already exist in the target suite version's manifest; unknown ids are rejected rather than invented, because a typo would otherwise import as a task the suite does not have and read as a model that never covered the version. The run is recorded as `completed` and is not executed: this is a write, not a run request, so no workflow is started. Trials that cover every task of the version get `task_ids: null`, which is what lets the run rank as a complete sweep. Trajectories are NOT part of this payload — a full 91-task run measured 8.3 MB of them — so upload each one against `PUT /evals/runs/{run_id}/samples/{sample_index}/trajectory` afterwards. Pass `idempotency_key` and a retried upload returns the first run instead of doubling the trials behind a board row.
164
+ */
165
+ importAgentRun(request: operations.ImportAgentEvalRunRequest, options?: RequestOptions): Promise<operations.ImportAgentEvalRunResponseBody>;
166
+ /**
167
+ * Append trials to an open coding-agent run
168
+ *
169
+ * @remarks
170
+ * Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
171
+ */
172
+ appendAgentTrials(request: operations.AppendAgentEvalTrialsRequest, options?: RequestOptions): Promise<operations.AppendAgentEvalTrialsResponseBody>;
131
173
  /**
132
174
  * Import historical eval results from Hugging Face
133
175
  *
@@ -1 +1 @@
1
- {"version":3,"file":"evals.d.ts","sourceRoot":"","sources":["../../../src/sdk/evals.ts"],"names":[],"mappings":"AA8BA,OAAO,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAC3D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAG5D,qBAAa,KAAM,SAAQ,SAAS;IAClC;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,eAAe,CAAC;IAQtC;;;;;OAKG;IACG,UAAU,CACd,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,aAAa,CAAC;IAQpC;;;;;OAKG;IACG,QAAQ,CACZ,OAAO,EAAE,UAAU,CAAC,mBAAmB,EACvC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,eAAe,CAAC;IAQtC;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,sBAAsB,CAAC;IAQ7C;;;;;OAKG;IACG,kBAAkB,CACtB,OAAO,EAAE,UAAU,CAAC,6BAA6B,EACjD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kCAAkC,CAAC;IAQzD;;;;;OAKG;IACG,iBAAiB,CACrB,OAAO,EAAE,UAAU,CAAC,4BAA4B,EAChD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,iCAAiC,CAAC;IAQxD;;;;;OAKG;IACG,eAAe,CACnB,OAAO,EAAE,UAAU,CAAC,0BAA0B,EAC9C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,+BAA+B,CAAC;IAQtD;;;;;OAKG;IACG,wBAAwB,CAC5B,OAAO,EAAE,UAAU,CAAC,mCAAmC,EACvD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,wCAAwC,CAAC;IAQ/D;;;;;OAKG;IACG,SAAS,CACb,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,yBAAyB,CAAC;IAQhD;;;;;OAKG;IACG,QAAQ,CACZ,OAAO,EAAE,UAAU,CAAC,mBAAmB,EACvC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,wBAAwB,CAAC;IAQ/C;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,iBAAiB,EACrC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,sBAAsB,CAAC;IAQ7C;;;;;OAKG;IACG,SAAS,CACb,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,oBAAoB,CAAC;IAQ3C;;;;;OAKG;IACG,SAAS,CACb,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,yBAAyB,CAAC;IAQhD;;;;;OAKG;IACG,kBAAkB,CACtB,OAAO,EAAE,UAAU,CAAC,6BAA6B,EACjD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kCAAkC,CAAC;IAQzD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC;IAQrC;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,qBAAqB,CAAC;IAQ5C;;;;;OAKG;IACG,YAAY,CAChB,OAAO,EAAE,UAAU,CAAC,uBAAuB,EAC3C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,mBAAmB,CAAC;IAQ1C;;;;;OAKG;IACG,uBAAuB,CAC3B,OAAO,EAAE,UAAU,CAAC,kCAAkC,EACtD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,0BAA0B,CAAC;IAQjD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,aAAa,CACjB,OAAO,EAAE,UAAU,CAAC,wBAAwB,EAC5C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,6BAA6B,CAAC;IAQpD;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,2BAA2B,CAAC;IAQlD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,yBAAyB,CAAC;IAQhD;;;;;OAKG;IACG,eAAe,CACnB,OAAO,EAAE,UAAU,CAAC,0BAA0B,EAC9C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,+BAA+B,CAAC;IAQtD;;;;;OAKG;IACG,gBAAgB,CACpB,OAAO,EAAE,UAAU,CAAC,2BAA2B,EAC/C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,gCAAgC,CAAC;CAOxD"}
1
+ {"version":3,"file":"evals.d.ts","sourceRoot":"","sources":["../../../src/sdk/evals.ts"],"names":[],"mappings":"AAoCA,OAAO,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAC3D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAG5D,qBAAa,KAAM,SAAQ,SAAS;IAClC;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,eAAe,CAAC;IAQtC;;;;;OAKG;IACG,UAAU,CACd,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,aAAa,CAAC;IAQpC;;;;;OAKG;IACG,QAAQ,CACZ,OAAO,EAAE,UAAU,CAAC,mBAAmB,EACvC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,eAAe,CAAC;IAQtC;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,sBAAsB,CAAC;IAQ7C;;;;;OAKG;IACG,kBAAkB,CACtB,OAAO,EAAE,UAAU,CAAC,6BAA6B,EACjD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kCAAkC,CAAC;IAQzD;;;;;OAKG;IACG,iBAAiB,CACrB,OAAO,EAAE,UAAU,CAAC,4BAA4B,EAChD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,iCAAiC,CAAC;IAQxD;;;;;OAKG;IACG,eAAe,CACnB,OAAO,EAAE,UAAU,CAAC,0BAA0B,EAC9C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,+BAA+B,CAAC;IAQtD;;;;;OAKG;IACG,wBAAwB,CAC5B,OAAO,EAAE,UAAU,CAAC,mCAAmC,EACvD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,wCAAwC,CAAC;IAQ/D;;;;;OAKG;IACG,mBAAmB,CACvB,OAAO,EAAE,UAAU,CAAC,8BAA8B,EAClD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,oBAAoB,CAAC;IAQ3C;;;;;OAKG;IACG,SAAS,CACb,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,yBAAyB,CAAC;IAQhD;;;;;OAKG;IACG,QAAQ,CACZ,OAAO,EAAE,UAAU,CAAC,mBAAmB,EACvC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,wBAAwB,CAAC;IAQ/C;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,iBAAiB,EACrC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,sBAAsB,CAAC;IAQ7C;;;;;OAKG;IACG,SAAS,CACb,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,oBAAoB,CAAC;IAQ3C;;;;;OAKG;IACG,SAAS,CACb,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,yBAAyB,CAAC;IAQhD;;;;;OAKG;IACG,kBAAkB,CACtB,OAAO,EAAE,UAAU,CAAC,6BAA6B,EACjD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kCAAkC,CAAC;IAQzD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,eAAe,CAAC;IAQtC;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC;IAQrC;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,qBAAqB,CAAC;IAQ5C;;;;;OAKG;IACG,mBAAmB,CACvB,OAAO,EAAE,UAAU,CAAC,8BAA8B,EAClD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,mCAAmC,CAAC;IAQ1D;;;;;OAKG;IACG,sBAAsB,CAC1B,OAAO,EAAE,UAAU,CAAC,iCAAiC,EACrD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kCAAkC,CAAC;IAQzD;;;;;OAKG;IACG,YAAY,CAChB,OAAO,EAAE,UAAU,CAAC,uBAAuB,EAC3C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,mBAAmB,CAAC;IAQ1C;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,iBAAiB,CACrB,OAAO,EAAE,UAAU,CAAC,4BAA4B,EAChD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,iCAAiC,CAAC;IAQxD;;;;;OAKG;IACG,uBAAuB,CAC3B,OAAO,EAAE,UAAU,CAAC,kCAAkC,EACtD,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,0BAA0B,CAAC;IAQjD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,aAAa,CACjB,OAAO,EAAE,UAAU,CAAC,wBAAwB,EAC5C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,6BAA6B,CAAC;IAQpD;;;;;OAKG;IACG,WAAW,CACf,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,2BAA2B,CAAC;IAQlD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,8BAA8B,CAAC;IAQrD;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,yBAAyB,CAAC;IAQhD;;;;;OAKG;IACG,eAAe,CACnB,OAAO,EAAE,UAAU,CAAC,0BAA0B,EAC9C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,+BAA+B,CAAC;IAQtD;;;;;OAKG;IACG,gBAAgB,CACpB,OAAO,EAAE,UAAU,CAAC,2BAA2B,EAC/C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,gCAAgC,CAAC;CAOxD"}
@@ -4,6 +4,7 @@
4
4
  */
5
5
  Object.defineProperty(exports, "__esModule", { value: true });
6
6
  exports.Evals = void 0;
7
+ const llmEvalsAppendAgentTrials_js_1 = require("../funcs/llmEvalsAppendAgentTrials.js");
7
8
  const llmEvalsCancelRun_js_1 = require("../funcs/llmEvalsCancelRun.js");
8
9
  const llmEvalsCreateRun_js_1 = require("../funcs/llmEvalsCreateRun.js");
9
10
  const llmEvalsCreateSchedule_js_1 = require("../funcs/llmEvalsCreateSchedule.js");
@@ -14,10 +15,14 @@ const llmEvalsDeleteSchedule_js_1 = require("../funcs/llmEvalsDeleteSchedule.js"
14
15
  const llmEvalsDeleteSuite_js_1 = require("../funcs/llmEvalsDeleteSuite.js");
15
16
  const llmEvalsGetArtifacts_js_1 = require("../funcs/llmEvalsGetArtifacts.js");
16
17
  const llmEvalsGetRun_js_1 = require("../funcs/llmEvalsGetRun.js");
18
+ const llmEvalsGetRunOverview_js_1 = require("../funcs/llmEvalsGetRunOverview.js");
17
19
  const llmEvalsGetSampleAudio_js_1 = require("../funcs/llmEvalsGetSampleAudio.js");
20
+ const llmEvalsGetSampleTrajectory_js_1 = require("../funcs/llmEvalsGetSampleTrajectory.js");
18
21
  const llmEvalsGetSchedule_js_1 = require("../funcs/llmEvalsGetSchedule.js");
19
22
  const llmEvalsGetSuite_js_1 = require("../funcs/llmEvalsGetSuite.js");
23
+ const llmEvalsGetSuiteLeaderboard_js_1 = require("../funcs/llmEvalsGetSuiteLeaderboard.js");
20
24
  const llmEvalsGetSuiteVersion_js_1 = require("../funcs/llmEvalsGetSuiteVersion.js");
25
+ const llmEvalsImportAgentRun_js_1 = require("../funcs/llmEvalsImportAgentRun.js");
21
26
  const llmEvalsImportHistoricalResults_js_1 = require("../funcs/llmEvalsImportHistoricalResults.js");
22
27
  const llmEvalsListRuns_js_1 = require("../funcs/llmEvalsListRuns.js");
23
28
  const llmEvalsListSamples_js_1 = require("../funcs/llmEvalsListSamples.js");
@@ -30,6 +35,7 @@ const llmEvalsRerunFailedSamples_js_1 = require("../funcs/llmEvalsRerunFailedSam
30
35
  const llmEvalsRetryFailedRun_js_1 = require("../funcs/llmEvalsRetryFailedRun.js");
31
36
  const llmEvalsTriggerSchedule_js_1 = require("../funcs/llmEvalsTriggerSchedule.js");
32
37
  const llmEvalsUpdateSchedule_js_1 = require("../funcs/llmEvalsUpdateSchedule.js");
38
+ const llmEvalsUploadSampleTrajectory_js_1 = require("../funcs/llmEvalsUploadSampleTrajectory.js");
33
39
  const sdks_js_1 = require("../lib/sdks.js");
34
40
  const fp_js_1 = require("../types/fp.js");
35
41
  class Evals extends sdks_js_1.ClientSDK {
@@ -105,6 +111,15 @@ class Evals extends sdks_js_1.ClientSDK {
105
111
  async listSuiteLeaderboardRuns(request, options) {
106
112
  return (0, fp_js_1.unwrapAsync)((0, llmEvalsListSuiteLeaderboardRuns_js_1.llmEvalsListSuiteLeaderboardRuns)(this, request, options));
107
113
  }
114
+ /**
115
+ * Get the coding-agent leaderboard for an eval suite
116
+ *
117
+ * @remarks
118
+ * Ranks the suite's completed coding-agent runs, one row per (agent, model, effort). Only runs that recorded an `agent_name` participate — a QA or transcription run of the same suite has no agent to attribute a score to and is not a board row. `accuracy` is the mean of `metric` (default `reward`) over the row's scored trials, and `accuracy_ci` is the 95% Wald interval around it; both are derived per request rather than stored, so rerunning a failed trial moves them instead of leaving a stale copy behind. `agent_version` is reported but is not part of the row identity, so an agent upgrade does not split a row in two. Rows are ordered by accuracy descending, nulls last. Pass `suite_version` when the suite has more than one, otherwise the board mixes task sets.
119
+ */
120
+ async getSuiteLeaderboard(request, options) {
121
+ return (0, fp_js_1.unwrapAsync)((0, llmEvalsGetSuiteLeaderboard_js_1.llmEvalsGetSuiteLeaderboard)(this, request, options));
122
+ }
108
123
  /**
109
124
  * Create an eval run
110
125
  *
@@ -168,6 +183,15 @@ class Evals extends sdks_js_1.ClientSDK {
168
183
  async retryFailedRun(request, options) {
169
184
  return (0, fp_js_1.unwrapAsync)((0, llmEvalsRetryFailedRun_js_1.llmEvalsRetryFailedRun)(this, request, options));
170
185
  }
186
+ /**
187
+ * Get an eval run overview
188
+ *
189
+ * @remarks
190
+ * Aggregate header for one run's trials view: trial counts, average reward, cost, and the input/output/cached token split. Its own route rather than fields on the run object because it scans the run's samples — folding it into `GET /evals/runs/{run_id}` would charge that scan to every run list and to the status polling that runs for the whole length of an eval. `trials.errored` overlaps `trials.failed` instead of partitioning it: a coding-agent trial can carry an agent timeout in `error` and still be completed and scored. `trials.retried` counts trials rerun through rerun-failed, read from the pre-rerun snapshot, since a rerun overwrites the sample in place.
191
+ */
192
+ async getRunOverview(request, options) {
193
+ return (0, fp_js_1.unwrapAsync)((0, llmEvalsGetRunOverview_js_1.llmEvalsGetRunOverview)(this, request, options));
194
+ }
171
195
  /**
172
196
  * List eval samples
173
197
  *
@@ -186,6 +210,24 @@ class Evals extends sdks_js_1.ClientSDK {
186
210
  async getSampleAudio(request, options) {
187
211
  return (0, fp_js_1.unwrapAsync)((0, llmEvalsGetSampleAudio_js_1.llmEvalsGetSampleAudio)(this, request, options));
188
212
  }
213
+ /**
214
+ * Get an eval sample trajectory
215
+ *
216
+ * @remarks
217
+ * Returns one coding-agent trial's session — the steps the agent took, verbatim in the harness's interchange format (see `schema_version`, e.g. `ATIF-v1.7`). Deliberately not part of the samples list: a trajectory averages ~92 KB and that list pages up to 500 rows. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one; an index that matches several trials returns 400 rather than guessing, and never falls back to another trial's session. Returns 404 when the sample does not exist or recorded no trajectory.
218
+ */
219
+ async getSampleTrajectory(request, options) {
220
+ return (0, fp_js_1.unwrapAsync)((0, llmEvalsGetSampleTrajectory_js_1.llmEvalsGetSampleTrajectory)(this, request, options));
221
+ }
222
+ /**
223
+ * Upload an eval sample trajectory
224
+ *
225
+ * @remarks
226
+ * Stores one coding-agent trial's session, in whatever interchange format the harness produced (record it in `schema_version`, e.g. `ATIF-v1.7`). `steps` is stored verbatim and never validated, so a harness format change needs no gateway release. Separate from the run import because a trajectory averages ~92 KB and a whole run's worth would not fit in one request. Upserts, so re-sending after a timeout replaces the trajectory rather than failing. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one — an ambiguous index returns 400 rather than writing to the wrong trial. Rejects a payload whose `steps` and `logs` together exceed 16 MiB with 413.
227
+ */
228
+ async uploadSampleTrajectory(request, options) {
229
+ return (0, fp_js_1.unwrapAsync)((0, llmEvalsUploadSampleTrajectory_js_1.llmEvalsUploadSampleTrajectory)(this, request, options));
230
+ }
189
231
  /**
190
232
  * Get eval run artifacts
191
233
  *
@@ -195,6 +237,24 @@ class Evals extends sdks_js_1.ClientSDK {
195
237
  async getArtifacts(request, options) {
196
238
  return (0, fp_js_1.unwrapAsync)((0, llmEvalsGetArtifacts_js_1.llmEvalsGetArtifacts)(this, request, options));
197
239
  }
240
+ /**
241
+ * Import a finished coding-agent run
242
+ *
243
+ * @remarks
244
+ * Uploads one completed harness job — the run and its trials — directly, so results never round-trip through external storage the way the Hugging Face importer does. Every `task_id` must already exist in the target suite version's manifest; unknown ids are rejected rather than invented, because a typo would otherwise import as a task the suite does not have and read as a model that never covered the version. The run is recorded as `completed` and is not executed: this is a write, not a run request, so no workflow is started. Trials that cover every task of the version get `task_ids: null`, which is what lets the run rank as a complete sweep. Trajectories are NOT part of this payload — a full 91-task run measured 8.3 MB of them — so upload each one against `PUT /evals/runs/{run_id}/samples/{sample_index}/trajectory` afterwards. Pass `idempotency_key` and a retried upload returns the first run instead of doubling the trials behind a board row.
245
+ */
246
+ async importAgentRun(request, options) {
247
+ return (0, fp_js_1.unwrapAsync)((0, llmEvalsImportAgentRun_js_1.llmEvalsImportAgentRun)(this, request, options));
248
+ }
249
+ /**
250
+ * Append trials to an open coding-agent run
251
+ *
252
+ * @remarks
253
+ * Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
254
+ */
255
+ async appendAgentTrials(request, options) {
256
+ return (0, fp_js_1.unwrapAsync)((0, llmEvalsAppendAgentTrials_js_1.llmEvalsAppendAgentTrials)(this, request, options));
257
+ }
198
258
  /**
199
259
  * Import historical eval results from Hugging Face
200
260
  *
@@ -1 +1 @@
1
- {"version":3,"file":"evals.js","sourceRoot":"","sources":["../../../src/sdk/evals.ts"],"names":[],"mappings":";AAAA;;GAEG;;;AAEH,wEAAkE;AAClE,wEAAkE;AAClE,kFAA4E;AAC5E,4EAAsE;AACtE,0FAAoF;AACpF,wEAAkE;AAClE,kFAA4E;AAC5E,4EAAsE;AACtE,8EAAwE;AACxE,kEAA4D;AAC5D,kFAA4E;AAC5E,4EAAsE;AACtE,sEAAgE;AAChE,oFAA8E;AAC9E,oGAA8F;AAC9F,sEAAgE;AAChE,4EAAsE;AACtE,sFAAgF;AAChF,gFAA0E;AAC1E,sGAAgG;AAChG,0EAAoE;AACpE,wFAAkF;AAClF,0FAAoF;AACpF,kFAA4E;AAC5E,oFAA8E;AAC9E,kFAA4E;AAC5E,4CAA2D;AAG3D,0CAA6C;AAE7C,MAAa,KAAM,SAAQ,mBAAS;IAClC;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,UAAU,CACd,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,QAAQ,CACZ,OAAuC,EACvC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,kBAAkB,CACtB,OAAiD,EACjD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0DAA0B,EAC3C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,iBAAiB,CACrB,OAAgD,EAChD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wDAAyB,EAC1C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,eAAe,CACnB,OAA8C,EAC9C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,oDAAuB,EACxC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,wBAAwB,CAC5B,OAAuD,EACvD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sEAAgC,EACjD,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,SAAS,CACb,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wCAAiB,EAClC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,QAAQ,CACZ,OAAuC,EACvC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAqC,EACrC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kCAAc,EAC/B,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,SAAS,CACb,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wCAAiB,EAClC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,SAAS,CACb,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wCAAiB,EAClC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,kBAAkB,CACtB,OAAiD,EACjD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0DAA0B,EAC3C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,YAAY,CAChB,OAA2C,EAC3C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,8CAAoB,EACrC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,uBAAuB,CAC3B,OAAsD,EACtD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,oEAA+B,EAChD,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,aAAa,CACjB,OAA4C,EAC5C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,gDAAqB,EACtC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,eAAe,CACnB,OAA8C,EAC9C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,oDAAuB,EACxC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,gBAAgB,CACpB,OAA+C,EAC/C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sDAAwB,EACzC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;CACF;AA1bD,sBA0bC"}
1
+ {"version":3,"file":"evals.js","sourceRoot":"","sources":["../../../src/sdk/evals.ts"],"names":[],"mappings":";AAAA;;GAEG;;;AAEH,wFAAkF;AAClF,wEAAkE;AAClE,wEAAkE;AAClE,kFAA4E;AAC5E,4EAAsE;AACtE,0FAAoF;AACpF,wEAAkE;AAClE,kFAA4E;AAC5E,4EAAsE;AACtE,8EAAwE;AACxE,kEAA4D;AAC5D,kFAA4E;AAC5E,kFAA4E;AAC5E,4FAAsF;AACtF,4EAAsE;AACtE,sEAAgE;AAChE,4FAAsF;AACtF,oFAA8E;AAC9E,kFAA4E;AAC5E,oGAA8F;AAC9F,sEAAgE;AAChE,4EAAsE;AACtE,sFAAgF;AAChF,gFAA0E;AAC1E,sGAAgG;AAChG,0EAAoE;AACpE,wFAAkF;AAClF,0FAAoF;AACpF,kFAA4E;AAC5E,oFAA8E;AAC9E,kFAA4E;AAC5E,kGAA4F;AAC5F,4CAA2D;AAG3D,0CAA6C;AAE7C,MAAa,KAAM,SAAQ,mBAAS;IAClC;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,UAAU,CACd,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,QAAQ,CACZ,OAAuC,EACvC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,kBAAkB,CACtB,OAAiD,EACjD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0DAA0B,EAC3C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,iBAAiB,CACrB,OAAgD,EAChD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wDAAyB,EAC1C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,eAAe,CACnB,OAA8C,EAC9C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,oDAAuB,EACxC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,wBAAwB,CAC5B,OAAuD,EACvD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sEAAgC,EACjD,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,mBAAmB,CACvB,OAAkD,EAClD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4DAA2B,EAC5C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,SAAS,CACb,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wCAAiB,EAClC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,QAAQ,CACZ,OAAuC,EACvC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAqC,EACrC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kCAAc,EAC/B,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,SAAS,CACb,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wCAAiB,EAClC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,SAAS,CACb,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wCAAiB,EAClC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,kBAAkB,CACtB,OAAiD,EACjD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0DAA0B,EAC3C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,mBAAmB,CACvB,OAAkD,EAClD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4DAA2B,EAC5C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,sBAAsB,CAC1B,OAAqD,EACrD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kEAA8B,EAC/C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,YAAY,CAChB,OAA2C,EAC3C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,8CAAoB,EACrC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,iBAAiB,CACrB,OAAgD,EAChD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,wDAAyB,EAC1C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,uBAAuB,CAC3B,OAAsD,EACtD,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,oEAA+B,EAChD,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,aAAa,CACjB,OAA4C,EAC5C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,gDAAqB,EACtC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,WAAW,CACf,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAA6C,EAC7C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,kDAAsB,EACvC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,eAAe,CACnB,OAA8C,EAC9C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,oDAAuB,EACxC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,gBAAgB,CACpB,OAA+C,EAC/C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sDAAwB,EACzC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;CACF;AAhiBD,sBAgiBC"}
@@ -1,9 +1,20 @@
1
+ import { CreateAcceptEnum } from "../funcs/llmResponsesCreate.js";
1
2
  import { GetAcceptEnum } from "../funcs/llmResponsesGet.js";
2
3
  import { ClientSDK, RequestOptions } from "../lib/sdks.js";
3
4
  import * as components from "../models/components/index.js";
4
5
  import * as operations from "../models/operations/index.js";
6
+ export { CreateAcceptEnum } from "../funcs/llmResponsesCreate.js";
5
7
  export { GetAcceptEnum } from "../funcs/llmResponsesGet.js";
6
8
  export declare class Responses extends ClientSDK {
9
+ /**
10
+ * Create an agent-powered response with tool support
11
+ *
12
+ * @remarks
13
+ * Creates a new AI agent response using advanced language models with autonomous tool usage capabilities.
14
+ */
15
+ create(request: operations.CreateResponseRequest, options?: RequestOptions & {
16
+ acceptHeaderOverride?: CreateAcceptEnum;
17
+ }): Promise<operations.CreateResponseResponse>;
7
18
  /**
8
19
  * List all responses with pagination
9
20
  *
@@ -1 +1 @@
1
- {"version":3,"file":"responses.d.ts","sourceRoot":"","sources":["../../../src/sdk/responses.ts"],"names":[],"mappings":"AAOA,OAAO,EAAE,aAAa,EAAmB,MAAM,6BAA6B,CAAC;AAK7E,OAAO,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAC3D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAG5D,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAE5D,qBAAa,SAAU,SAAQ,SAAS;IACtC;;;;;OAKG;IACG,IAAI,CACR,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kBAAkB,CAAC;IAQzC;;;;;OAKG;IACG,GAAG,CACP,OAAO,EAAE,UAAU,CAAC,kBAAkB,EACtC,OAAO,CAAC,EAAE,cAAc,GAAG;QAAE,oBAAoB,CAAC,EAAE,aAAa,CAAA;KAAE,GAClE,OAAO,CAAC,UAAU,CAAC,mBAAmB,CAAC;IAQ1C;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC;IAQrC;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,oBAAoB,CAAC;IAQ3C;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC;IAQrC;;;;;OAKG;IACG,IAAI,CACR,OAAO,EAAE,UAAU,CAAC,mBAAmB,EACvC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,wBAAwB,CAAC;IAQ/C;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,mBAAmB,CAAC;IAQ1C;;;;;OAKG;IACG,OAAO,CACX,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,iBAAiB,CAAC;CAOzC"}
1
+ {"version":3,"file":"responses.d.ts","sourceRoot":"","sources":["../../../src/sdk/responses.ts"],"names":[],"mappings":"AAMA,OAAO,EACL,gBAAgB,EAEjB,MAAM,gCAAgC,CAAC;AAExC,OAAO,EAAE,aAAa,EAAmB,MAAM,6BAA6B,CAAC;AAK7E,OAAO,EAAE,SAAS,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAC3D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAG5D,OAAO,EAAE,gBAAgB,EAAE,MAAM,gCAAgC,CAAC;AAElE,OAAO,EAAE,aAAa,EAAE,MAAM,6BAA6B,CAAC;AAE5D,qBAAa,SAAU,SAAQ,SAAS;IACtC;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GAAG;QAAE,oBAAoB,CAAC,EAAE,gBAAgB,CAAA;KAAE,GACrE,OAAO,CAAC,UAAU,CAAC,sBAAsB,CAAC;IAQ7C;;;;;OAKG;IACG,IAAI,CACR,OAAO,EAAE,UAAU,CAAC,oBAAoB,EACxC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,kBAAkB,CAAC;IAQzC;;;;;OAKG;IACG,GAAG,CACP,OAAO,EAAE,UAAU,CAAC,kBAAkB,EACtC,OAAO,CAAC,EAAE,cAAc,GAAG;QAAE,oBAAoB,CAAC,EAAE,aAAa,CAAA;KAAE,GAClE,OAAO,CAAC,UAAU,CAAC,mBAAmB,CAAC;IAQ1C;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC;IAQrC;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,oBAAoB,CAAC;IAQ3C;;;;;OAKG;IACG,MAAM,CACV,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,cAAc,CAAC;IAQrC;;;;;OAKG;IACG,IAAI,CACR,OAAO,EAAE,UAAU,CAAC,mBAAmB,EACvC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,wBAAwB,CAAC;IAQ/C;;;;;OAKG;IACG,cAAc,CAClB,OAAO,EAAE,UAAU,CAAC,qBAAqB,EACzC,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,mBAAmB,CAAC;IAQ1C;;;;;OAKG;IACG,OAAO,CACX,OAAO,EAAE,UAAU,CAAC,sBAAsB,EAC1C,OAAO,CAAC,EAAE,cAAc,GACvB,OAAO,CAAC,UAAU,CAAC,iBAAiB,CAAC;CAOzC"}
@@ -3,9 +3,10 @@
3
3
  * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
4
4
  */
5
5
  Object.defineProperty(exports, "__esModule", { value: true });
6
- exports.Responses = exports.GetAcceptEnum = void 0;
6
+ exports.Responses = exports.GetAcceptEnum = exports.CreateAcceptEnum = void 0;
7
7
  const llmResponsesCancel_js_1 = require("../funcs/llmResponsesCancel.js");
8
8
  const llmResponsesCompact_js_1 = require("../funcs/llmResponsesCompact.js");
9
+ const llmResponsesCreate_js_1 = require("../funcs/llmResponsesCreate.js");
9
10
  const llmResponsesDelete_js_1 = require("../funcs/llmResponsesDelete.js");
10
11
  const llmResponsesGet_js_1 = require("../funcs/llmResponsesGet.js");
11
12
  const llmResponsesList_js_1 = require("../funcs/llmResponsesList.js");
@@ -14,9 +15,20 @@ const llmResponsesUpdate_js_1 = require("../funcs/llmResponsesUpdate.js");
14
15
  const llmResponsesWake_js_1 = require("../funcs/llmResponsesWake.js");
15
16
  const sdks_js_1 = require("../lib/sdks.js");
16
17
  const fp_js_1 = require("../types/fp.js");
18
+ var llmResponsesCreate_js_2 = require("../funcs/llmResponsesCreate.js");
19
+ Object.defineProperty(exports, "CreateAcceptEnum", { enumerable: true, get: function () { return llmResponsesCreate_js_2.CreateAcceptEnum; } });
17
20
  var llmResponsesGet_js_2 = require("../funcs/llmResponsesGet.js");
18
21
  Object.defineProperty(exports, "GetAcceptEnum", { enumerable: true, get: function () { return llmResponsesGet_js_2.GetAcceptEnum; } });
19
22
  class Responses extends sdks_js_1.ClientSDK {
23
+ /**
24
+ * Create an agent-powered response with tool support
25
+ *
26
+ * @remarks
27
+ * Creates a new AI agent response using advanced language models with autonomous tool usage capabilities.
28
+ */
29
+ async create(request, options) {
30
+ return (0, fp_js_1.unwrapAsync)((0, llmResponsesCreate_js_1.llmResponsesCreate)(this, request, options));
31
+ }
20
32
  /**
21
33
  * List all responses with pagination
22
34
  *
@@ -1 +1 @@
1
- {"version":3,"file":"responses.js","sourceRoot":"","sources":["../../../src/sdk/responses.ts"],"names":[],"mappings":";AAAA;;GAEG;;;AAEH,0EAAoE;AACpE,4EAAsE;AACtE,0EAAoE;AACpE,oEAA6E;AAC7E,sEAAgE;AAChE,0FAAoF;AACpF,0EAAoE;AACpE,sEAAgE;AAChE,4CAA2D;AAG3D,0CAA6C;AAE7C,kEAA4D;AAAnD,mHAAA,aAAa,OAAA;AAEtB,MAAa,SAAU,SAAQ,mBAAS;IACtC;;;;;OAKG;IACH,KAAK,CAAC,IAAI,CACR,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,GAAG,CACP,OAAsC,EACtC,OAAmE;QAEnE,OAAO,IAAA,mBAAW,EAAC,IAAA,oCAAe,EAChC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,IAAI,CACR,OAAuC,EACvC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0DAA0B,EAC3C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,OAAO,CACX,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;CACF;AAxID,8BAwIC"}
1
+ {"version":3,"file":"responses.js","sourceRoot":"","sources":["../../../src/sdk/responses.ts"],"names":[],"mappings":";AAAA;;GAEG;;;AAEH,0EAAoE;AACpE,4EAAsE;AACtE,0EAGwC;AACxC,0EAAoE;AACpE,oEAA6E;AAC7E,sEAAgE;AAChE,0FAAoF;AACpF,0EAAoE;AACpE,sEAAgE;AAChE,4CAA2D;AAG3D,0CAA6C;AAE7C,wEAAkE;AAAzD,yHAAA,gBAAgB,OAAA;AAEzB,kEAA4D;AAAnD,mHAAA,aAAa,OAAA;AAEtB,MAAa,SAAU,SAAQ,mBAAS;IACtC;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAsE;QAEtE,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,IAAI,CACR,OAAwC,EACxC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,GAAG,CACP,OAAsC,EACtC,OAAmE;QAEnE,OAAO,IAAA,mBAAW,EAAC,IAAA,oCAAe,EAChC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,MAAM,CACV,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0CAAkB,EACnC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,IAAI,CACR,OAAuC,EACvC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,sCAAgB,EACjC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,cAAc,CAClB,OAAyC,EACzC,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,0DAA0B,EAC3C,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;IAED;;;;;OAKG;IACH,KAAK,CAAC,OAAO,CACX,OAA0C,EAC1C,OAAwB;QAExB,OAAO,IAAA,mBAAW,EAAC,IAAA,4CAAmB,EACpC,IAAI,EACJ,OAAO,EACP,OAAO,CACR,CAAC,CAAC;IACL,CAAC;CACF;AAzJD,8BAyJC"}
@@ -0,0 +1,19 @@
1
+ import { SDKCore } from "../core.js";
2
+ import { RequestOptions } from "../lib/sdks.js";
3
+ import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
4
+ import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
5
+ import { SDKError } from "../models/errors/sdkerror.js";
6
+ import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
7
+ import * as operations from "../models/operations/index.js";
8
+ import { APIPromise } from "../types/async.js";
9
+ import { Result } from "../types/fp.js";
10
+ /**
11
+ * Append trials to an open coding-agent run
12
+ *
13
+ * @remarks
14
+ * Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
15
+ *
16
+ * If set, this operation will use {@link Security.bearerAuth} from the global security.
17
+ */
18
+ export declare function llmEvalsAppendAgentTrials(client: SDKCore, request: operations.AppendAgentEvalTrialsRequest, options?: RequestOptions): APIPromise<Result<operations.AppendAgentEvalTrialsResponseBody, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
19
+ //# sourceMappingURL=llmEvalsAppendAgentTrials.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"llmEvalsAppendAgentTrials.d.ts","sourceRoot":"","sources":["../../../src/funcs/llmEvalsAppendAgentTrials.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,OAAO,EAAE,MAAM,YAAY,CAAC;AAMrC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGhD,OAAO,EACL,eAAe,EACf,mBAAmB,EACnB,mBAAmB,EACnB,mBAAmB,EACnB,qBAAqB,EACtB,MAAM,sCAAsC,CAAC;AAC9C,OAAO,EAAE,uBAAuB,EAAE,MAAM,6CAA6C,CAAC;AACtF,OAAO,EAAE,QAAQ,EAAE,MAAM,8BAA8B,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,wCAAwC,CAAC;AAC5E,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AACxD,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AAExC;;;;;;;GAOG;AACH,wBAAgB,yBAAyB,CACvC,MAAM,EAAE,OAAO,EACf,OAAO,EAAE,UAAU,CAAC,4BAA4B,EAChD,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CACX,MAAM,CACJ,UAAU,CAAC,iCAAiC,EAC1C,QAAQ,GACR,uBAAuB,GACvB,eAAe,GACf,mBAAmB,GACnB,mBAAmB,GACnB,mBAAmB,GACnB,qBAAqB,GACrB,kBAAkB,CACrB,CACF,CAMA"}
@@ -0,0 +1,100 @@
1
+ /*
2
+ * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
3
+ */
4
+ import { encodeJSON, encodeSimple } from "../lib/encodings.js";
5
+ import { matchStatusCode } from "../lib/http.js";
6
+ import * as M from "../lib/matchers.js";
7
+ import { compactMap } from "../lib/primitives.js";
8
+ import { safeParse } from "../lib/schemas.js";
9
+ import { extractSecurity, resolveGlobalSecurity } from "../lib/security.js";
10
+ import { pathToFunc } from "../lib/url.js";
11
+ import * as operations from "../models/operations/index.js";
12
+ import { APIPromise } from "../types/async.js";
13
+ /**
14
+ * Append trials to an open coding-agent run
15
+ *
16
+ * @remarks
17
+ * Adds finished trials to a run opened with `finalize: false`, so a job started from MKA1 can be watched while it runs instead of appearing complete out of nowhere at the end. Each trial pins its own `sample_index` and upserts on (task, model, sample_index): a harness cannot tell a timeout from a lost response, so re-sending a batch is safe and replaces rather than duplicates. The whole batch and its aggregate recompute land in one transaction, serialized per run. Counts, metrics and cost are recomputed from the stored rows on every call, never accumulated from the request, so a replayed batch cannot double them. Send `finalize: true` (usually with an empty `trials`) to close the run — until then it stays `in_progress` and off the leaderboards, which only count completed runs. Appending to an already-completed or cancelled run is rejected: that record is finished, and rewriting it would silently move a number someone may have already read.
18
+ *
19
+ * If set, this operation will use {@link Security.bearerAuth} from the global security.
20
+ */
21
+ export function llmEvalsAppendAgentTrials(client, request, options) {
22
+ return new APIPromise($do(client, request, options));
23
+ }
24
+ async function $do(client, request, options) {
25
+ const parsed = safeParse(request, (value) => operations.AppendAgentEvalTrialsRequest$outboundSchema.parse(value), "Input validation failed");
26
+ if (!parsed.ok) {
27
+ return [parsed, { status: "invalid" }];
28
+ }
29
+ const payload = parsed.value;
30
+ const body = encodeJSON("body", payload.AppendAgentTrialsRequest, {
31
+ explode: true,
32
+ });
33
+ const pathParams = {
34
+ run_id: encodeSimple("run_id", payload.run_id, {
35
+ explode: false,
36
+ charEncoding: "percent",
37
+ }),
38
+ };
39
+ const path = pathToFunc("/api/v1/llm/evals/runs/{run_id}/trials")(pathParams);
40
+ const headers = new Headers(compactMap({
41
+ "Content-Type": "application/json",
42
+ Accept: "application/json",
43
+ "X-On-Behalf-Of": encodeSimple("X-On-Behalf-Of", payload["X-On-Behalf-Of"], { explode: false, charEncoding: "none" }),
44
+ }));
45
+ const secConfig = await extractSecurity(client._options.bearerAuth);
46
+ const securityInput = secConfig == null ? {} : { bearerAuth: secConfig };
47
+ const requestSecurity = resolveGlobalSecurity(securityInput, [0]);
48
+ const context = {
49
+ options: client._options,
50
+ baseURL: options?.serverURL ?? client._baseURL ?? "",
51
+ operationID: "appendAgentEvalTrials",
52
+ oAuth2Scopes: null,
53
+ resolvedSecurity: requestSecurity,
54
+ securitySource: client._options.bearerAuth,
55
+ retryConfig: options?.retries
56
+ || client._options.retryConfig
57
+ || {
58
+ strategy: "backoff",
59
+ backoff: {
60
+ initialInterval: 500,
61
+ maxInterval: 5000,
62
+ exponent: 1.5,
63
+ maxElapsedTime: 15000,
64
+ },
65
+ retryConnectionErrors: true,
66
+ }
67
+ || { strategy: "none" },
68
+ retryCodes: options?.retryCodes || ["429", "500", "502", "503", "504"],
69
+ };
70
+ const requestRes = client._createRequest(context, {
71
+ security: requestSecurity,
72
+ method: "POST",
73
+ baseURL: options?.serverURL,
74
+ path: path,
75
+ headers: headers,
76
+ body: body,
77
+ userAgent: client._options.userAgent,
78
+ timeoutMs: options?.timeoutMs || client._options.timeoutMs || -1,
79
+ }, options);
80
+ if (!requestRes.ok) {
81
+ return [requestRes, { status: "invalid" }];
82
+ }
83
+ const req = requestRes.value;
84
+ const doResult = await client._do(req, {
85
+ context,
86
+ isErrorStatusCode: (statusCode) => matchStatusCode({ status: statusCode }, ["4XX", "5XX"]),
87
+ retryConfig: context.retryConfig,
88
+ retryCodes: context.retryCodes,
89
+ });
90
+ if (!doResult.ok) {
91
+ return [doResult, { status: "request-error", request: req }];
92
+ }
93
+ const response = doResult.value;
94
+ const [result] = await M.match(M.json(200, operations.AppendAgentEvalTrialsResponseBody$inboundSchema), M.fail("4XX"), M.fail("5XX"))(response, req);
95
+ if (!result.ok) {
96
+ return [result, { status: "complete", request: req, response }];
97
+ }
98
+ return [result, { status: "complete", request: req, response }];
99
+ }
100
+ //# sourceMappingURL=llmEvalsAppendAgentTrials.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"llmEvalsAppendAgentTrials.js","sourceRoot":"","sources":["../../../src/funcs/llmEvalsAppendAgentTrials.ts"],"names":[],"mappings":"AAAA;;GAEG;AAGH,OAAO,EAAE,UAAU,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAC;AAC/D,OAAO,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AACjD,OAAO,KAAK,CAAC,MAAM,oBAAoB,CAAC;AACxC,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAC;AAClD,OAAO,EAAE,SAAS,EAAE,MAAM,mBAAmB,CAAC;AAE9C,OAAO,EAAE,eAAe,EAAE,qBAAqB,EAAE,MAAM,oBAAoB,CAAC;AAC5E,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAW3C,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAGxD;;;;;;;GAOG;AACH,MAAM,UAAU,yBAAyB,CACvC,MAAe,EACf,OAAgD,EAChD,OAAwB;IAcxB,OAAO,IAAI,UAAU,CAAC,GAAG,CACvB,MAAM,EACN,OAAO,EACP,OAAO,CACR,CAAC,CAAC;AACL,CAAC;AAED,KAAK,UAAU,GAAG,CAChB,MAAe,EACf,OAAgD,EAChD,OAAwB;IAiBxB,MAAM,MAAM,GAAG,SAAS,CACtB,OAAO,EACP,CAAC,KAAK,EAAE,EAAE,CACR,UAAU,CAAC,2CAA2C,CAAC,KAAK,CAAC,KAAK,CAAC,EACrE,yBAAyB,CAC1B,CAAC;IACF,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IACzC,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAC;IAC7B,MAAM,IAAI,GAAG,UAAU,CAAC,MAAM,EAAE,OAAO,CAAC,wBAAwB,EAAE;QAChE,OAAO,EAAE,IAAI;KACd,CAAC,CAAC;IAEH,MAAM,UAAU,GAAG;QACjB,MAAM,EAAE,YAAY,CAAC,QAAQ,EAAE,OAAO,CAAC,MAAM,EAAE;YAC7C,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,SAAS;SACxB,CAAC;KACH,CAAC;IACF,MAAM,IAAI,GAAG,UAAU,CAAC,wCAAwC,CAAC,CAAC,UAAU,CAAC,CAAC;IAE9E,MAAM,OAAO,GAAG,IAAI,OAAO,CAAC,UAAU,CAAC;QACrC,cAAc,EAAE,kBAAkB;QAClC,MAAM,EAAE,kBAAkB;QAC1B,gBAAgB,EAAE,YAAY,CAC5B,gBAAgB,EAChB,OAAO,CAAC,gBAAgB,CAAC,EACzB,EAAE,OAAO,EAAE,KAAK,EAAE,YAAY,EAAE,MAAM,EAAE,CACzC;KACF,CAAC,CAAC,CAAC;IAEJ,MAAM,SAAS,GAAG,MAAM,eAAe,CAAC,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;IACpE,MAAM,aAAa,GAAG,SAAS,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,SAAS,EAAE,CAAC;IACzE,MAAM,eAAe,GAAG,qBAAqB,CAAC,aAAa,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IAElE,MAAM,OAAO,GAAG;QACd,OAAO,EAAE,MAAM,CAAC,QAAQ;QACxB,OAAO,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,IAAI,EAAE;QACpD,WAAW,EAAE,uBAAuB;QACpC,YAAY,EAAE,IAAI;QAElB,gBAAgB,EAAE,eAAe;QAEjC,cAAc,EAAE,MAAM,CAAC,QAAQ,CAAC,UAAU;QAC1C,WAAW,EAAE,OAAO,EAAE,OAAO;eACxB,MAAM,CAAC,QAAQ,CAAC,WAAW;eAC3B;gBACD,QAAQ,EAAE,SAAS;gBACnB,OAAO,EAAE;oBACP,eAAe,EAAE,GAAG;oBACpB,WAAW,EAAE,IAAI;oBACjB,QAAQ,EAAE,GAAG;oBACb,cAAc,EAAE,KAAK;iBACtB;gBACD,qBAAqB,EAAE,IAAI;aAC5B;eACE,EAAE,QAAQ,EAAE,MAAM,EAAE;QACzB,UAAU,EAAE,OAAO,EAAE,UAAU,IAAI,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC;KACvE,CAAC;IAEF,MAAM,UAAU,GAAG,MAAM,CAAC,cAAc,CAAC,OAAO,EAAE;QAChD,QAAQ,EAAE,eAAe;QACzB,MAAM,EAAE,MAAM;QACd,OAAO,EAAE,OAAO,EAAE,SAAS;QAC3B,IAAI,EAAE,IAAI;QACV,OAAO,EAAE,OAAO;QAChB,IAAI,EAAE,IAAI;QACV,SAAS,EAAE,MAAM,CAAC,QAAQ,CAAC,SAAS;QACpC,SAAS,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,CAAC,SAAS,IAAI,CAAC,CAAC;KACjE,EAAE,OAAO,CAAC,CAAC;IACZ,IAAI,CAAC,UAAU,CAAC,EAAE,EAAE,CAAC;QACnB,OAAO,CAAC,UAAU,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,CAAC;IACD,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC;IAE7B,MAAM,QAAQ,GAAG,MAAM,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE;QACrC,OAAO;QACP,iBAAiB,EAAE,CAAC,UAAkB,EAAE,EAAE,CACxC,eAAe,CAAC,EAAE,MAAM,EAAE,UAAU,EAAc,EAAE,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACrE,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,UAAU,EAAE,OAAO,CAAC,UAAU;KAC/B,CAAC,CAAC;IACH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,OAAO,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,GAAG,EAAE,CAAC,CAAC;IAC/D,CAAC;IACD,MAAM,QAAQ,GAAG,QAAQ,CAAC,KAAK,CAAC;IAEhC,MAAM,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,KAAK,CAW5B,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,UAAU,CAAC,+CAA+C,CAAC,EACvE,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EACb,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CACd,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACjB,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;AAClE,CAAC"}
@@ -0,0 +1,20 @@
1
+ import { SDKCore } from "../core.js";
2
+ import { RequestOptions } from "../lib/sdks.js";
3
+ import * as components from "../models/components/index.js";
4
+ import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
5
+ import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
6
+ import { SDKError } from "../models/errors/sdkerror.js";
7
+ import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
8
+ import * as operations from "../models/operations/index.js";
9
+ import { APIPromise } from "../types/async.js";
10
+ import { Result } from "../types/fp.js";
11
+ /**
12
+ * Get an eval run overview
13
+ *
14
+ * @remarks
15
+ * Aggregate header for one run's trials view: trial counts, average reward, cost, and the input/output/cached token split. Its own route rather than fields on the run object because it scans the run's samples — folding it into `GET /evals/runs/{run_id}` would charge that scan to every run list and to the status polling that runs for the whole length of an eval. `trials.errored` overlaps `trials.failed` instead of partitioning it: a coding-agent trial can carry an agent timeout in `error` and still be completed and scored. `trials.retried` counts trials rerun through rerun-failed, read from the pre-rerun snapshot, since a rerun overwrites the sample in place.
16
+ *
17
+ * If set, this operation will use {@link Security.bearerAuth} from the global security.
18
+ */
19
+ export declare function llmEvalsGetRunOverview(client: SDKCore, request: operations.GetEvalRunOverviewRequest, options?: RequestOptions): APIPromise<Result<components.EvalRunOverview, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
20
+ //# sourceMappingURL=llmEvalsGetRunOverview.d.ts.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"llmEvalsGetRunOverview.d.ts","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetRunOverview.ts"],"names":[],"mappings":"AAIA,OAAO,EAAE,OAAO,EAAE,MAAM,YAAY,CAAC;AAMrC,OAAO,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGhD,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EACL,eAAe,EACf,mBAAmB,EACnB,mBAAmB,EACnB,mBAAmB,EACnB,qBAAqB,EACtB,MAAM,sCAAsC,CAAC;AAC9C,OAAO,EAAE,uBAAuB,EAAE,MAAM,6CAA6C,CAAC;AACtF,OAAO,EAAE,QAAQ,EAAE,MAAM,8BAA8B,CAAC;AACxD,OAAO,EAAE,kBAAkB,EAAE,MAAM,wCAAwC,CAAC;AAC5E,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AACxD,OAAO,EAAE,MAAM,EAAE,MAAM,gBAAgB,CAAC;AAExC;;;;;;;GAOG;AACH,wBAAgB,sBAAsB,CACpC,MAAM,EAAE,OAAO,EACf,OAAO,EAAE,UAAU,CAAC,yBAAyB,EAC7C,OAAO,CAAC,EAAE,cAAc,GACvB,UAAU,CACX,MAAM,CACJ,UAAU,CAAC,eAAe,EACxB,QAAQ,GACR,uBAAuB,GACvB,eAAe,GACf,mBAAmB,GACnB,mBAAmB,GACnB,mBAAmB,GACnB,qBAAqB,GACrB,kBAAkB,CACrB,CACF,CAMA"}
@@ -0,0 +1,102 @@
1
+ /*
2
+ * Code generated by Speakeasy (https://speakeasy.com). DO NOT EDIT.
3
+ */
4
+ import { encodeFormQuery, encodeSimple } from "../lib/encodings.js";
5
+ import { matchStatusCode } from "../lib/http.js";
6
+ import * as M from "../lib/matchers.js";
7
+ import { compactMap } from "../lib/primitives.js";
8
+ import { safeParse } from "../lib/schemas.js";
9
+ import { extractSecurity, resolveGlobalSecurity } from "../lib/security.js";
10
+ import { pathToFunc } from "../lib/url.js";
11
+ import * as components from "../models/components/index.js";
12
+ import * as operations from "../models/operations/index.js";
13
+ import { APIPromise } from "../types/async.js";
14
+ /**
15
+ * Get an eval run overview
16
+ *
17
+ * @remarks
18
+ * Aggregate header for one run's trials view: trial counts, average reward, cost, and the input/output/cached token split. Its own route rather than fields on the run object because it scans the run's samples — folding it into `GET /evals/runs/{run_id}` would charge that scan to every run list and to the status polling that runs for the whole length of an eval. `trials.errored` overlaps `trials.failed` instead of partitioning it: a coding-agent trial can carry an agent timeout in `error` and still be completed and scored. `trials.retried` counts trials rerun through rerun-failed, read from the pre-rerun snapshot, since a rerun overwrites the sample in place.
19
+ *
20
+ * If set, this operation will use {@link Security.bearerAuth} from the global security.
21
+ */
22
+ export function llmEvalsGetRunOverview(client, request, options) {
23
+ return new APIPromise($do(client, request, options));
24
+ }
25
+ async function $do(client, request, options) {
26
+ const parsed = safeParse(request, (value) => operations.GetEvalRunOverviewRequest$outboundSchema.parse(value), "Input validation failed");
27
+ if (!parsed.ok) {
28
+ return [parsed, { status: "invalid" }];
29
+ }
30
+ const payload = parsed.value;
31
+ const body = null;
32
+ const pathParams = {
33
+ run_id: encodeSimple("run_id", payload.run_id, {
34
+ explode: false,
35
+ charEncoding: "percent",
36
+ }),
37
+ };
38
+ const path = pathToFunc("/api/v1/llm/evals/runs/{run_id}/overview")(pathParams);
39
+ const query = encodeFormQuery({
40
+ "metric": payload.metric,
41
+ });
42
+ const headers = new Headers(compactMap({
43
+ Accept: "application/json",
44
+ "X-On-Behalf-Of": encodeSimple("X-On-Behalf-Of", payload["X-On-Behalf-Of"], { explode: false, charEncoding: "none" }),
45
+ }));
46
+ const secConfig = await extractSecurity(client._options.bearerAuth);
47
+ const securityInput = secConfig == null ? {} : { bearerAuth: secConfig };
48
+ const requestSecurity = resolveGlobalSecurity(securityInput, [0]);
49
+ const context = {
50
+ options: client._options,
51
+ baseURL: options?.serverURL ?? client._baseURL ?? "",
52
+ operationID: "getEvalRunOverview",
53
+ oAuth2Scopes: null,
54
+ resolvedSecurity: requestSecurity,
55
+ securitySource: client._options.bearerAuth,
56
+ retryConfig: options?.retries
57
+ || client._options.retryConfig
58
+ || {
59
+ strategy: "backoff",
60
+ backoff: {
61
+ initialInterval: 500,
62
+ maxInterval: 5000,
63
+ exponent: 1.5,
64
+ maxElapsedTime: 15000,
65
+ },
66
+ retryConnectionErrors: true,
67
+ }
68
+ || { strategy: "none" },
69
+ retryCodes: options?.retryCodes || ["429", "500", "502", "503", "504"],
70
+ };
71
+ const requestRes = client._createRequest(context, {
72
+ security: requestSecurity,
73
+ method: "GET",
74
+ baseURL: options?.serverURL,
75
+ path: path,
76
+ headers: headers,
77
+ query: query,
78
+ body: body,
79
+ userAgent: client._options.userAgent,
80
+ timeoutMs: options?.timeoutMs || client._options.timeoutMs || -1,
81
+ }, options);
82
+ if (!requestRes.ok) {
83
+ return [requestRes, { status: "invalid" }];
84
+ }
85
+ const req = requestRes.value;
86
+ const doResult = await client._do(req, {
87
+ context,
88
+ isErrorStatusCode: (statusCode) => matchStatusCode({ status: statusCode }, ["4XX", "5XX"]),
89
+ retryConfig: context.retryConfig,
90
+ retryCodes: context.retryCodes,
91
+ });
92
+ if (!doResult.ok) {
93
+ return [doResult, { status: "request-error", request: req }];
94
+ }
95
+ const response = doResult.value;
96
+ const [result] = await M.match(M.json(200, components.EvalRunOverview$inboundSchema), M.fail("4XX"), M.fail("5XX"))(response, req);
97
+ if (!result.ok) {
98
+ return [result, { status: "complete", request: req, response }];
99
+ }
100
+ return [result, { status: "complete", request: req, response }];
101
+ }
102
+ //# sourceMappingURL=llmEvalsGetRunOverview.js.map
@@ -0,0 +1 @@
1
+ {"version":3,"file":"llmEvalsGetRunOverview.js","sourceRoot":"","sources":["../../../src/funcs/llmEvalsGetRunOverview.ts"],"names":[],"mappings":"AAAA;;GAEG;AAGH,OAAO,EAAE,eAAe,EAAE,YAAY,EAAE,MAAM,qBAAqB,CAAC;AACpE,OAAO,EAAE,eAAe,EAAE,MAAM,gBAAgB,CAAC;AACjD,OAAO,KAAK,CAAC,MAAM,oBAAoB,CAAC;AACxC,OAAO,EAAE,UAAU,EAAE,MAAM,sBAAsB,CAAC;AAClD,OAAO,EAAE,SAAS,EAAE,MAAM,mBAAmB,CAAC;AAE9C,OAAO,EAAE,eAAe,EAAE,qBAAqB,EAAE,MAAM,oBAAoB,CAAC;AAC5E,OAAO,EAAE,UAAU,EAAE,MAAM,eAAe,CAAC;AAC3C,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAW5D,OAAO,KAAK,UAAU,MAAM,+BAA+B,CAAC;AAC5D,OAAO,EAAW,UAAU,EAAE,MAAM,mBAAmB,CAAC;AAGxD;;;;;;;GAOG;AACH,MAAM,UAAU,sBAAsB,CACpC,MAAe,EACf,OAA6C,EAC7C,OAAwB;IAcxB,OAAO,IAAI,UAAU,CAAC,GAAG,CACvB,MAAM,EACN,OAAO,EACP,OAAO,CACR,CAAC,CAAC;AACL,CAAC;AAED,KAAK,UAAU,GAAG,CAChB,MAAe,EACf,OAA6C,EAC7C,OAAwB;IAiBxB,MAAM,MAAM,GAAG,SAAS,CACtB,OAAO,EACP,CAAC,KAAK,EAAE,EAAE,CAAC,UAAU,CAAC,wCAAwC,CAAC,KAAK,CAAC,KAAK,CAAC,EAC3E,yBAAyB,CAC1B,CAAC;IACF,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IACzC,CAAC;IACD,MAAM,OAAO,GAAG,MAAM,CAAC,KAAK,CAAC;IAC7B,MAAM,IAAI,GAAG,IAAI,CAAC;IAElB,MAAM,UAAU,GAAG;QACjB,MAAM,EAAE,YAAY,CAAC,QAAQ,EAAE,OAAO,CAAC,MAAM,EAAE;YAC7C,OAAO,EAAE,KAAK;YACd,YAAY,EAAE,SAAS;SACxB,CAAC;KACH,CAAC;IACF,MAAM,IAAI,GAAG,UAAU,CAAC,0CAA0C,CAAC,CACjE,UAAU,CACX,CAAC;IAEF,MAAM,KAAK,GAAG,eAAe,CAAC;QAC5B,QAAQ,EAAE,OAAO,CAAC,MAAM;KACzB,CAAC,CAAC;IAEH,MAAM,OAAO,GAAG,IAAI,OAAO,CAAC,UAAU,CAAC;QACrC,MAAM,EAAE,kBAAkB;QAC1B,gBAAgB,EAAE,YAAY,CAC5B,gBAAgB,EAChB,OAAO,CAAC,gBAAgB,CAAC,EACzB,EAAE,OAAO,EAAE,KAAK,EAAE,YAAY,EAAE,MAAM,EAAE,CACzC;KACF,CAAC,CAAC,CAAC;IAEJ,MAAM,SAAS,GAAG,MAAM,eAAe,CAAC,MAAM,CAAC,QAAQ,CAAC,UAAU,CAAC,CAAC;IACpE,MAAM,aAAa,GAAG,SAAS,IAAI,IAAI,CAAC,CAAC,CAAC,EAAE,CAAC,CAAC,CAAC,EAAE,UAAU,EAAE,SAAS,EAAE,CAAC;IACzE,MAAM,eAAe,GAAG,qBAAqB,CAAC,aAAa,EAAE,CAAC,CAAC,CAAC,CAAC,CAAC;IAElE,MAAM,OAAO,GAAG;QACd,OAAO,EAAE,MAAM,CAAC,QAAQ;QACxB,OAAO,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,IAAI,EAAE;QACpD,WAAW,EAAE,oBAAoB;QACjC,YAAY,EAAE,IAAI;QAElB,gBAAgB,EAAE,eAAe;QAEjC,cAAc,EAAE,MAAM,CAAC,QAAQ,CAAC,UAAU;QAC1C,WAAW,EAAE,OAAO,EAAE,OAAO;eACxB,MAAM,CAAC,QAAQ,CAAC,WAAW;eAC3B;gBACD,QAAQ,EAAE,SAAS;gBACnB,OAAO,EAAE;oBACP,eAAe,EAAE,GAAG;oBACpB,WAAW,EAAE,IAAI;oBACjB,QAAQ,EAAE,GAAG;oBACb,cAAc,EAAE,KAAK;iBACtB;gBACD,qBAAqB,EAAE,IAAI;aAC5B;eACE,EAAE,QAAQ,EAAE,MAAM,EAAE;QACzB,UAAU,EAAE,OAAO,EAAE,UAAU,IAAI,CAAC,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,EAAE,KAAK,CAAC;KACvE,CAAC;IAEF,MAAM,UAAU,GAAG,MAAM,CAAC,cAAc,CAAC,OAAO,EAAE;QAChD,QAAQ,EAAE,eAAe;QACzB,MAAM,EAAE,KAAK;QACb,OAAO,EAAE,OAAO,EAAE,SAAS;QAC3B,IAAI,EAAE,IAAI;QACV,OAAO,EAAE,OAAO;QAChB,KAAK,EAAE,KAAK;QACZ,IAAI,EAAE,IAAI;QACV,SAAS,EAAE,MAAM,CAAC,QAAQ,CAAC,SAAS;QACpC,SAAS,EAAE,OAAO,EAAE,SAAS,IAAI,MAAM,CAAC,QAAQ,CAAC,SAAS,IAAI,CAAC,CAAC;KACjE,EAAE,OAAO,CAAC,CAAC;IACZ,IAAI,CAAC,UAAU,CAAC,EAAE,EAAE,CAAC;QACnB,OAAO,CAAC,UAAU,EAAE,EAAE,MAAM,EAAE,SAAS,EAAE,CAAC,CAAC;IAC7C,CAAC;IACD,MAAM,GAAG,GAAG,UAAU,CAAC,KAAK,CAAC;IAE7B,MAAM,QAAQ,GAAG,MAAM,MAAM,CAAC,GAAG,CAAC,GAAG,EAAE;QACrC,OAAO;QACP,iBAAiB,EAAE,CAAC,UAAkB,EAAE,EAAE,CACxC,eAAe,CAAC,EAAE,MAAM,EAAE,UAAU,EAAc,EAAE,CAAC,KAAK,EAAE,KAAK,CAAC,CAAC;QACrE,WAAW,EAAE,OAAO,CAAC,WAAW;QAChC,UAAU,EAAE,OAAO,CAAC,UAAU;KAC/B,CAAC,CAAC;IACH,IAAI,CAAC,QAAQ,CAAC,EAAE,EAAE,CAAC;QACjB,OAAO,CAAC,QAAQ,EAAE,EAAE,MAAM,EAAE,eAAe,EAAE,OAAO,EAAE,GAAG,EAAE,CAAC,CAAC;IAC/D,CAAC;IACD,MAAM,QAAQ,GAAG,QAAQ,CAAC,KAAK,CAAC;IAEhC,MAAM,CAAC,MAAM,CAAC,GAAG,MAAM,CAAC,CAAC,KAAK,CAW5B,CAAC,CAAC,IAAI,CAAC,GAAG,EAAE,UAAU,CAAC,6BAA6B,CAAC,EACrD,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,EACb,CAAC,CAAC,IAAI,CAAC,KAAK,CAAC,CACd,CAAC,QAAQ,EAAE,GAAG,CAAC,CAAC;IACjB,IAAI,CAAC,MAAM,CAAC,EAAE,EAAE,CAAC;QACf,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;IAClE,CAAC;IAED,OAAO,CAAC,MAAM,EAAE,EAAE,MAAM,EAAE,UAAU,EAAE,OAAO,EAAE,GAAG,EAAE,QAAQ,EAAE,CAAC,CAAC;AAClE,CAAC"}
@@ -0,0 +1,19 @@
1
+ import { SDKCore } from "../core.js";
2
+ import { RequestOptions } from "../lib/sdks.js";
3
+ import { ConnectionError, InvalidRequestError, RequestAbortedError, RequestTimeoutError, UnexpectedClientError } from "../models/errors/httpclienterrors.js";
4
+ import { ResponseValidationError } from "../models/errors/responsevalidationerror.js";
5
+ import { SDKError } from "../models/errors/sdkerror.js";
6
+ import { SDKValidationError } from "../models/errors/sdkvalidationerror.js";
7
+ import * as operations from "../models/operations/index.js";
8
+ import { APIPromise } from "../types/async.js";
9
+ import { Result } from "../types/fp.js";
10
+ /**
11
+ * Get an eval sample trajectory
12
+ *
13
+ * @remarks
14
+ * Returns one coding-agent trial's session — the steps the agent took, verbatim in the harness's interchange format (see `schema_version`, e.g. `ATIF-v1.7`). Deliberately not part of the samples list: a trajectory averages ~92 KB and that list pages up to 500 rows. Sample indices are unique per (task, model), not per run, so pass `task_id` and/or `model` when the run covers more than one; an index that matches several trials returns 400 rather than guessing, and never falls back to another trial's session. Returns 404 when the sample does not exist or recorded no trajectory.
15
+ *
16
+ * If set, this operation will use {@link Security.bearerAuth} from the global security.
17
+ */
18
+ export declare function llmEvalsGetSampleTrajectory(client: SDKCore, request: operations.GetEvalSampleTrajectoryRequest, options?: RequestOptions): APIPromise<Result<operations.GetEvalSampleTrajectoryResponseBody, SDKError | ResponseValidationError | ConnectionError | RequestAbortedError | RequestTimeoutError | InvalidRequestError | UnexpectedClientError | SDKValidationError>>;
19
+ //# sourceMappingURL=llmEvalsGetSampleTrajectory.d.ts.map