@terreno/admin-frontend 57.21.0 → 57.22.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (308) hide show
  1. package/CHANGELOG.md +31 -0
  2. package/dist/index.d.ts +1 -1
  3. package/dist/index.d.ts.map +1 -1
  4. package/dist/index.js +1 -1
  5. package/dist/index.js.map +1 -1
  6. package/dist/widgets/aiObservability/datasets/AiDatasetsListScreen.d.ts.map +1 -1
  7. package/dist/widgets/aiObservability/datasets/AiDatasetsListScreen.js +19 -9
  8. package/dist/widgets/aiObservability/datasets/AiDatasetsListScreen.js.map +1 -1
  9. package/dist/widgets/aiObservability/datasets/AiDatasetsListView.d.ts +7 -2
  10. package/dist/widgets/aiObservability/datasets/AiDatasetsListView.d.ts.map +1 -1
  11. package/dist/widgets/aiObservability/datasets/AiDatasetsListView.js +155 -43
  12. package/dist/widgets/aiObservability/datasets/AiDatasetsListView.js.map +1 -1
  13. package/dist/widgets/aiObservability/datasets/datasetTypes.d.ts +20 -1
  14. package/dist/widgets/aiObservability/datasets/datasetTypes.d.ts.map +1 -1
  15. package/dist/widgets/aiObservability/datasets/datasetTypes.js +17 -12
  16. package/dist/widgets/aiObservability/datasets/datasetTypes.js.map +1 -1
  17. package/dist/widgets/aiObservability/evaluators/AiEvaluatorDetailScreen.d.ts.map +1 -1
  18. package/dist/widgets/aiObservability/evaluators/AiEvaluatorDetailScreen.js +12 -8
  19. package/dist/widgets/aiObservability/evaluators/AiEvaluatorDetailScreen.js.map +1 -1
  20. package/dist/widgets/aiObservability/evaluators/AiEvaluatorNewScreen.d.ts.map +1 -1
  21. package/dist/widgets/aiObservability/evaluators/AiEvaluatorNewScreen.js +4 -1
  22. package/dist/widgets/aiObservability/evaluators/AiEvaluatorNewScreen.js.map +1 -1
  23. package/dist/widgets/aiObservability/evaluators/AiEvaluatorPanels.d.ts +8 -0
  24. package/dist/widgets/aiObservability/evaluators/AiEvaluatorPanels.d.ts.map +1 -1
  25. package/dist/widgets/aiObservability/evaluators/AiEvaluatorPanels.js +68 -37
  26. package/dist/widgets/aiObservability/evaluators/AiEvaluatorPanels.js.map +1 -1
  27. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListScreen.d.ts.map +1 -1
  28. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListScreen.js +4 -2
  29. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListScreen.js.map +1 -1
  30. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListView.d.ts +8 -0
  31. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListView.d.ts.map +1 -1
  32. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListView.js +156 -33
  33. package/dist/widgets/aiObservability/evaluators/AiEvaluatorsListView.js.map +1 -1
  34. package/dist/widgets/aiObservability/evaluators/evaluatorTypes.d.ts +32 -0
  35. package/dist/widgets/aiObservability/evaluators/evaluatorTypes.d.ts.map +1 -1
  36. package/dist/widgets/aiObservability/evaluators/evaluatorTypes.js +49 -0
  37. package/dist/widgets/aiObservability/evaluators/evaluatorTypes.js.map +1 -1
  38. package/dist/widgets/aiObservability/experiments/AiExperimentNewScreen.d.ts.map +1 -1
  39. package/dist/widgets/aiObservability/experiments/AiExperimentNewScreen.js +235 -12
  40. package/dist/widgets/aiObservability/experiments/AiExperimentNewScreen.js.map +1 -1
  41. package/dist/widgets/aiObservability/experiments/AiExperimentNewView.d.ts +10 -1
  42. package/dist/widgets/aiObservability/experiments/AiExperimentNewView.d.ts.map +1 -1
  43. package/dist/widgets/aiObservability/experiments/AiExperimentNewView.js +113 -56
  44. package/dist/widgets/aiObservability/experiments/AiExperimentNewView.js.map +1 -1
  45. package/dist/widgets/aiObservability/experiments/AiExperimentResultsScreen.d.ts.map +1 -1
  46. package/dist/widgets/aiObservability/experiments/AiExperimentResultsScreen.js +53 -38
  47. package/dist/widgets/aiObservability/experiments/AiExperimentResultsScreen.js.map +1 -1
  48. package/dist/widgets/aiObservability/experiments/AiExperimentResultsView.d.ts +2 -3
  49. package/dist/widgets/aiObservability/experiments/AiExperimentResultsView.d.ts.map +1 -1
  50. package/dist/widgets/aiObservability/experiments/AiExperimentResultsView.js +117 -32
  51. package/dist/widgets/aiObservability/experiments/AiExperimentResultsView.js.map +1 -1
  52. package/dist/widgets/aiObservability/experiments/AiExperimentsListScreen.d.ts.map +1 -1
  53. package/dist/widgets/aiObservability/experiments/AiExperimentsListScreen.js +13 -4
  54. package/dist/widgets/aiObservability/experiments/AiExperimentsListScreen.js.map +1 -1
  55. package/dist/widgets/aiObservability/experiments/AiExperimentsListView.d.ts +5 -0
  56. package/dist/widgets/aiObservability/experiments/AiExperimentsListView.d.ts.map +1 -1
  57. package/dist/widgets/aiObservability/experiments/AiExperimentsListView.js +157 -55
  58. package/dist/widgets/aiObservability/experiments/AiExperimentsListView.js.map +1 -1
  59. package/dist/widgets/aiObservability/experiments/AiJudgeExperimentSteps.d.ts +41 -0
  60. package/dist/widgets/aiObservability/experiments/AiJudgeExperimentSteps.d.ts.map +1 -0
  61. package/dist/widgets/aiObservability/experiments/AiJudgeExperimentSteps.js +113 -0
  62. package/dist/widgets/aiObservability/experiments/AiJudgeExperimentSteps.js.map +1 -0
  63. package/dist/widgets/aiObservability/experiments/ExperimentWizard.d.ts +30 -0
  64. package/dist/widgets/aiObservability/experiments/ExperimentWizard.d.ts.map +1 -0
  65. package/dist/widgets/aiObservability/experiments/ExperimentWizard.js +29 -0
  66. package/dist/widgets/aiObservability/experiments/ExperimentWizard.js.map +1 -0
  67. package/dist/widgets/aiObservability/experiments/experimentTypes.d.ts +82 -3
  68. package/dist/widgets/aiObservability/experiments/experimentTypes.d.ts.map +1 -1
  69. package/dist/widgets/aiObservability/experiments/experimentTypes.js +172 -6
  70. package/dist/widgets/aiObservability/experiments/experimentTypes.js.map +1 -1
  71. package/dist/widgets/aiObservability/experiments/useAiObservabilityExperimentsApi.d.ts +34 -4
  72. package/dist/widgets/aiObservability/experiments/useAiObservabilityExperimentsApi.d.ts.map +1 -1
  73. package/dist/widgets/aiObservability/experiments/useAiObservabilityExperimentsApi.js +11 -4
  74. package/dist/widgets/aiObservability/experiments/useAiObservabilityExperimentsApi.js.map +1 -1
  75. package/dist/widgets/aiObservability/prompts/AiPromptEditorScreen.d.ts.map +1 -1
  76. package/dist/widgets/aiObservability/prompts/AiPromptEditorScreen.js +24 -5
  77. package/dist/widgets/aiObservability/prompts/AiPromptEditorScreen.js.map +1 -1
  78. package/dist/widgets/aiObservability/prompts/AiPromptEditorView.d.ts +2 -0
  79. package/dist/widgets/aiObservability/prompts/AiPromptEditorView.d.ts.map +1 -1
  80. package/dist/widgets/aiObservability/prompts/AiPromptEditorView.js +36 -6
  81. package/dist/widgets/aiObservability/prompts/AiPromptEditorView.js.map +1 -1
  82. package/dist/widgets/aiObservability/prompts/AiPromptHubView.d.ts +3 -0
  83. package/dist/widgets/aiObservability/prompts/AiPromptHubView.d.ts.map +1 -1
  84. package/dist/widgets/aiObservability/prompts/AiPromptHubView.js +6 -6
  85. package/dist/widgets/aiObservability/prompts/AiPromptHubView.js.map +1 -1
  86. package/dist/widgets/aiObservability/prompts/AiPromptsListScreen.d.ts.map +1 -1
  87. package/dist/widgets/aiObservability/prompts/AiPromptsListScreen.js +12 -12
  88. package/dist/widgets/aiObservability/prompts/AiPromptsListScreen.js.map +1 -1
  89. package/dist/widgets/aiObservability/prompts/AiPromptsListView.d.ts.map +1 -1
  90. package/dist/widgets/aiObservability/prompts/AiPromptsListView.js +156 -35
  91. package/dist/widgets/aiObservability/prompts/AiPromptsListView.js.map +1 -1
  92. package/dist/widgets/aiObservability/prompts/promptTypes.d.ts +13 -3
  93. package/dist/widgets/aiObservability/prompts/promptTypes.d.ts.map +1 -1
  94. package/dist/widgets/aiObservability/prompts/promptTypes.js +61 -19
  95. package/dist/widgets/aiObservability/prompts/promptTypes.js.map +1 -1
  96. package/dist/widgets/aiObservability/review/AiReviewBatchScreen.d.ts +11 -0
  97. package/dist/widgets/aiObservability/review/AiReviewBatchScreen.d.ts.map +1 -0
  98. package/dist/widgets/aiObservability/review/AiReviewBatchScreen.js +115 -0
  99. package/dist/widgets/aiObservability/review/AiReviewBatchScreen.js.map +1 -0
  100. package/dist/widgets/aiObservability/review/AiReviewBatchView.d.ts +22 -0
  101. package/dist/widgets/aiObservability/review/AiReviewBatchView.d.ts.map +1 -0
  102. package/dist/widgets/aiObservability/review/AiReviewBatchView.js +136 -0
  103. package/dist/widgets/aiObservability/review/AiReviewBatchView.js.map +1 -0
  104. package/dist/widgets/aiObservability/review/AiReviewBatchesScreen.d.ts +4 -0
  105. package/dist/widgets/aiObservability/review/AiReviewBatchesScreen.d.ts.map +1 -0
  106. package/dist/widgets/aiObservability/review/AiReviewBatchesScreen.js +92 -0
  107. package/dist/widgets/aiObservability/review/AiReviewBatchesScreen.js.map +1 -0
  108. package/dist/widgets/aiObservability/review/AiReviewBatchesView.d.ts +26 -0
  109. package/dist/widgets/aiObservability/review/AiReviewBatchesView.d.ts.map +1 -0
  110. package/dist/widgets/aiObservability/review/AiReviewBatchesView.js +115 -0
  111. package/dist/widgets/aiObservability/review/AiReviewBatchesView.js.map +1 -0
  112. package/dist/widgets/aiObservability/review/AiReviewItemScreen.d.ts.map +1 -1
  113. package/dist/widgets/aiObservability/review/AiReviewItemScreen.js +73 -16
  114. package/dist/widgets/aiObservability/review/AiReviewItemScreen.js.map +1 -1
  115. package/dist/widgets/aiObservability/review/AiReviewItemView.d.ts +19 -5
  116. package/dist/widgets/aiObservability/review/AiReviewItemView.d.ts.map +1 -1
  117. package/dist/widgets/aiObservability/review/AiReviewItemView.js +14 -9
  118. package/dist/widgets/aiObservability/review/AiReviewItemView.js.map +1 -1
  119. package/dist/widgets/aiObservability/review/AiReviewQueueScreen.d.ts.map +1 -1
  120. package/dist/widgets/aiObservability/review/AiReviewQueueScreen.js +16 -2
  121. package/dist/widgets/aiObservability/review/AiReviewQueueScreen.js.map +1 -1
  122. package/dist/widgets/aiObservability/review/AiReviewQueueView.d.ts +11 -1
  123. package/dist/widgets/aiObservability/review/AiReviewQueueView.d.ts.map +1 -1
  124. package/dist/widgets/aiObservability/review/AiReviewQueueView.js +96 -37
  125. package/dist/widgets/aiObservability/review/AiReviewQueueView.js.map +1 -1
  126. package/dist/widgets/aiObservability/review/ReviewQuestionList.d.ts +13 -0
  127. package/dist/widgets/aiObservability/review/ReviewQuestionList.d.ts.map +1 -0
  128. package/dist/widgets/aiObservability/review/ReviewQuestionList.js +28 -0
  129. package/dist/widgets/aiObservability/review/ReviewQuestionList.js.map +1 -0
  130. package/dist/widgets/aiObservability/review/ReviewReadOnlyPanel.d.ts +3 -0
  131. package/dist/widgets/aiObservability/review/ReviewReadOnlyPanel.d.ts.map +1 -1
  132. package/dist/widgets/aiObservability/review/ReviewReadOnlyPanel.js +2 -2
  133. package/dist/widgets/aiObservability/review/ReviewReadOnlyPanel.js.map +1 -1
  134. package/dist/widgets/aiObservability/review/ReviewScoreField.d.ts +14 -0
  135. package/dist/widgets/aiObservability/review/ReviewScoreField.d.ts.map +1 -1
  136. package/dist/widgets/aiObservability/review/ReviewScoreField.js +41 -12
  137. package/dist/widgets/aiObservability/review/ReviewScoreField.js.map +1 -1
  138. package/dist/widgets/aiObservability/review/batchTypes.d.ts +103 -0
  139. package/dist/widgets/aiObservability/review/batchTypes.d.ts.map +1 -0
  140. package/dist/widgets/aiObservability/review/batchTypes.js +61 -0
  141. package/dist/widgets/aiObservability/review/batchTypes.js.map +1 -0
  142. package/dist/widgets/aiObservability/review/reviewShortcuts.d.ts +21 -0
  143. package/dist/widgets/aiObservability/review/reviewShortcuts.d.ts.map +1 -0
  144. package/dist/widgets/aiObservability/review/reviewShortcuts.js +141 -0
  145. package/dist/widgets/aiObservability/review/reviewShortcuts.js.map +1 -0
  146. package/dist/widgets/aiObservability/review/reviewTypes.d.ts +23 -2
  147. package/dist/widgets/aiObservability/review/reviewTypes.d.ts.map +1 -1
  148. package/dist/widgets/aiObservability/review/reviewTypes.js +25 -0
  149. package/dist/widgets/aiObservability/review/reviewTypes.js.map +1 -1
  150. package/dist/widgets/aiObservability/review/useAiObservabilityReviewApi.d.ts +48 -0
  151. package/dist/widgets/aiObservability/review/useAiObservabilityReviewApi.d.ts.map +1 -1
  152. package/dist/widgets/aiObservability/review/useAiObservabilityReviewApi.js +49 -0
  153. package/dist/widgets/aiObservability/review/useAiObservabilityReviewApi.js.map +1 -1
  154. package/dist/widgets/aiObservability/shell/AgreementMeter.d.ts +30 -0
  155. package/dist/widgets/aiObservability/shell/AgreementMeter.d.ts.map +1 -0
  156. package/dist/widgets/aiObservability/shell/AgreementMeter.js +32 -0
  157. package/dist/widgets/aiObservability/shell/AgreementMeter.js.map +1 -0
  158. package/dist/widgets/aiObservability/shell/AiObservabilityChrome.d.ts +10 -0
  159. package/dist/widgets/aiObservability/shell/AiObservabilityChrome.d.ts.map +1 -1
  160. package/dist/widgets/aiObservability/shell/AiObservabilityChrome.js +6 -4
  161. package/dist/widgets/aiObservability/shell/AiObservabilityChrome.js.map +1 -1
  162. package/dist/widgets/aiObservability/shell/AiObservabilityScreenWidgets.d.ts +3 -1
  163. package/dist/widgets/aiObservability/shell/AiObservabilityScreenWidgets.d.ts.map +1 -1
  164. package/dist/widgets/aiObservability/shell/AiObservabilityScreenWidgets.js +5 -1
  165. package/dist/widgets/aiObservability/shell/AiObservabilityScreenWidgets.js.map +1 -1
  166. package/dist/widgets/aiObservability/shell/AiObservabilityStatusChip.d.ts.map +1 -1
  167. package/dist/widgets/aiObservability/shell/AiObservabilityStatusChip.js +3 -3
  168. package/dist/widgets/aiObservability/shell/AiObservabilityStatusChip.js.map +1 -1
  169. package/dist/widgets/aiObservability/shell/EvalPipelineOverview.d.ts +14 -0
  170. package/dist/widgets/aiObservability/shell/EvalPipelineOverview.d.ts.map +1 -0
  171. package/dist/widgets/aiObservability/shell/EvalPipelineOverview.js +26 -0
  172. package/dist/widgets/aiObservability/shell/EvalPipelineOverview.js.map +1 -0
  173. package/dist/widgets/aiObservability/shell/EvalStepBanner.d.ts +11 -0
  174. package/dist/widgets/aiObservability/shell/EvalStepBanner.d.ts.map +1 -0
  175. package/dist/widgets/aiObservability/shell/EvalStepBanner.js +8 -0
  176. package/dist/widgets/aiObservability/shell/EvalStepBanner.js.map +1 -0
  177. package/dist/widgets/aiObservability/shell/EvalStepper.d.ts +22 -0
  178. package/dist/widgets/aiObservability/shell/EvalStepper.d.ts.map +1 -0
  179. package/dist/widgets/aiObservability/shell/EvalStepper.js +28 -0
  180. package/dist/widgets/aiObservability/shell/EvalStepper.js.map +1 -0
  181. package/dist/widgets/aiObservability/shell/ObservabilityPageHeader.d.ts +17 -0
  182. package/dist/widgets/aiObservability/shell/ObservabilityPageHeader.d.ts.map +1 -0
  183. package/dist/widgets/aiObservability/shell/ObservabilityPageHeader.js +10 -0
  184. package/dist/widgets/aiObservability/shell/ObservabilityPageHeader.js.map +1 -0
  185. package/dist/widgets/aiObservability/shell/ObservabilityStates.d.ts +24 -0
  186. package/dist/widgets/aiObservability/shell/ObservabilityStates.d.ts.map +1 -0
  187. package/dist/widgets/aiObservability/shell/ObservabilityStates.js +11 -0
  188. package/dist/widgets/aiObservability/shell/ObservabilityStates.js.map +1 -0
  189. package/dist/widgets/aiObservability/shell/ObservabilityStatusBadge.d.ts +11 -0
  190. package/dist/widgets/aiObservability/shell/ObservabilityStatusBadge.d.ts.map +1 -0
  191. package/dist/widgets/aiObservability/shell/ObservabilityStatusBadge.js +9 -0
  192. package/dist/widgets/aiObservability/shell/ObservabilityStatusBadge.js.map +1 -0
  193. package/dist/widgets/aiObservability/shell/aiObservabilityNav.d.ts +1 -0
  194. package/dist/widgets/aiObservability/shell/aiObservabilityNav.d.ts.map +1 -1
  195. package/dist/widgets/aiObservability/shell/aiObservabilityNav.js +15 -8
  196. package/dist/widgets/aiObservability/shell/aiObservabilityNav.js.map +1 -1
  197. package/dist/widgets/aiObservability/shell/clientTable.d.ts +48 -0
  198. package/dist/widgets/aiObservability/shell/clientTable.d.ts.map +1 -0
  199. package/dist/widgets/aiObservability/shell/clientTable.js +163 -0
  200. package/dist/widgets/aiObservability/shell/clientTable.js.map +1 -0
  201. package/dist/widgets/aiObservability/shell/evalPipeline.d.ts +24 -0
  202. package/dist/widgets/aiObservability/shell/evalPipeline.d.ts.map +1 -0
  203. package/dist/widgets/aiObservability/shell/evalPipeline.js +43 -0
  204. package/dist/widgets/aiObservability/shell/evalPipeline.js.map +1 -0
  205. package/dist/widgets/aiObservability/shell/observabilityStatus.d.ts +23 -0
  206. package/dist/widgets/aiObservability/shell/observabilityStatus.d.ts.map +1 -0
  207. package/dist/widgets/aiObservability/shell/observabilityStatus.js +72 -0
  208. package/dist/widgets/aiObservability/shell/observabilityStatus.js.map +1 -0
  209. package/dist/widgets/aiObservability/traces/AiTracesListScreen.d.ts.map +1 -1
  210. package/dist/widgets/aiObservability/traces/AiTracesListScreen.js +18 -9
  211. package/dist/widgets/aiObservability/traces/AiTracesListScreen.js.map +1 -1
  212. package/dist/widgets/aiObservability/traces/AiTracesListView.d.ts +18 -7
  213. package/dist/widgets/aiObservability/traces/AiTracesListView.d.ts.map +1 -1
  214. package/dist/widgets/aiObservability/traces/AiTracesListView.js +198 -78
  215. package/dist/widgets/aiObservability/traces/AiTracesListView.js.map +1 -1
  216. package/dist/widgets/aiObservability/traces/traceTypes.d.ts +23 -1
  217. package/dist/widgets/aiObservability/traces/traceTypes.d.ts.map +1 -1
  218. package/dist/widgets/aiObservability/traces/traceTypes.js +92 -1
  219. package/dist/widgets/aiObservability/traces/traceTypes.js.map +1 -1
  220. package/dist/widgets/aiObservability/traces/useAiObservabilityTracesApi.d.ts +2 -0
  221. package/dist/widgets/aiObservability/traces/useAiObservabilityTracesApi.d.ts.map +1 -1
  222. package/dist/widgets/aiObservability/traces/useAiObservabilityTracesApi.js +9 -2
  223. package/dist/widgets/aiObservability/traces/useAiObservabilityTracesApi.js.map +1 -1
  224. package/package.json +3 -3
  225. package/src/index.tsx +2 -0
  226. package/src/isolated/AiPromptEditorScreen.isolated.tsx +24 -0
  227. package/src/isolated/aiListTables.isolated.tsx +654 -0
  228. package/src/isolated/aiObservabilityScreens.isolated.tsx +715 -287
  229. package/src/isolated/aiReviewBatchScreens.isolated.tsx +378 -0
  230. package/src/isolated/aiTracesTable.isolated.tsx +375 -0
  231. package/src/widgets/aiObservability/datasets/AiDatasetsListScreen.tsx +44 -13
  232. package/src/widgets/aiObservability/datasets/AiDatasetsListView.tsx +303 -103
  233. package/src/widgets/aiObservability/datasets/datasetTypes.test.ts +0 -13
  234. package/src/widgets/aiObservability/datasets/datasetTypes.ts +37 -13
  235. package/src/widgets/aiObservability/evaluators/AiEvaluatorDetailScreen.tsx +34 -11
  236. package/src/widgets/aiObservability/evaluators/AiEvaluatorNewScreen.tsx +12 -1
  237. package/src/widgets/aiObservability/evaluators/AiEvaluatorPanels.test.tsx +97 -9
  238. package/src/widgets/aiObservability/evaluators/AiEvaluatorPanels.tsx +235 -131
  239. package/src/widgets/aiObservability/evaluators/AiEvaluatorsListScreen.tsx +21 -2
  240. package/src/widgets/aiObservability/evaluators/AiEvaluatorsListView.tsx +261 -76
  241. package/src/widgets/aiObservability/evaluators/evaluatorTypes.test.ts +7 -0
  242. package/src/widgets/aiObservability/evaluators/evaluatorTypes.ts +82 -0
  243. package/src/widgets/aiObservability/experiments/AiExperimentNewScreen.tsx +271 -13
  244. package/src/widgets/aiObservability/experiments/AiExperimentNewView.test.tsx +164 -2
  245. package/src/widgets/aiObservability/experiments/AiExperimentNewView.tsx +400 -186
  246. package/src/widgets/aiObservability/experiments/AiExperimentResultsScreen.tsx +104 -45
  247. package/src/widgets/aiObservability/experiments/AiExperimentResultsView.test.tsx +290 -0
  248. package/src/widgets/aiObservability/experiments/AiExperimentResultsView.tsx +342 -97
  249. package/src/widgets/aiObservability/experiments/AiExperimentsListScreen.tsx +35 -4
  250. package/src/widgets/aiObservability/experiments/AiExperimentsListView.tsx +302 -112
  251. package/src/widgets/aiObservability/experiments/AiJudgeExperimentSteps.test.tsx +250 -0
  252. package/src/widgets/aiObservability/experiments/AiJudgeExperimentSteps.tsx +468 -0
  253. package/src/widgets/aiObservability/experiments/ExperimentWizard.tsx +106 -0
  254. package/src/widgets/aiObservability/experiments/experimentTypes.test.ts +103 -16
  255. package/src/widgets/aiObservability/experiments/experimentTypes.ts +250 -10
  256. package/src/widgets/aiObservability/experiments/useAiObservabilityExperimentsApi.test.ts +35 -0
  257. package/src/widgets/aiObservability/experiments/useAiObservabilityExperimentsApi.ts +55 -9
  258. package/src/widgets/aiObservability/prompts/AiPromptEditorScreen.tsx +26 -2
  259. package/src/widgets/aiObservability/prompts/AiPromptEditorView.tsx +95 -1
  260. package/src/widgets/aiObservability/prompts/AiPromptHubView.test.tsx +61 -1
  261. package/src/widgets/aiObservability/prompts/AiPromptHubView.tsx +71 -27
  262. package/src/widgets/aiObservability/prompts/AiPromptsListScreen.tsx +34 -15
  263. package/src/widgets/aiObservability/prompts/AiPromptsListView.test.tsx +104 -8
  264. package/src/widgets/aiObservability/prompts/AiPromptsListView.tsx +287 -117
  265. package/src/widgets/aiObservability/prompts/promptTypes.test.ts +63 -1
  266. package/src/widgets/aiObservability/prompts/promptTypes.ts +83 -22
  267. package/src/widgets/aiObservability/review/AiReviewBatchScreen.tsx +217 -0
  268. package/src/widgets/aiObservability/review/AiReviewBatchView.tsx +398 -0
  269. package/src/widgets/aiObservability/review/AiReviewBatchViews.test.tsx +328 -0
  270. package/src/widgets/aiObservability/review/AiReviewBatchesScreen.tsx +137 -0
  271. package/src/widgets/aiObservability/review/AiReviewBatchesView.tsx +333 -0
  272. package/src/widgets/aiObservability/review/AiReviewItemScreen.tsx +121 -25
  273. package/src/widgets/aiObservability/review/AiReviewItemView.tsx +112 -70
  274. package/src/widgets/aiObservability/review/AiReviewQueueScreen.tsx +29 -2
  275. package/src/widgets/aiObservability/review/AiReviewQueueView.tsx +183 -75
  276. package/src/widgets/aiObservability/review/ReviewQuestionList.tsx +128 -0
  277. package/src/widgets/aiObservability/review/ReviewReadOnlyPanel.tsx +21 -13
  278. package/src/widgets/aiObservability/review/ReviewScoreField.tsx +111 -27
  279. package/src/widgets/aiObservability/review/batchTypes.test.ts +207 -0
  280. package/src/widgets/aiObservability/review/batchTypes.ts +162 -0
  281. package/src/widgets/aiObservability/review/reviewShortcuts.ts +195 -0
  282. package/src/widgets/aiObservability/review/reviewTypes.ts +62 -2
  283. package/src/widgets/aiObservability/review/useAiObservabilityReviewApi.test.ts +74 -0
  284. package/src/widgets/aiObservability/review/useAiObservabilityReviewApi.ts +98 -0
  285. package/src/widgets/aiObservability/shell/AgreementMeter.tsx +103 -0
  286. package/src/widgets/aiObservability/shell/AiObservabilityChrome.tsx +48 -14
  287. package/src/widgets/aiObservability/shell/AiObservabilityScreenWidgets.tsx +6 -0
  288. package/src/widgets/aiObservability/shell/AiObservabilityStatusChip.tsx +10 -2
  289. package/src/widgets/aiObservability/shell/EvalPipelineOverview.tsx +68 -0
  290. package/src/widgets/aiObservability/shell/EvalStepBanner.tsx +24 -0
  291. package/src/widgets/aiObservability/shell/EvalStepper.test.tsx +80 -0
  292. package/src/widgets/aiObservability/shell/EvalStepper.tsx +126 -0
  293. package/src/widgets/aiObservability/shell/ObservabilityPageHeader.tsx +50 -0
  294. package/src/widgets/aiObservability/shell/ObservabilitySharedUi.test.tsx +140 -0
  295. package/src/widgets/aiObservability/shell/ObservabilityStates.tsx +81 -0
  296. package/src/widgets/aiObservability/shell/ObservabilityStatusBadge.tsx +29 -0
  297. package/src/widgets/aiObservability/shell/aiObservabilityNav.ts +16 -8
  298. package/src/widgets/aiObservability/shell/clientTable.test.ts +176 -0
  299. package/src/widgets/aiObservability/shell/clientTable.ts +251 -0
  300. package/src/widgets/aiObservability/shell/evalPipeline.ts +74 -0
  301. package/src/widgets/aiObservability/shell/observabilityStatus.test.ts +73 -0
  302. package/src/widgets/aiObservability/shell/observabilityStatus.ts +100 -0
  303. package/src/widgets/aiObservability/traces/AiTracesListScreen.tsx +41 -13
  304. package/src/widgets/aiObservability/traces/AiTracesListView.tsx +423 -300
  305. package/src/widgets/aiObservability/traces/traceTypes.test.ts +52 -1
  306. package/src/widgets/aiObservability/traces/traceTypes.ts +117 -2
  307. package/src/widgets/aiObservability/traces/useAiObservabilityTracesApi.test.ts +13 -1
  308. package/src/widgets/aiObservability/traces/useAiObservabilityTracesApi.ts +10 -2
@@ -36,9 +36,17 @@ import type {
36
36
  PromptListItem,
37
37
  } from "../widgets/aiObservability/prompts/promptTypes";
38
38
  import {AiReviewItemScreenWidget} from "../widgets/aiObservability/review/AiReviewItemScreen";
39
- import {AiReviewItemView} from "../widgets/aiObservability/review/AiReviewItemView";
39
+ import {
40
+ AiReviewItemHeaderMeta,
41
+ AiReviewItemNav,
42
+ AiReviewItemView,
43
+ reviewItemTitle,
44
+ } from "../widgets/aiObservability/review/AiReviewItemView";
40
45
  import {AiReviewScreenWidget} from "../widgets/aiObservability/review/AiReviewQueueScreen";
41
- import {AiReviewQueueView} from "../widgets/aiObservability/review/AiReviewQueueView";
46
+ import {
47
+ AiReviewQueueActions,
48
+ AiReviewQueueView,
49
+ } from "../widgets/aiObservability/review/AiReviewQueueView";
42
50
  import {ReviewScoreField} from "../widgets/aiObservability/review/ReviewScoreField";
43
51
  import type {ReviewDetail, ReviewListItem} from "../widgets/aiObservability/review/reviewTypes";
44
52
  import {AiObservabilityChrome} from "../widgets/aiObservability/shell/AiObservabilityChrome";
@@ -53,12 +61,11 @@ import {
53
61
  import {AiTraceDetailScreenWidget} from "../widgets/aiObservability/traces/AiTraceDetailScreen";
54
62
  import {AiTraceDetailView} from "../widgets/aiObservability/traces/AiTraceDetailView";
55
63
  import {AiTracesScreenWidget} from "../widgets/aiObservability/traces/AiTracesListScreen";
56
- import {AiTracesListView} from "../widgets/aiObservability/traces/AiTracesListView";
57
64
  import {
58
- emptyTraceFilters,
59
- type TraceDetail,
60
- type TraceListItem,
61
- } from "../widgets/aiObservability/traces/traceTypes";
65
+ AiTracesHeaderActions,
66
+ AiTracesListView,
67
+ } from "../widgets/aiObservability/traces/AiTracesListView";
68
+ import type {TraceDetail, TraceListItem} from "../widgets/aiObservability/traces/traceTypes";
62
69
  import {operatorObservabilityStatus} from "./observabilityStatusFixtures.isolated";
63
70
 
64
71
  interface ExpoRouterPushMock {
@@ -492,10 +499,7 @@ describe("AiDatasetsListScreen", () => {
492
499
  });
493
500
  expect(view.getByText("Name is required.")).toBeTruthy();
494
501
 
495
- fireEvent.changeText(
496
- view.getAllByDisplayValue("")[0] ?? view.getByLabelText("Name"),
497
- "new-set"
498
- );
502
+ fireEvent.changeText(view.getByTestId("ai-datasets-create-name"), "new-set");
499
503
  await act(async () => {
500
504
  fireEvent.press(view.getByText("Create dataset"));
501
505
  await new Promise((resolve) => setTimeout(resolve, 50));
@@ -565,9 +569,10 @@ describe("AiDatasetsListScreen", () => {
565
569
  <AiDatasetsScreenWidget api={createApi()} {...widgetProps} />
566
570
  );
567
571
  expect(errored.getByTestId("ai-datasets-load-error")).toBeTruthy();
572
+ expect(errored.getByText("Could not load datasets.")).toBeTruthy();
568
573
  listState.refetch.mockClear();
569
574
  await act(async () => {
570
- fireEvent.press(errored.getByText("Retry"));
575
+ fireEvent.press(errored.getByText("Try again"));
571
576
  await new Promise((resolve) => setTimeout(resolve, 50));
572
577
  });
573
578
  assert.isAtLeast(listState.refetch.mock.calls.length, 1);
@@ -588,7 +593,7 @@ describe("AiDatasetsListScreen", () => {
588
593
  fireEvent.press(createFail.getByTestId("ai-datasets-create"));
589
594
  await Promise.resolve();
590
595
  });
591
- fireEvent.changeText(createFail.getAllByDisplayValue("")[0]!, "broken");
596
+ fireEvent.changeText(createFail.getByTestId("ai-datasets-create-name"), "broken");
592
597
  await act(async () => {
593
598
  fireEvent.press(createFail.getByText("Create dataset"));
594
599
  await Promise.resolve();
@@ -669,7 +674,7 @@ describe("AiDatasetsListScreen", () => {
669
674
  fireEvent.press(failImportButtons[failImportButtons.length - 1]!);
670
675
  await Promise.resolve();
671
676
  });
672
- expect(failing.getByText("Import failed.")).toBeTruthy();
677
+ expect(failing.getByText("Could not import these items.")).toBeTruthy();
673
678
  });
674
679
 
675
680
  it("dismisses create and import modals", async () => {
@@ -711,11 +716,8 @@ describe("AiDatasetsListScreen", () => {
711
716
  fireEvent.press(view.getByTestId("ai-datasets-create"));
712
717
  await Promise.resolve();
713
718
  });
714
- const emptyFields = view.getAllByDisplayValue("");
715
- fireEvent.changeText(emptyFields[0]!, "bound-set");
716
- if (emptyFields[1]) {
717
- fireEvent.changeText(emptyFields[1], "summarize");
718
- }
719
+ fireEvent.changeText(view.getByTestId("ai-datasets-create-name"), "bound-set");
720
+ fireEvent.changeText(view.getByTestId("ai-datasets-create-binding"), "summarize");
719
721
  await act(async () => {
720
722
  fireEvent.press(view.getByText("Create dataset"));
721
723
  await new Promise((resolve) => setTimeout(resolve, 50));
@@ -847,7 +849,7 @@ describe("AiDatasetsListView", () => {
847
849
  expect(view.getByTestId("ai-datasets-import-result")).toBeTruthy();
848
850
  expect(view.getByTestId("ai-datasets-import-error")).toBeTruthy();
849
851
  await act(async () => {
850
- fireEvent.press(view.getByText("Retry"));
852
+ fireEvent.press(view.getByText("Try again"));
851
853
  await Promise.resolve();
852
854
  });
853
855
  assert.equal(onRetry.mock.calls.length, 1);
@@ -957,6 +959,7 @@ describe("AiDatasetsListView", () => {
957
959
 
958
960
  it("ignores empty file selection and failed file reads", async () => {
959
961
  const onFilePicked = mock(() => undefined);
962
+ const onFileReadError = mock((_message: string) => undefined);
960
963
  const originalFetch = globalThis.fetch;
961
964
  globalThis.fetch = mock(async () => {
962
965
  throw new Error("read failed");
@@ -978,6 +981,7 @@ describe("AiDatasetsListView", () => {
978
981
  onDismissCreate={() => undefined}
979
982
  onDismissImport={() => undefined}
980
983
  onFilePicked={onFilePicked}
984
+ onFileReadError={onFileReadError}
981
985
  onImportPasteChange={() => undefined}
982
986
  onImportSubmit={() => undefined}
983
987
  onOpenCreate={() => undefined}
@@ -993,6 +997,8 @@ describe("AiDatasetsListView", () => {
993
997
  await new Promise((resolve) => setTimeout(resolve, 50));
994
998
  });
995
999
  assert.equal(onFilePicked.mock.calls.length, 0);
1000
+ assert.equal(onFileReadError.mock.calls.length, 1);
1001
+ assert.include(String(onFileReadError.mock.calls[0]?.[0]), "Could not read that file");
996
1002
  globalThis.fetch = originalFetch;
997
1003
  });
998
1004
 
@@ -1242,7 +1248,7 @@ describe("AiEvaluatorDetailScreen", () => {
1242
1248
  screenName="ai-evaluator-detail"
1243
1249
  />
1244
1250
  );
1245
- expect(errored.getByText("Failed to load evaluator.")).toBeTruthy();
1251
+ expect(errored.getByText("Could not load evaluator.")).toBeTruthy();
1246
1252
  detailState.isError = false;
1247
1253
  detailState.data = evaluator;
1248
1254
  });
@@ -1392,7 +1398,7 @@ describe("AiEvaluatorNewScreen", () => {
1392
1398
  fireEvent.changeText(view.getByTestId("ai-evaluator-name"), "quality");
1393
1399
  setDimensionKey(view, "wrong-key");
1394
1400
  await act(async () => {
1395
- fireEvent.press(view.getByTestId("ai-evaluator-type-llm-judge"));
1401
+ fireEvent.press(view.getByText("LLM judge"));
1396
1402
  await Promise.resolve();
1397
1403
  });
1398
1404
  await act(async () => {
@@ -1413,7 +1419,7 @@ describe("AiEvaluatorNewScreen", () => {
1413
1419
  expect(view.getByTestId("ai-evaluator-schema-mismatch")).toBeTruthy();
1414
1420
 
1415
1421
  await act(async () => {
1416
- fireEvent.press(view.getByTestId("ai-evaluator-type-human"));
1422
+ fireEvent.press(view.getByText("Human"));
1417
1423
  await Promise.resolve();
1418
1424
  });
1419
1425
  setDimensionKey(view, "correct");
@@ -1460,7 +1466,7 @@ describe("AiEvaluatorNewScreen", () => {
1460
1466
  );
1461
1467
  fireEvent.changeText(view.getByTestId("ai-evaluator-name"), "assert");
1462
1468
  await act(async () => {
1463
- fireEvent.press(view.getByTestId("ai-evaluator-type-json-assert"));
1469
+ fireEvent.press(view.getByText("JSON assert"));
1464
1470
  await Promise.resolve();
1465
1471
  });
1466
1472
  fireEvent.changeText(view.getByTestId("ai-evaluator-assertion-path"), "output.text");
@@ -1497,7 +1503,7 @@ describe("AiEvaluatorNewScreen", () => {
1497
1503
  );
1498
1504
  setDimensionKey(view, "pass");
1499
1505
  await act(async () => {
1500
- fireEvent.press(view.getByTestId("ai-evaluator-type-human"));
1506
+ fireEvent.press(view.getByText("Human"));
1501
1507
  await Promise.resolve();
1502
1508
  });
1503
1509
  fireEvent.changeText(view.getByTestId("ai-evaluator-instructions"), "Rate quality");
@@ -1542,16 +1548,16 @@ describe("AiEvaluatorNewScreen", () => {
1542
1548
  assert.isOk(view.getByTestId("ai-evaluator-dimension-0-key"));
1543
1549
 
1544
1550
  await act(async () => {
1545
- fireEvent.press(view.getAllByText("numeric")[0]!);
1551
+ fireEvent.press(view.getAllByText("Number")[0]!);
1546
1552
  await Promise.resolve();
1547
1553
  });
1548
1554
  fireEvent.changeText(view.getByTestId("ai-evaluator-dimension-0-min"), "8");
1549
1555
  await act(async () => {
1550
- fireEvent.press(view.getAllByText("boolean")[0]!);
1556
+ fireEvent.press(view.getAllByText("Yes or no")[0]!);
1551
1557
  await Promise.resolve();
1552
1558
  });
1553
1559
  await act(async () => {
1554
- fireEvent.press(view.getAllByText("numeric")[0]!);
1560
+ fireEvent.press(view.getAllByText("Number")[0]!);
1555
1561
  await Promise.resolve();
1556
1562
  });
1557
1563
  assert.equal(view.getByTestId("ai-evaluator-dimension-0-min").props.value, "0");
@@ -1568,7 +1574,7 @@ describe("AiEvaluatorNewScreen", () => {
1568
1574
  ).toBeTruthy();
1569
1575
 
1570
1576
  await act(async () => {
1571
- fireEvent.press(view.getAllByText("categorical")[0]!);
1577
+ fireEvent.press(view.getAllByText("Category")[0]!);
1572
1578
  await Promise.resolve();
1573
1579
  });
1574
1580
  await act(async () => {
@@ -1578,11 +1584,11 @@ describe("AiEvaluatorNewScreen", () => {
1578
1584
  expect(view.getByText("Add at least one category for each categorical score.")).toBeTruthy();
1579
1585
 
1580
1586
  await act(async () => {
1581
- fireEvent.press(view.getAllByText("boolean")[0]!);
1587
+ fireEvent.press(view.getAllByText("Yes or no")[0]!);
1582
1588
  await Promise.resolve();
1583
1589
  });
1584
1590
  await act(async () => {
1585
- fireEvent.press(view.getByTestId("ai-evaluator-type-json-assert"));
1591
+ fireEvent.press(view.getByText("JSON assert"));
1586
1592
  await Promise.resolve();
1587
1593
  });
1588
1594
  fireEvent.changeText(view.getByTestId("ai-evaluator-live-sample"), "25");
@@ -1612,7 +1618,7 @@ describe("AiEvaluatorNewScreen", () => {
1612
1618
  fireEvent.changeText(view.getByTestId("ai-evaluator-name"), "judge-check");
1613
1619
  setDimensionKey(view, "quality");
1614
1620
  await act(async () => {
1615
- fireEvent.press(view.getByTestId("ai-evaluator-type-llm-judge"));
1621
+ fireEvent.press(view.getByText("LLM judge"));
1616
1622
  await Promise.resolve();
1617
1623
  });
1618
1624
  const judgeSelect = view.UNSAFE_root.findAllByType(SelectField).find((field) => {
@@ -1819,7 +1825,7 @@ describe("AiEvaluatorsListView", () => {
1819
1825
  expect(getByTestId("ai-evaluator-open-eval-1")).toBeTruthy();
1820
1826
  });
1821
1827
 
1822
- it("uses a distinct badge status for each evaluator type", () => {
1828
+ it("uses one neutral badge colour for every evaluator kind and filters by kind", async () => {
1823
1829
  const baseEvaluator = evaluators[0];
1824
1830
  assert.exists(baseEvaluator);
1825
1831
  const allTypes: EvaluatorRecord[] = [
@@ -1827,7 +1833,7 @@ describe("AiEvaluatorsListView", () => {
1827
1833
  {...baseEvaluator, id: "eval-2", name: "human", type: "human"},
1828
1834
  {...baseEvaluator, id: "eval-3", name: "assert", type: "json-assert"},
1829
1835
  ];
1830
- const {getByTestId} = renderWithTheme(
1836
+ const {getAllByText, getByTestId, queryByTestId} = renderWithTheme(
1831
1837
  <AiEvaluatorsListView
1832
1838
  evaluators={allTypes}
1833
1839
  isLoading={false}
@@ -1840,7 +1846,53 @@ describe("AiEvaluatorsListView", () => {
1840
1846
  return getByTestId(`ai-evaluator-type-${evaluator.type}`).props.style[0].backgroundColor;
1841
1847
  });
1842
1848
 
1843
- assert.equal(new Set(colors).size, 3);
1849
+ // Colour means state, not category: kinds differ by icon and label only.
1850
+ assert.equal(new Set(colors).size, 1);
1851
+ expect(getByTestId("ai-evaluators-kind-filter")).toBeTruthy();
1852
+ assert.lengthOf(getAllByText("Full trace"), 3);
1853
+
1854
+ await act(async () => {
1855
+ // The kind filter renders above the table, so its segment is the first match.
1856
+ fireEvent.press(getAllByText("JSON assert")[0]!);
1857
+ await Promise.resolve();
1858
+ });
1859
+ expect(getByTestId("ai-evaluator-open-eval-3")).toBeTruthy();
1860
+ expect(queryByTestId("ai-evaluator-open-eval-1")).toBeNull();
1861
+ });
1862
+
1863
+ it("shows a retryable error and an empty state with New evaluator", async () => {
1864
+ const onRetry = mock(() => undefined);
1865
+ const onCreate = mock(() => undefined);
1866
+ const errored = renderWithTheme(
1867
+ <AiEvaluatorsListView
1868
+ evaluators={[]}
1869
+ isLoading={false}
1870
+ loadError="Could not load evaluators."
1871
+ onCreate={onCreate}
1872
+ onOpen={() => undefined}
1873
+ onRetry={onRetry}
1874
+ />
1875
+ );
1876
+ await act(async () => {
1877
+ fireEvent.press(errored.getByText("Try again"));
1878
+ await new Promise((resolve) => setTimeout(resolve, 0));
1879
+ });
1880
+ assert.equal(onRetry.mock.calls.length, 1);
1881
+
1882
+ const empty = renderWithTheme(
1883
+ <AiEvaluatorsListView
1884
+ evaluators={[]}
1885
+ isLoading={false}
1886
+ onCreate={onCreate}
1887
+ onOpen={() => undefined}
1888
+ onRetry={onRetry}
1889
+ />
1890
+ );
1891
+ await act(async () => {
1892
+ fireEvent.press(empty.getByTestId("ai-evaluators-empty-action"));
1893
+ await new Promise((resolve) => setTimeout(resolve, 0));
1894
+ });
1895
+ assert.equal(onCreate.mock.calls.length, 1);
1844
1896
  });
1845
1897
  });
1846
1898
  });
@@ -1857,7 +1909,7 @@ describe("AiExperimentNewScreen", () => {
1857
1909
  const pendingEstimates: PendingEstimate[] = [];
1858
1910
 
1859
1911
  beforeEach(() => {
1860
- setExpoSearchParams(() => ({datasetId: "ds-1"}));
1912
+ setExpoSearchParams(() => ({datasetId: "ds-1", pipeline: "prompt"}));
1861
1913
  routerPush.mockClear();
1862
1914
  estimateShouldFail = false;
1863
1915
  createShouldFail = false;
@@ -1924,10 +1976,36 @@ describe("AiExperimentNewScreen", () => {
1924
1976
  counts: {auto: 0, human: 2, needsReview: 0, total: 2},
1925
1977
  created: "2026-01-01T00:00:00.000Z",
1926
1978
  id: "ds-1",
1979
+ judgments: [
1980
+ {
1981
+ answered: 2,
1982
+ current: 2,
1983
+ evaluatorId: "eval-human",
1984
+ evaluatorName: "review queue",
1985
+ stale: 0,
1986
+ total: 2,
1987
+ },
1988
+ {
1989
+ answered: 1,
1990
+ current: 1,
1991
+ evaluatorId: "eval-tone-human",
1992
+ evaluatorName: "tone review",
1993
+ stale: 0,
1994
+ total: 2,
1995
+ },
1996
+ ],
1927
1997
  name: "gold",
1928
1998
  tags: [],
1929
1999
  updated: "2026-01-02T00:00:00.000Z",
1930
2000
  },
2001
+ {
2002
+ counts: {auto: 0, human: 0, needsReview: 0, total: 1},
2003
+ created: "2026-01-01T00:00:00.000Z",
2004
+ id: "ds-plain",
2005
+ name: "ungraded",
2006
+ tags: [],
2007
+ updated: "2026-01-02T00:00:00.000Z",
2008
+ },
1931
2009
  ],
1932
2010
  isLoading: false,
1933
2011
  }),
@@ -1942,6 +2020,38 @@ describe("AiExperimentNewScreen", () => {
1942
2020
  target: "full trace",
1943
2021
  type: "human",
1944
2022
  },
2023
+ {
2024
+ confidenceAlertBelow: 0.5,
2025
+ dimensions: [{dataType: "boolean", key: "tone", required: true}],
2026
+ id: "eval-tone-human",
2027
+ name: "tone review",
2028
+ runModes: {allowManualRun: true, availableInExperiments: true, liveSampleRate: 0},
2029
+ target: "full trace",
2030
+ type: "human",
2031
+ },
2032
+ {
2033
+ confidenceAlertBelow: 0.5,
2034
+ dimensions: [{dataType: "boolean", key: "correct", required: true}],
2035
+ id: "eval-judge",
2036
+ judgePromptName: "summarize",
2037
+ name: "tone judge",
2038
+ runModes: {allowManualRun: true, availableInExperiments: true, liveSampleRate: 0},
2039
+ target: "full trace",
2040
+ type: "llm-judge",
2041
+ },
2042
+ {
2043
+ confidenceAlertBelow: 0.5,
2044
+ dimensions: [
2045
+ {dataType: "boolean", key: "correct", required: true},
2046
+ {dataType: "boolean", key: "tone", required: true},
2047
+ ],
2048
+ id: "eval-judge-tone",
2049
+ judgePromptName: "summarize",
2050
+ name: "full judge",
2051
+ runModes: {allowManualRun: true, availableInExperiments: true, liveSampleRate: 0},
2052
+ target: "full trace",
2053
+ type: "llm-judge",
2054
+ },
1945
2055
  {
1946
2056
  confidenceAlertBelow: 0.5,
1947
2057
  dimensions: [{dataType: "boolean", key: "correct", required: true}],
@@ -2110,18 +2220,15 @@ describe("AiExperimentNewScreen", () => {
2110
2220
  await Promise.resolve();
2111
2221
  });
2112
2222
  await waitFor(() => {
2113
- assert.include(
2114
- view.getByTestId("ai-experiment-estimate").props.children.join(""),
2115
- "~$0.20"
2116
- );
2223
+ assert.include(String(view.getByTestId("ai-experiment-estimate").props.children), "$0.20");
2117
2224
  });
2118
2225
 
2119
2226
  await act(async () => {
2120
2227
  stale.resolve({costUsd: 9.99, generations: 1, wallClockSeconds: 60});
2121
2228
  await Promise.resolve();
2122
2229
  });
2123
- assert.include(view.getByTestId("ai-experiment-estimate").props.children.join(""), "~$0.20");
2124
- assert.notInclude(view.getByTestId("ai-experiment-estimate").props.children.join(""), "9.99");
2230
+ assert.include(String(view.getByTestId("ai-experiment-estimate").props.children), "$0.20");
2231
+ assert.notInclude(String(view.getByTestId("ai-experiment-estimate").props.children), "9.99");
2125
2232
 
2126
2233
  await act(async () => {
2127
2234
  fireEvent.changeText(view.getByTestId("ai-experiment-model-override"), "gpt-next");
@@ -2145,10 +2252,7 @@ describe("AiExperimentNewScreen", () => {
2145
2252
  await Promise.resolve();
2146
2253
  });
2147
2254
  await waitFor(() => {
2148
- assert.include(
2149
- view.getByTestId("ai-experiment-estimate").props.children.join(""),
2150
- "~$0.30"
2151
- );
2255
+ assert.include(String(view.getByTestId("ai-experiment-estimate").props.children), "$0.30");
2152
2256
  });
2153
2257
  assert.isNull(view.queryByText("Could not estimate experiment cost."));
2154
2258
  });
@@ -2266,6 +2370,80 @@ describe("AiExperimentNewScreen", () => {
2266
2370
  });
2267
2371
  expect(view.getByTestId("ai-experiment-step-review")).toBeTruthy();
2268
2372
  });
2373
+
2374
+ it("runs a judge calibration from a judged dataset", async () => {
2375
+ setExpoSearchParams(() => ({pipeline: "judge"}));
2376
+ estimateShouldFail = false;
2377
+ createShouldFail = false;
2378
+ routerPush.mockClear();
2379
+ const view = renderWithTheme(
2380
+ <AiExperimentNewScreenWidget
2381
+ api={stableApi}
2382
+ config={emptyConfig}
2383
+ routeBase="/admin"
2384
+ screenName="ai-experiment-new"
2385
+ />
2386
+ );
2387
+ fireEvent.changeText(view.getByTestId("ai-experiment-name"), "calibrate tone");
2388
+ fireEvent.press(view.getByTestId("ai-judge-dataset-send-review-ds-plain"));
2389
+ await act(async () => {
2390
+ fireEvent.press(view.getByTestId("ai-judge-dataset-ds-1-clickable"));
2391
+ await Promise.resolve();
2392
+ });
2393
+ await act(async () => {
2394
+ fireEvent.press(view.getByTestId("ai-judge-next"));
2395
+ await Promise.resolve();
2396
+ });
2397
+ expect(view.getByTestId("ai-judge-step-question-set")).toBeTruthy();
2398
+ await act(async () => {
2399
+ fireEvent.press(view.getByTestId("web_dropdown_option_eval-tone-human"));
2400
+ fireEvent.press(view.getByTestId("web_dropdown_option_eval-human"));
2401
+ await Promise.resolve();
2402
+ });
2403
+ await act(async () => {
2404
+ fireEvent.press(view.getByTestId("ai-judge-next"));
2405
+ await Promise.resolve();
2406
+ });
2407
+ expect(view.getByTestId("ai-judge-step-judge")).toBeTruthy();
2408
+ await act(async () => {
2409
+ fireEvent.press(view.getByTestId("web_dropdown_option_eval-judge-tone"));
2410
+ fireEvent.press(view.getByTestId("web_dropdown_option_eval-judge"));
2411
+ await Promise.resolve();
2412
+ });
2413
+ await act(async () => {
2414
+ fireEvent.press(view.getByTestId("ai-judge-version-1-clickable"));
2415
+ fireEvent.press(view.getByTestId("ai-judge-version-2-clickable"));
2416
+ fireEvent.press(view.getByTestId("ai-judge-version-1-clickable"));
2417
+ fireEvent.press(view.getByTestId("ai-judge-version-1-clickable"));
2418
+ await Promise.resolve();
2419
+ });
2420
+ await act(async () => {
2421
+ fireEvent.press(view.getByTestId("ai-judge-next"));
2422
+ await Promise.resolve();
2423
+ });
2424
+ await waitFor(() => {
2425
+ expect(view.getByTestId("ai-judge-estimate")).toBeTruthy();
2426
+ });
2427
+
2428
+ estimateShouldFail = true;
2429
+ fireEvent.changeText(view.getByTestId("ai-judge-model-override"), "gpt-test");
2430
+ await waitFor(() => {
2431
+ expect(view.getByText("Could not estimate experiment cost.")).toBeTruthy();
2432
+ });
2433
+
2434
+ estimateShouldFail = false;
2435
+ createShouldFail = true;
2436
+ fireEvent.press(view.getByTestId("ai-judge-run"));
2437
+ await waitFor(() => {
2438
+ expect(view.getByText("Could not start experiment.")).toBeTruthy();
2439
+ });
2440
+
2441
+ createShouldFail = false;
2442
+ fireEvent.press(view.getByTestId("ai-judge-run"));
2443
+ await waitFor(() => {
2444
+ expect(routerPush).toHaveBeenCalled();
2445
+ });
2446
+ });
2269
2447
  });
2270
2448
  });
2271
2449
 
@@ -2423,10 +2601,21 @@ describe("AiExperimentResultsScreen", () => {
2423
2601
  });
2424
2602
 
2425
2603
  it("does not reset the selected version when polled experiment data updates", async () => {
2426
- detailData = baseExperiment;
2604
+ // Both versions pass, so the version picker shows.
2605
+ const bothPass: ExperimentRecord = {
2606
+ ...baseExperiment,
2607
+ results: {
2608
+ ...(baseExperiment.results as NonNullable<ExperimentRecord["results"]>),
2609
+ gates: (baseExperiment.results?.gates ?? []).map((gate) => ({...gate, passed: true})),
2610
+ progress: {completed: 2, total: 2},
2611
+ },
2612
+ status: "completed",
2613
+ };
2614
+ detailData = bothPass;
2427
2615
  const {getByTestId, rerender} = renderWithTheme(
2428
2616
  <AiExperimentResultsScreenWidget {...widgetProps} />
2429
2617
  );
2618
+ expect(getByTestId("ai-experiment-promote")).toHaveTextContent("Promote v2 to production");
2430
2619
  await act(async () => {
2431
2620
  fireEvent.press(getByTestId("web_picker"));
2432
2621
  await Promise.resolve();
@@ -2435,16 +2624,47 @@ describe("AiExperimentResultsScreen", () => {
2435
2624
  fireEvent.press(getByTestId("web_dropdown_option_1"));
2436
2625
  await Promise.resolve();
2437
2626
  });
2627
+ detailData = {...bothPass, updated: "2026-01-01T00:06:00.000Z"};
2628
+ rerender(<AiExperimentResultsScreenWidget {...widgetProps} />);
2629
+ expect(getByTestId("ai-experiment-promote")).toHaveTextContent("Promote v1 to production");
2630
+ });
2631
+
2632
+ it("re-picks the promote version when gates arrive after the run finishes", () => {
2633
+ // While running there are no gates yet, so the default is the newest version.
2438
2634
  detailData = {
2439
2635
  ...baseExperiment,
2440
2636
  results: {
2441
- ...baseExperiment.results!,
2637
+ ...(baseExperiment.results as NonNullable<ExperimentRecord["results"]>),
2638
+ gates: [],
2639
+ progress: {completed: 1, total: 2},
2640
+ },
2641
+ status: "running",
2642
+ };
2643
+ const view = renderWithTheme(<AiExperimentResultsScreenWidget {...widgetProps} />);
2644
+ expect(view.getByTestId("ai-experiment-promote")).toHaveTextContent(
2645
+ "Promote v2 to production"
2646
+ );
2647
+ expect(view.queryByTestId("ai-experiment-promote-version")).toBeNull();
2648
+
2649
+ // The run finishes and only the earlier version passes.
2650
+ detailData = {
2651
+ ...baseExperiment,
2652
+ results: {
2653
+ ...(baseExperiment.results as NonNullable<ExperimentRecord["results"]>),
2654
+ gates: (baseExperiment.results?.gates ?? []).map((gate) => {
2655
+ return {...gate, passed: gate.version === 1};
2656
+ }),
2442
2657
  progress: {completed: 2, total: 2},
2443
2658
  },
2444
2659
  status: "completed",
2660
+ updated: "2026-01-01T00:06:00.000Z",
2445
2661
  };
2446
- rerender(<AiExperimentResultsScreenWidget {...widgetProps} />);
2447
- expect(getByTestId("ai-experiment-gate-correct")).toHaveTextContent(/v1 quality\.correct/);
2662
+ view.rerender(<AiExperimentResultsScreenWidget {...widgetProps} />);
2663
+ expect(view.getByTestId("ai-experiment-promote")).toHaveTextContent(
2664
+ "Promote v1 to production"
2665
+ );
2666
+ expect(view.getByTestId("ai-experiment-promote")).not.toBeDisabled();
2667
+ expect(view.getByTestId("ai-experiment-promote-version")).toBeTruthy();
2448
2668
  });
2449
2669
 
2450
2670
  it("blocks promote when gates fail and surfaces API errors", async () => {
@@ -2470,19 +2690,27 @@ describe("AiExperimentResultsScreen", () => {
2470
2690
  };
2471
2691
  const view = renderWithTheme(<AiExperimentResultsScreenWidget {...widgetProps} />);
2472
2692
  expect(view.getByTestId("ai-experiment-gates-failing")).toBeTruthy();
2693
+ expect(view.getByTestId("ai-experiment-promote")).toBeDisabled();
2473
2694
  fireEvent.press(view.getByTestId("ai-experiment-promote"));
2474
2695
  await act(async () => {
2475
2696
  await Promise.resolve();
2476
2697
  });
2477
- expect(view.getByTestId("ai-experiment-promote-blocked")).toBeTruthy();
2698
+ expect(view.getByTestId("ai-experiment-gates-failing")).toHaveTextContent(
2699
+ /v2 fails 1 gate: quality: correct ≥ 0\.8 \(got 0\.40\) — can't promote v2\./
2700
+ );
2478
2701
  });
2479
2702
 
2480
- it("shows query errors", () => {
2703
+ it("shows query errors with a retry", async () => {
2481
2704
  detailIsError = true;
2482
2705
 
2483
2706
  const view = renderWithTheme(<AiExperimentResultsScreenWidget {...widgetProps} />);
2484
2707
 
2485
- assert.exists(view.getByText("Failed to load experiment results."));
2708
+ assert.exists(view.getByText("Could not load experiment results."));
2709
+ await act(async () => {
2710
+ fireEvent.press(view.getByTestId("ai-experiment-results-error-retry"));
2711
+ await new Promise((resolve) => setTimeout(resolve, 50));
2712
+ });
2713
+ assert.isAtLeast(refetch.mock.calls.length, 1);
2486
2714
  });
2487
2715
 
2488
2716
  it("surfaces promote API errors and dismisses the confirmation", async () => {
@@ -2631,6 +2859,7 @@ describe("AiExperimentsListScreen", () => {
2631
2859
  const api = {
2632
2860
  enhanceEndpoints: () => api,
2633
2861
  injectEndpoints: () => ({
2862
+ useAiObservabilityDatasetsQuery: () => ({data: [], isError: false, isLoading: false}),
2634
2863
  useAiObservabilityExperimentsQuery: () => listState,
2635
2864
  useAiObservabilityStatusQuery: () => ({
2636
2865
  data: statusData,
@@ -2772,11 +3001,11 @@ describe("AiObservabilityChrome", () => {
2772
3001
 
2773
3002
  const localOffStatus: ObservabilityStatusPayload = {
2774
3003
  localOn: false,
2775
- plugins: [{capabilities: ["prompts", "traces"], id: "langfuse"}],
3004
+ plugins: [{capabilities: ["prompts", "traces"], id: "remote"}],
2776
3005
  primaries: {
2777
- datasets: "langfuse",
2778
- experiments: "langfuse",
2779
- prompts: "langfuse",
3006
+ datasets: "remote",
3007
+ experiments: "remote",
3008
+ prompts: "remote",
2780
3009
  reviewQueue: "local",
2781
3010
  },
2782
3011
  };
@@ -2786,12 +3015,8 @@ describe("AiObservabilityChrome", () => {
2786
3015
 
2787
3016
  describe("AI observability chrome", () => {
2788
3017
  it("formats the status chip for local on and local off primaries", () => {
2789
- expect(formatObservabilityStatusChip(localOnStatus)).toBe(
2790
- "Local on · prompts:local · datasets:local · experiments:local"
2791
- );
2792
- expect(formatObservabilityStatusChip(localOffStatus)).toBe(
2793
- "Local off · prompts:langfuse · datasets:langfuse · experiments:langfuse"
2794
- );
3018
+ expect(formatObservabilityStatusChip(localOnStatus)).toBe("Local observability on");
3019
+ expect(formatObservabilityStatusChip(localOffStatus)).toBe("Local observability off");
2795
3020
  });
2796
3021
 
2797
3022
  it("unwraps both envelope and already-unwrapped status payloads", () => {
@@ -2812,6 +3037,54 @@ describe("AiObservabilityChrome", () => {
2812
3037
  ]);
2813
3038
  });
2814
3039
 
3040
+ it("ends list screen breadcrumbs at the section", () => {
3041
+ const crumbs = buildAiObservabilityBreadcrumbs({
3042
+ routeBase: "/admin",
3043
+ screenName: "ai-datasets",
3044
+ });
3045
+ expect(crumbs.map((crumb) => crumb.label)).toEqual(["Admin", "AI Observability", "Datasets"]);
3046
+ });
3047
+
3048
+ it("renders the page header with title override, description, meta, and actions", () => {
3049
+ const {getByTestId, getByText} = renderWithTheme(
3050
+ <AiObservabilityChrome
3051
+ actions={<Text>Header action</Text>}
3052
+ api={stubApi}
3053
+ config={emptyConfig}
3054
+ description="What this screen is for."
3055
+ meta={<Text>Header meta</Text>}
3056
+ routeBase="/admin"
3057
+ screenName="ai-review-batch"
3058
+ status={localOnStatus}
3059
+ title="Recent summaries — batch 1"
3060
+ >
3061
+ <Text>Body</Text>
3062
+ </AiObservabilityChrome>
3063
+ );
3064
+ expect(getByTestId("observability-page-header-title")).toBeTruthy();
3065
+ expect(getByText("Recent summaries — batch 1")).toBeTruthy();
3066
+ expect(getByText("What this screen is for.")).toBeTruthy();
3067
+ expect(getByText("Header meta")).toBeTruthy();
3068
+ expect(getByText("Header action")).toBeTruthy();
3069
+ expect(getByText("Body")).toBeTruthy();
3070
+ });
3071
+
3072
+ it("hides the page header when asked", () => {
3073
+ const {queryByTestId} = renderWithTheme(
3074
+ <AiObservabilityChrome
3075
+ api={stubApi}
3076
+ config={emptyConfig}
3077
+ hideHeader
3078
+ routeBase="/admin"
3079
+ screenName="ai-datasets"
3080
+ status={localOnStatus}
3081
+ >
3082
+ <Text>Body</Text>
3083
+ </AiObservabilityChrome>
3084
+ );
3085
+ expect(queryByTestId("observability-page-header")).toBeNull();
3086
+ });
3087
+
2815
3088
  it("renders loading, error, local-on, and local-off chip states", () => {
2816
3089
  const loading = renderWithTheme(<AiObservabilityStatusChip isLoading />);
2817
3090
  expect(loading.getByText("Checking observability…")).toBeTruthy();
@@ -2820,14 +3093,10 @@ describe("AiObservabilityChrome", () => {
2820
3093
  expect(errored.getByText("Observability unavailable")).toBeTruthy();
2821
3094
 
2822
3095
  const on = renderWithTheme(<AiObservabilityStatusChip status={localOnStatus} />);
2823
- expect(
2824
- on.getByText("Local on · prompts:local · datasets:local · experiments:local")
2825
- ).toBeTruthy();
3096
+ expect(on.getByText("Local observability on")).toBeTruthy();
2826
3097
 
2827
3098
  const off = renderWithTheme(<AiObservabilityStatusChip status={localOffStatus} />);
2828
- expect(
2829
- off.getByText("Local off · prompts:langfuse · datasets:langfuse · experiments:langfuse")
2830
- ).toBeTruthy();
3099
+ expect(off.getByText("Local observability off")).toBeTruthy();
2831
3100
  });
2832
3101
 
2833
3102
  it("fetches loading and error states through the injected api", () => {
@@ -2868,9 +3137,7 @@ describe("AiObservabilityChrome", () => {
2868
3137
  }),
2869
3138
  } as unknown as AdminApi;
2870
3139
  const unwrapped = renderWithTheme(<AiObservabilityStatusChip api={unwrappedApi} />);
2871
- expect(
2872
- unwrapped.getByText("Local on · prompts:local · datasets:local · experiments:local")
2873
- ).toBeTruthy();
3140
+ expect(unwrapped.getByText("Local observability on")).toBeTruthy();
2874
3141
 
2875
3142
  const missingStatusApi = {
2876
3143
  enhanceEndpoints: () => missingStatusApi,
@@ -2911,9 +3178,7 @@ describe("AiObservabilityChrome", () => {
2911
3178
  },
2912
3179
  } as unknown as AdminApi;
2913
3180
  const fetched = renderWithTheme(<AiObservabilityStatusChip api={api} />);
2914
- expect(
2915
- fetched.getByText("Local on · prompts:local · datasets:local · experiments:local")
2916
- ).toBeTruthy();
3181
+ expect(fetched.getByText("Local observability on")).toBeTruthy();
2917
3182
  assert.deepEqual(statusQuery?.(), {method: "GET", url: "/ai/observability/status"});
2918
3183
  });
2919
3184
 
@@ -2965,6 +3230,8 @@ describe("AiObservabilityChrome", () => {
2965
3230
  "ai-prompt-editor",
2966
3231
  "ai-prompts",
2967
3232
  "ai-review",
3233
+ "ai-review-batch",
3234
+ "ai-review-batches",
2968
3235
  "ai-review-item",
2969
3236
  "ai-trace-detail",
2970
3237
  "ai-traces",
@@ -2998,6 +3265,7 @@ describe("AiPromptEditorScreen", () => {
2998
3265
  name: "summarize",
2999
3266
  relationships: emptyPromptRelationships,
3000
3267
  tags: [],
3268
+ usedBy: {items: [], limit: 20, total: 0},
3001
3269
  versions: [
3002
3270
  {
3003
3271
  config: {temperature: 0.3},
@@ -3063,6 +3331,12 @@ describe("AiPromptEditorScreen", () => {
3063
3331
 
3064
3332
  const injectedHooks = {
3065
3333
  useAiObservabilityPromptQuery: () => detailState,
3334
+ useAiObservabilityPromptsQuery: () => ({
3335
+ data: [],
3336
+ isError: false,
3337
+ isLoading: false,
3338
+ refetch: mock(() => {}),
3339
+ }),
3066
3340
  useAiObservabilityStatusQuery: () => ({
3067
3341
  data: statusData,
3068
3342
  isError: false,
@@ -3298,6 +3572,7 @@ describe("AiPromptEditorView", () => {
3298
3572
  name: "summarize",
3299
3573
  relationships: emptyPromptRelationships,
3300
3574
  tags: [],
3575
+ usedBy: {items: [], limit: 20, total: 0},
3301
3576
  versions: [
3302
3577
  {
3303
3578
  config: {temperature: 0.3},
@@ -3507,6 +3782,7 @@ describe("AiPromptPlaygroundView", () => {
3507
3782
  traces: {items: [], limit: 20, total: 0},
3508
3783
  },
3509
3784
  tags: [],
3785
+ usedBy: {items: [], limit: 20, total: 0},
3510
3786
  versions: [
3511
3787
  {
3512
3788
  config: {},
@@ -3728,7 +4004,7 @@ describe("AiPromptsListScreen", () => {
3728
4004
 
3729
4005
  listState = {data: undefined, error: {data: {}}, isError: true, isLoading: false};
3730
4006
  const errored = renderWithTheme(<AiPromptsScreenWidget {...widgetProps} />);
3731
- expect(errored.getByText("Failed to load prompts")).toBeTruthy();
4007
+ expect(errored.getByText("Could not load prompts.")).toBeTruthy();
3732
4008
  });
3733
4009
 
3734
4010
  it("filters by folder and search and retries load errors", async () => {
@@ -3736,7 +4012,8 @@ describe("AiPromptsListScreen", () => {
3736
4012
  const view = renderWithTheme(<AiPromptsScreenWidget {...widgetProps} />);
3737
4013
  fireEvent.changeText(view.getByTestId("ai-prompts-search"), "summ");
3738
4014
  await act(async () => {
3739
- fireEvent.press(view.getByTestId("ai-prompts-folder-examples"));
4015
+ // The folder picker renders above the table, so its segment is the first match.
4016
+ fireEvent.press(view.getAllByText("examples")[0]!);
3740
4017
  await Promise.resolve();
3741
4018
  });
3742
4019
  expect(view.getByTestId("ai-prompts-table")).toBeTruthy();
@@ -3744,7 +4021,7 @@ describe("AiPromptsListScreen", () => {
3744
4021
  listState = {data: undefined, error: {data: {}}, isError: true, isLoading: false};
3745
4022
  const errored = renderWithTheme(<AiPromptsScreenWidget {...widgetProps} />);
3746
4023
  await act(async () => {
3747
- fireEvent.press(errored.getByText("Retry"));
4024
+ fireEvent.press(errored.getByText("Try again"));
3748
4025
  await Promise.resolve();
3749
4026
  });
3750
4027
  listState = {data: loaded, error: undefined, isError: false, isLoading: false};
@@ -3832,11 +4109,11 @@ describe("AiPromptsListView", () => {
3832
4109
  />
3833
4110
  );
3834
4111
  expect(getByTestId("ai-prompts-empty")).toBeTruthy();
3835
- expect(getByText("No prompts in this folder yet.")).toBeTruthy();
4112
+ expect(getByText("No prompts yet")).toBeTruthy();
3836
4113
  });
3837
4114
 
3838
- it("renders a loaded table with folder counts and latest vs production columns", () => {
3839
- const {getByTestId, getByText} = renderWithTheme(
4115
+ it("renders a loaded table with folder counts and newest vs production columns", () => {
4116
+ const {getAllByText, getByTestId, getByText} = renderWithTheme(
3840
4117
  <AiPromptsListView
3841
4118
  createDescription=""
3842
4119
  createFolder="examples"
@@ -3851,9 +4128,11 @@ describe("AiPromptsListView", () => {
3851
4128
  />
3852
4129
  );
3853
4130
  expect(getByTestId("ai-prompts-table")).toBeTruthy();
3854
- expect(getByText("All (1)")).toBeTruthy();
3855
- expect(getByText("examples (1)")).toBeTruthy();
3856
- expect(getByText("examples/summarize")).toBeTruthy();
4131
+ expect(getByTestId("ai-prompts-folders")).toBeTruthy();
4132
+ expect(getByText("All")).toBeTruthy();
4133
+ // Folder segment plus the row's folder line.
4134
+ assert.isAtLeast(getAllByText("examples").length, 2);
4135
+ expect(getByText("summarize")).toBeTruthy();
3857
4136
  expect(getByText("v2")).toBeTruthy();
3858
4137
  expect(getByText("v1")).toBeTruthy();
3859
4138
  });
@@ -3881,7 +4160,7 @@ describe("AiPromptsListView", () => {
3881
4160
  const onSearchChange = mock(() => undefined);
3882
4161
  const onCreate = mock(() => undefined);
3883
4162
  const onRetry = mock(() => undefined);
3884
- const {getByTestId, getByText} = renderWithTheme(
4163
+ const {getAllByText, getByTestId, getByText} = renderWithTheme(
3885
4164
  <AiPromptsListView
3886
4165
  createDescription="Short summary"
3887
4166
  createError="Name required"
@@ -3891,7 +4170,7 @@ describe("AiPromptsListView", () => {
3891
4170
  createSystem="You are helpful"
3892
4171
  createTemplate="Hi {{name}}"
3893
4172
  folder=""
3894
- loadError="Failed to load prompts"
4173
+ loadError="Could not load prompts."
3895
4174
  onCreate={onCreate}
3896
4175
  onCreateDescriptionChange={() => undefined}
3897
4176
  onCreateFolderChange={() => undefined}
@@ -3911,12 +4190,12 @@ describe("AiPromptsListView", () => {
3911
4190
  fireEvent.changeText(getByTestId("ai-prompts-search"), "note");
3912
4191
  assert.isAtLeast(onSearchChange.mock.calls.length, 1);
3913
4192
  await act(async () => {
3914
- fireEvent.press(getByTestId("ai-prompts-folder-examples"));
4193
+ fireEvent.press(getAllByText("examples")[0]!);
3915
4194
  await Promise.resolve();
3916
4195
  });
3917
4196
  assert.isAtLeast(onFolderChange.mock.calls.length, 1);
3918
4197
  await act(async () => {
3919
- fireEvent.press(getByText("Retry"));
4198
+ fireEvent.press(getByText("Try again"));
3920
4199
  await Promise.resolve();
3921
4200
  });
3922
4201
  assert.equal(onRetry.mock.calls.length, 1);
@@ -3977,6 +4256,12 @@ describe("AiReviewItemScreen", () => {
3977
4256
  options?.currentUserId === "" ? undefined : {id: options?.currentUserId ?? "user-1"},
3978
4257
  isLoading: false,
3979
4258
  }),
4259
+ useAiObservabilityReviewBatchQueueQuery: () => ({
4260
+ data: undefined,
4261
+ isError: false,
4262
+ isLoading: false,
4263
+ refetch: mock(() => {}),
4264
+ }),
3980
4265
  useAiObservabilityReviewItemQuery: () => ({
3981
4266
  data: detail,
3982
4267
  isError: false,
@@ -4018,6 +4303,12 @@ describe("AiReviewItemScreen", () => {
4018
4303
  enhanceEndpoints: () => loadingApi,
4019
4304
  injectEndpoints: () => ({
4020
4305
  useAiObservabilityCurrentUserQuery: () => ({data: undefined, isLoading: false}),
4306
+ useAiObservabilityReviewBatchQueueQuery: () => ({
4307
+ data: undefined,
4308
+ isError: false,
4309
+ isLoading: false,
4310
+ refetch: mock(() => {}),
4311
+ }),
4021
4312
  useAiObservabilityReviewItemQuery: () => ({
4022
4313
  data: undefined,
4023
4314
  isError: false,
@@ -4061,7 +4352,7 @@ describe("AiReviewItemScreen", () => {
4061
4352
  />
4062
4353
  );
4063
4354
  expect(loaded.getByTestId("ai-review-item")).toBeTruthy();
4064
- expect(loaded.getByTestId("ai-review-score-boolean-correct")).toBeTruthy();
4355
+ expect(loaded.getByTestId("ai-review-question-correct")).toBeTruthy();
4065
4356
  });
4066
4357
 
4067
4358
  it("requires scores before submit and submits on pass", async () => {
@@ -4078,10 +4369,10 @@ describe("AiReviewItemScreen", () => {
4078
4369
  fireEvent.press(view.getByTestId("ai-review-submit-next"));
4079
4370
  await Promise.resolve();
4080
4371
  });
4081
- expect(view.getByText("Score correct before submitting.")).toBeTruthy();
4372
+ expect(view.getByText(`Answer "correct" before submitting.`)).toBeTruthy();
4082
4373
 
4083
4374
  await act(async () => {
4084
- fireEvent.press(view.getByTestId("ai-review-score-correct-pass"));
4375
+ fireEvent.press(view.getByTestId("ai-review-question-correct-yes"));
4085
4376
  await Promise.resolve();
4086
4377
  });
4087
4378
  await act(async () => {
@@ -4110,6 +4401,12 @@ describe("AiReviewItemScreen", () => {
4110
4401
  enhanceEndpoints: () => errorApi,
4111
4402
  injectEndpoints: () => ({
4112
4403
  useAiObservabilityCurrentUserQuery: () => ({data: {id: "user-1"}, isLoading: false}),
4404
+ useAiObservabilityReviewBatchQueueQuery: () => ({
4405
+ data: undefined,
4406
+ isError: false,
4407
+ isLoading: false,
4408
+ refetch: mock(() => {}),
4409
+ }),
4113
4410
  useAiObservabilityReviewItemQuery: () => ({
4114
4411
  data: undefined,
4115
4412
  isError: true,
@@ -4142,7 +4439,7 @@ describe("AiReviewItemScreen", () => {
4142
4439
  />
4143
4440
  );
4144
4441
  await act(async () => {
4145
- fireEvent.press(errored.getByText("Retry"));
4442
+ fireEvent.press(errored.getByTestId("ai-review-item-error-retry"));
4146
4443
  await new Promise((resolve) => setTimeout(resolve, 100));
4147
4444
  });
4148
4445
  assert.isAtLeast(refetch.mock.calls.length, 1);
@@ -4217,6 +4514,12 @@ describe("AiReviewItemScreen", () => {
4217
4514
  enhanceEndpoints: () => twoPendingApi,
4218
4515
  injectEndpoints: () => ({
4219
4516
  useAiObservabilityCurrentUserQuery: () => ({data: {id: "user-1"}, isLoading: false}),
4517
+ useAiObservabilityReviewBatchQueueQuery: () => ({
4518
+ data: undefined,
4519
+ isError: false,
4520
+ isLoading: false,
4521
+ refetch: mock(() => {}),
4522
+ }),
4220
4523
  useAiObservabilityReviewItemQuery: () => ({
4221
4524
  data: detail,
4222
4525
  isError: false,
@@ -4261,7 +4564,7 @@ describe("AiReviewItemScreen", () => {
4261
4564
 
4262
4565
  actionImpl.mockClear();
4263
4566
  await act(async () => {
4264
- fireEvent.press(view.getByTestId("ai-review-score-correct-pass"));
4567
+ fireEvent.press(view.getByTestId("ai-review-question-correct-yes"));
4265
4568
  await Promise.resolve();
4266
4569
  });
4267
4570
  await act(async () => {
@@ -4274,6 +4577,88 @@ describe("AiReviewItemScreen", () => {
4274
4577
  });
4275
4578
  assert.isAtLeast(actionImpl.mock.calls.length, 1);
4276
4579
  });
4580
+
4581
+ it("walks pending and in-progress items of the item's batch", async () => {
4582
+ const batchItem = (id: string, status: ReviewListItem["status"]): ReviewListItem => ({
4583
+ batchId: "b1",
4584
+ enqueuedAt: "2026-01-01T00:00:00.000Z",
4585
+ evaluatorId: "eval-1",
4586
+ id,
4587
+ reason: "manual",
4588
+ status,
4589
+ traceId: `trace-${id}`,
4590
+ traceName: "summarize",
4591
+ });
4592
+ const batchQueueArgs: unknown[] = [];
4593
+ // One object across renders, like RTK Query's cached data; a new one each render loops the reset effect.
4594
+ const batchDetail = {...detail, batchId: "b1"};
4595
+ const batchApi = {
4596
+ enhanceEndpoints: () => batchApi,
4597
+ injectEndpoints: () => ({
4598
+ useAiObservabilityCurrentUserQuery: () => ({data: {id: "user-1"}, isLoading: false}),
4599
+ useAiObservabilityReviewBatchQueueQuery: (args: unknown) => {
4600
+ batchQueueArgs.push(args);
4601
+ return {
4602
+ data: {
4603
+ data: [
4604
+ batchItem("rev-1", "pending"),
4605
+ batchItem("rev-2", "in_progress"),
4606
+ batchItem("rev-3", "done"),
4607
+ ],
4608
+ },
4609
+ isError: false,
4610
+ isLoading: false,
4611
+ refetch: mock(() => {}),
4612
+ };
4613
+ },
4614
+ useAiObservabilityReviewItemQuery: () => ({
4615
+ data: batchDetail,
4616
+ isError: false,
4617
+ isLoading: false,
4618
+ refetch: mock(() => {}),
4619
+ }),
4620
+ useAiObservabilityReviewQuery: () => ({
4621
+ data: {data: []},
4622
+ isError: false,
4623
+ isLoading: false,
4624
+ refetch: mock(() => {}),
4625
+ }),
4626
+ useAiObservabilityStatusQuery: () => ({
4627
+ data: statusData,
4628
+ isError: false,
4629
+ isLoading: false,
4630
+ }),
4631
+ useUpdateAiObservabilityReviewItemMutation: () => [
4632
+ () => ({unwrap: actionImpl}),
4633
+ {isError: false, isLoading: false},
4634
+ ],
4635
+ }),
4636
+ } as unknown as AdminApi;
4637
+
4638
+ routerPush.mockClear();
4639
+ actionImpl.mockClear();
4640
+ const view = renderWithTheme(
4641
+ <AiReviewItemScreenWidget
4642
+ api={batchApi}
4643
+ config={emptyConfig}
4644
+ routeBase="/admin"
4645
+ screenName="ai-review-item"
4646
+ />
4647
+ );
4648
+ expect(batchQueueArgs.at(-1)).toEqual({batchId: "b1"});
4649
+ expect(view.getByText("Item 1 of 2")).toBeTruthy();
4650
+
4651
+ await act(async () => {
4652
+ fireEvent.press(view.getByTestId("ai-review-question-correct-yes"));
4653
+ await Promise.resolve();
4654
+ });
4655
+ await act(async () => {
4656
+ fireEvent.press(view.getByTestId("ai-review-submit-next"));
4657
+ await new Promise((resolve) => setTimeout(resolve, 50));
4658
+ });
4659
+ assert.equal(actionImpl.mock.calls.length, 1);
4660
+ assert.equal(String(routerPush.mock.calls.at(-1)?.[0]), "/admin/ai-review-item?id=rev-2");
4661
+ });
4277
4662
  });
4278
4663
  });
4279
4664
 
@@ -4304,18 +4689,16 @@ describe("AiReviewItemView", () => {
4304
4689
  <AiReviewItemView
4305
4690
  comment=""
4306
4691
  detail={detail}
4307
- isPending
4308
4692
  onAssign={() => undefined}
4309
4693
  onCommentChange={() => undefined}
4310
4694
  onScoreChange={() => undefined}
4311
4695
  onSkip={() => undefined}
4312
4696
  onSubmit={() => undefined}
4313
- position={1}
4314
4697
  scores={{}}
4315
- totalPending={2}
4316
4698
  />
4317
4699
  );
4318
- expect(getByText("Item 1 of 2 pending")).toBeTruthy();
4700
+ expect(reviewItemTitle({isPending: true, position: 1, totalPending: 2})).toBe("Item 1 of 2");
4701
+ expect(reviewItemTitle({isPending: false, position: 1, totalPending: 0})).toBe("Review item");
4319
4702
  expect(getByText("45 words")).toBeTruthy();
4320
4703
  expect(queryByText(longInput)).toBeNull();
4321
4704
  expect(getByTestId("ai-review-raw-json")).toBeTruthy();
@@ -4332,15 +4715,12 @@ describe("AiReviewItemView", () => {
4332
4715
  <AiReviewItemView
4333
4716
  comment=""
4334
4717
  detail={detail}
4335
- isPending
4336
4718
  onAssign={onAssign}
4337
4719
  onCommentChange={() => undefined}
4338
4720
  onScoreChange={() => undefined}
4339
4721
  onSkip={onSkip}
4340
4722
  onSubmit={onSubmit}
4341
- position={1}
4342
4723
  scores={{correct: true}}
4343
- totalPending={1}
4344
4724
  />
4345
4725
  );
4346
4726
  await act(async () => {
@@ -4359,24 +4739,25 @@ describe("AiReviewItemView", () => {
4359
4739
  const onPrevious = mock(() => undefined);
4360
4740
  const onCommentChange = mock(() => undefined);
4361
4741
  const {getByTestId, getByText} = renderWithTheme(
4362
- <AiReviewItemView
4363
- comment="needs work"
4364
- detail={{...detail, status: "done"}}
4365
- isPending={false}
4366
- onAssign={() => undefined}
4367
- onCommentChange={onCommentChange}
4368
- onNext={onNext}
4369
- onPrevious={onPrevious}
4370
- onScoreChange={() => undefined}
4371
- onSkip={() => undefined}
4372
- onSubmit={() => undefined}
4373
- position={1}
4374
- scores={{correct: true}}
4375
- submitError="Could not submit this review."
4376
- totalPending={0}
4377
- />
4378
- );
4379
- expect(getByText(/not in pending queue/)).toBeTruthy();
4742
+ <>
4743
+ <AiReviewItemHeaderMeta detail={{...detail, status: "done"}} isPending={false} />
4744
+ <AiReviewItemNav onNext={onNext} onPrevious={onPrevious} />
4745
+ <AiReviewItemView
4746
+ comment="needs work"
4747
+ detail={{...detail, status: "done"}}
4748
+ onAssign={() => undefined}
4749
+ onCommentChange={onCommentChange}
4750
+ onScoreChange={() => undefined}
4751
+ onSkip={() => undefined}
4752
+ onSubmit={() => undefined}
4753
+ scores={{correct: true}}
4754
+ submitError="Could not submit this review."
4755
+ />
4756
+ </>
4757
+ );
4758
+ expect(getByText("Not in the pending queue")).toBeTruthy();
4759
+ expect(getByText("From a trace")).toBeTruthy();
4760
+ expect(getByTestId("ai-review-item-status")).toBeTruthy();
4380
4761
  await act(async () => {
4381
4762
  fireEvent.press(getByText("Previous"));
4382
4763
  fireEvent.press(getByText("Next"));
@@ -4392,22 +4773,22 @@ describe("AiReviewItemView", () => {
4392
4773
  it("scores boolean dimensions when navigation handlers are absent", async () => {
4393
4774
  const onScoreChange = mock(() => undefined);
4394
4775
  const {getByTestId, getByText, UNSAFE_root} = renderWithTheme(
4395
- <AiReviewItemView
4396
- comment=""
4397
- detail={detail}
4398
- isPending
4399
- onAssign={() => undefined}
4400
- onCommentChange={() => undefined}
4401
- onScoreChange={onScoreChange}
4402
- onSkip={() => undefined}
4403
- onSubmit={() => undefined}
4404
- position={1}
4405
- scores={{}}
4406
- totalPending={1}
4407
- />
4776
+ <>
4777
+ <AiReviewItemNav />
4778
+ <AiReviewItemView
4779
+ comment=""
4780
+ detail={detail}
4781
+ onAssign={() => undefined}
4782
+ onCommentChange={() => undefined}
4783
+ onScoreChange={onScoreChange}
4784
+ onSkip={() => undefined}
4785
+ onSubmit={() => undefined}
4786
+ scores={{}}
4787
+ />
4788
+ </>
4408
4789
  );
4409
4790
  await act(async () => {
4410
- fireEvent.press(getByTestId("ai-review-score-correct-pass"));
4791
+ fireEvent.press(getByTestId("ai-review-question-correct-yes"));
4411
4792
  await Promise.resolve();
4412
4793
  });
4413
4794
  assert.isAtLeast(onScoreChange.mock.calls.length, 1);
@@ -4430,15 +4811,12 @@ describe("AiReviewItemView", () => {
4430
4811
  <AiReviewItemView
4431
4812
  comment=""
4432
4813
  detail={detail}
4433
- isPending
4434
4814
  onAssign={() => undefined}
4435
4815
  onCommentChange={() => undefined}
4436
4816
  onScoreChange={() => undefined}
4437
4817
  onSkip={() => undefined}
4438
4818
  onSubmit={() => undefined}
4439
- position={1}
4440
4819
  scores={{}}
4441
- totalPending={1}
4442
4820
  />
4443
4821
  );
4444
4822
  await act(async () => {
@@ -4463,19 +4841,18 @@ describe("AiReviewItemView", () => {
4463
4841
  <AiReviewItemView
4464
4842
  comment=""
4465
4843
  detail={multiDetail}
4466
- isPending
4467
4844
  isSaving
4468
4845
  onAssign={() => undefined}
4469
4846
  onCommentChange={() => undefined}
4470
4847
  onScoreChange={onScoreChange}
4471
4848
  onSkip={() => undefined}
4472
4849
  onSubmit={() => undefined}
4473
- position={2}
4474
4850
  scores={{correct: true, helpfulness: 0.7}}
4475
- totalPending={3}
4476
4851
  />
4477
4852
  );
4478
- expect(getByText("Item 2 of 3 pending")).toBeTruthy();
4853
+ // Scores without question text are labelled by their humanized key, not "2. helpfulness".
4854
+ expect(getByText("Helpfulness")).toBeTruthy();
4855
+ expect(queryByText("2. helpfulness")).toBeNull();
4479
4856
  expect(queryByText("Mark correct only when grounded.")).toBeNull();
4480
4857
  await act(async () => {
4481
4858
  fireEvent.press(getByTestId("ai-review-score-tone-safe"));
@@ -4527,6 +4904,12 @@ describe("AiReviewQueueScreen", () => {
4527
4904
  const api = {
4528
4905
  enhanceEndpoints: () => api,
4529
4906
  injectEndpoints: () => ({
4907
+ useAiObservabilityEvaluatorsQuery: () => ({
4908
+ data: [{dimensions: [], id: "eval-1", name: "summary-questions", type: "human"}],
4909
+ isError: false,
4910
+ isLoading: false,
4911
+ refetch: mock(() => {}),
4912
+ }),
4530
4913
  useAiObservabilityReviewQuery: () => listState,
4531
4914
  useAiObservabilityStatusQuery: () => ({
4532
4915
  data: statusData,
@@ -4552,11 +4935,22 @@ describe("AiReviewQueueScreen", () => {
4552
4935
  />
4553
4936
  );
4554
4937
  expect(view.getByTestId("ai-review-table")).toBeTruthy();
4938
+ expect(view.getByText("summary-questions")).toBeTruthy();
4939
+ expect(
4940
+ view.getByText(
4941
+ "Answer yes or no questions about AI outputs, oldest first. Items arrive from Traces and from review batches."
4942
+ )
4943
+ ).toBeTruthy();
4555
4944
  await act(async () => {
4556
4945
  fireEvent.press(view.getByTestId("ai-review-start-oldest"));
4557
4946
  await new Promise((resolve) => setTimeout(resolve, 50));
4558
4947
  });
4559
4948
  assert.include(String(routerPush.mock.calls[0]?.[0]), "ai-review-item");
4949
+ await act(async () => {
4950
+ fireEvent.press(view.getByTestId("ai-review-open-batches"));
4951
+ await new Promise((resolve) => setTimeout(resolve, 50));
4952
+ });
4953
+ assert.include(String(routerPush.mock.calls.at(-1)?.[0]), "ai-review-batches");
4560
4954
  });
4561
4955
  });
4562
4956
  });
@@ -4579,40 +4973,49 @@ describe("AiReviewQueueView", () => {
4579
4973
  };
4580
4974
 
4581
4975
  describe("AiReviewQueueView", () => {
4582
- it("names both review intake paths in the empty state", () => {
4976
+ it("names both review intake paths in the empty state and links to Traces", async () => {
4977
+ const onOpenTraces = mock(() => undefined);
4583
4978
  const {getByTestId, getByText} = renderWithTheme(
4584
4979
  <AiReviewQueueView
4585
4980
  counts={counts}
4586
4981
  items={[]}
4587
4982
  onOpenItem={() => undefined}
4983
+ onOpenTraces={onOpenTraces}
4588
4984
  onRetry={() => undefined}
4589
- onStart={() => undefined}
4590
4985
  onStatusChange={() => undefined}
4591
4986
  status="pending"
4592
4987
  />
4593
4988
  );
4594
4989
  expect(getByTestId("ai-review-empty")).toBeTruthy();
4595
- expect(getByText(/Traces bulk action/)).toBeTruthy();
4596
- expect(getByText(/Assign to me for manual assignment/)).toBeTruthy();
4990
+ expect(getByText(/send them to human review, or start a review batch/)).toBeTruthy();
4991
+ await act(async () => {
4992
+ fireEvent.press(getByTestId("ai-review-empty-action"));
4993
+ await new Promise((resolve) => setTimeout(resolve, 50));
4994
+ });
4995
+ expect(onOpenTraces).toHaveBeenCalled();
4597
4996
  });
4598
4997
 
4599
4998
  it("renders oldest-first row fields and starts reviewing", async () => {
4600
4999
  const onStart = mock(() => undefined);
4601
- const {getByTestId, getByText} = renderWithTheme(
4602
- <AiReviewQueueView
4603
- counts={{...counts, pending: 1}}
4604
- items={[item]}
4605
- onOpenItem={() => undefined}
4606
- onRetry={() => undefined}
4607
- onStart={onStart}
4608
- onStatusChange={() => undefined}
4609
- status="pending"
4610
- />
5000
+ const {getByTestId, getByText, queryByText} = renderWithTheme(
5001
+ <>
5002
+ <AiReviewQueueActions canStart onStart={onStart} />
5003
+ <AiReviewQueueView
5004
+ counts={{...counts, pending: 1}}
5005
+ items={[item, {...item, batchId: "b1", id: "review-item-2", outputPreview: "Short"}]}
5006
+ onOpenItem={() => undefined}
5007
+ onRetry={() => undefined}
5008
+ onStatusChange={() => undefined}
5009
+ status="pending"
5010
+ />
5011
+ </>
4611
5012
  );
4612
5013
  expect(getByTestId("ai-review-table")).toBeTruthy();
4613
- expect(getByText("generate summary")).toBeTruthy();
4614
- expect(getByText("summarize")).toBeTruthy();
4615
- expect(getByText("Unassigned")).toBeTruthy();
5014
+ expect(getByTestId("ai-review-open-review-item-1")).toBeTruthy();
5015
+ expect(getByText("From Traces")).toBeTruthy();
5016
+ expect(getByText("Short")).toBeTruthy();
5017
+ expect(getByText("Review oldest pending")).toBeTruthy();
5018
+ expect(queryByText("Open")).toBeNull();
4616
5019
  await act(async () => {
4617
5020
  fireEvent.press(getByTestId("ai-review-start-oldest"));
4618
5021
  await new Promise((resolve) => setTimeout(resolve, 50));
@@ -4620,6 +5023,26 @@ describe("AiReviewQueueView", () => {
4620
5023
  expect(onStart).toHaveBeenCalled();
4621
5024
  });
4622
5025
 
5026
+ it("labels where each untitled review item came from", () => {
5027
+ const {getByText} = renderWithTheme(
5028
+ <AiReviewQueueView
5029
+ counts={{...counts, pending: 3}}
5030
+ items={[
5031
+ {...item, batchId: "b1", id: "review-item-batch"},
5032
+ {...item, id: "review-item-eval", reason: "eval"},
5033
+ {...item, id: "review-item-other", reason: "other"},
5034
+ ]}
5035
+ onOpenItem={() => undefined}
5036
+ onRetry={() => undefined}
5037
+ onStatusChange={() => undefined}
5038
+ status="pending"
5039
+ />
5040
+ );
5041
+ expect(getByText("From a review batch")).toBeTruthy();
5042
+ expect(getByText("From an experiment")).toBeTruthy();
5043
+ expect(getByText("From Traces")).toBeTruthy();
5044
+ });
5045
+
4623
5046
  it("renders loading, error retry, status tabs, and open controls", async () => {
4624
5047
  const onRetry = mock(() => undefined);
4625
5048
  const onStatusChange = mock(() => undefined);
@@ -4631,7 +5054,6 @@ describe("AiReviewQueueView", () => {
4631
5054
  items={[]}
4632
5055
  onOpenItem={onOpenItem}
4633
5056
  onRetry={onRetry}
4634
- onStart={() => undefined}
4635
5057
  onStatusChange={onStatusChange}
4636
5058
  status="pending"
4637
5059
  />
@@ -4645,24 +5067,23 @@ describe("AiReviewQueueView", () => {
4645
5067
  items={[]}
4646
5068
  onOpenItem={onOpenItem}
4647
5069
  onRetry={onRetry}
4648
- onStart={() => undefined}
4649
5070
  onStatusChange={onStatusChange}
4650
5071
  status="pending"
4651
5072
  />
4652
5073
  );
5074
+ expect(errored.getByText("Could not load the review queue.")).toBeTruthy();
4653
5075
  await act(async () => {
4654
- fireEvent.press(errored.getByText("Retry"));
4655
- await Promise.resolve();
5076
+ fireEvent.press(errored.getByTestId("ai-review-error-retry"));
5077
+ await new Promise((resolve) => setTimeout(resolve, 50));
4656
5078
  });
4657
5079
  expect(onRetry).toHaveBeenCalled();
4658
5080
 
4659
- const {getByText} = renderWithTheme(
5081
+ const {getByTestId, getByText} = renderWithTheme(
4660
5082
  <AiReviewQueueView
4661
5083
  counts={{...counts, done: 1, pending: 1}}
4662
5084
  items={[item]}
4663
5085
  onOpenItem={onOpenItem}
4664
5086
  onRetry={onRetry}
4665
- onStart={() => undefined}
4666
5087
  onStatusChange={onStatusChange}
4667
5088
  status="pending"
4668
5089
  />
@@ -4673,10 +5094,10 @@ describe("AiReviewQueueView", () => {
4673
5094
  });
4674
5095
  assert.isAtLeast(onStatusChange.mock.calls.length, 1);
4675
5096
  await act(async () => {
4676
- fireEvent.press(getByText("Open"));
5097
+ fireEvent.press(getByTestId("ai-review-open-review-item-1"));
4677
5098
  await Promise.resolve();
4678
5099
  });
4679
- expect(onOpenItem).toHaveBeenCalled();
5100
+ expect(onOpenItem).toHaveBeenCalledWith("review-item-1");
4680
5101
  });
4681
5102
  });
4682
5103
  });
@@ -5268,22 +5689,14 @@ describe("AiTracesListScreen", () => {
5268
5689
  fireEvent.press(view.getByTestId("ai-traces-clear-selection"));
5269
5690
  await Promise.resolve();
5270
5691
  });
5271
- const filterFields = view.UNSAFE_root.findAllByType(SelectField);
5272
- const promptFilter = filterFields.find(
5273
- (field) => field.props.testID === "ai-traces-filter-prompt"
5274
- );
5275
- const scoreFilter = filterFields.find(
5276
- (field) => field.props.testID === "ai-traces-filter-has-score"
5277
- );
5278
- const sensitiveFilter = filterFields.find(
5279
- (field) => field.props.testID === "ai-traces-filter-sensitive"
5280
- );
5281
- assert.isDefined(promptFilter);
5282
- assert.isDefined(scoreFilter);
5283
- assert.isDefined(sensitiveFilter);
5284
- fireEvent(promptFilter!, "onChange", "summarize");
5285
- fireEvent(scoreFilter!, "onChange", "false");
5286
- fireEvent(sensitiveFilter!, "onChange", "true");
5692
+ await act(async () => {
5693
+ fireEvent(view.getByTestId("ai-traces-table"), "filterValuesChange", {
5694
+ hasScore: false,
5695
+ prompt: ["summarize"],
5696
+ sensitive: true,
5697
+ });
5698
+ await Promise.resolve();
5699
+ });
5287
5700
  expect(view.getByTestId("ai-traces-pagination")).toBeTruthy();
5288
5701
  listState = {
5289
5702
  data: {data: loaded, limit: 20, more: false, page: 1, total: 1},
@@ -5292,10 +5705,11 @@ describe("AiTracesListScreen", () => {
5292
5705
  };
5293
5706
  });
5294
5707
 
5295
- it("surfaces list load error in the bulk bar", () => {
5708
+ it("surfaces a list load error with Try again", () => {
5296
5709
  listState = {data: undefined, isError: true, isLoading: false};
5297
5710
  const view = renderWithTheme(<AiTracesScreenWidget {...widgetProps} />);
5298
- expect(view.getByText("Failed to load traces.")).toBeTruthy();
5711
+ expect(view.getByText("Could not load traces.")).toBeTruthy();
5712
+ expect(view.getByTestId("ai-traces-load-error-retry")).toBeTruthy();
5299
5713
  listState = {
5300
5714
  data: {data: loaded, limit: 20, more: false, page: 1, total: 1},
5301
5715
  isError: false,
@@ -5416,12 +5830,12 @@ describe("AiTracesListView", () => {
5416
5830
  onDismissReviewModal: () => undefined,
5417
5831
  onEnqueueReview: () => undefined,
5418
5832
  onEvaluatorChange: () => undefined,
5419
- onFiltersChange: () => undefined,
5833
+ onFilterValuesChange: () => undefined,
5420
5834
  onOpenAddToDataset: () => undefined,
5421
5835
  onOpenReview: () => undefined,
5422
5836
  onOpenTrace: () => undefined,
5423
5837
  onPageChange: () => undefined,
5424
- onRunTestMultiStage: () => undefined,
5838
+ onSortChange: () => undefined,
5425
5839
  onToggleSelect: () => undefined,
5426
5840
  };
5427
5841
 
@@ -5441,7 +5855,7 @@ describe("AiTracesListView", () => {
5441
5855
  {...datasetDefaults}
5442
5856
  evaluatorId=""
5443
5857
  evaluators={[]}
5444
- filters={emptyTraceFilters()}
5858
+ filterValues={{}}
5445
5859
  page={1}
5446
5860
  selectedIds={[]}
5447
5861
  showMultiStageTest
@@ -5451,26 +5865,31 @@ describe("AiTracesListView", () => {
5451
5865
  />
5452
5866
  );
5453
5867
  expect(getByTestId("ai-traces-empty")).toBeTruthy();
5454
- expect(getByText("No traces match these filters.")).toBeTruthy();
5868
+ expect(getByText("No traces yet")).toBeTruthy();
5455
5869
  });
5456
5870
 
5457
- it("runs the multi-stage trace smoke action", async () => {
5458
- const onRunTestMultiStage = mock(() => undefined);
5459
- const {getByTestId} = renderWithTheme(
5871
+ it("says no traces match when filters are applied", () => {
5872
+ const {getByText} = renderWithTheme(
5460
5873
  <AiTracesListView
5461
5874
  {...datasetDefaults}
5462
5875
  evaluatorId=""
5463
5876
  evaluators={[]}
5464
- filters={emptyTraceFilters()}
5877
+ filterValues={{status: ["error"]}}
5465
5878
  page={1}
5466
5879
  selectedIds={[]}
5467
- showMultiStageTest
5468
5880
  total={0}
5469
5881
  traces={[]}
5470
5882
  {...idleHandlers}
5471
- onRunTestMultiStage={onRunTestMultiStage}
5472
5883
  />
5473
5884
  );
5885
+ expect(getByText("No traces match these filters")).toBeTruthy();
5886
+ });
5887
+
5888
+ it("runs the test trace from the header action", async () => {
5889
+ const onRunTestMultiStage = mock(() => undefined);
5890
+ const {getByTestId} = renderWithTheme(
5891
+ <AiTracesHeaderActions onRunTestMultiStage={onRunTestMultiStage} showMultiStageTest />
5892
+ );
5474
5893
 
5475
5894
  await act(async () => {
5476
5895
  fireEvent.press(getByTestId("ai-traces-run-multi-stage"));
@@ -5480,14 +5899,24 @@ describe("AiTracesListView", () => {
5480
5899
  assert.equal(onRunTestMultiStage.mock.calls.length, 1);
5481
5900
  });
5482
5901
 
5483
- it("disables the multi-stage action and explains why when it is blocked", () => {
5902
+ it("disables the test trace action and explains why when it is blocked", () => {
5484
5903
  const onRunTestMultiStage = mock(() => undefined);
5485
- const {getByTestId} = renderWithTheme(
5904
+ const header = renderWithTheme(
5905
+ <AiTracesHeaderActions
5906
+ multiStageBlockedMessage="Save a Gemini API key on Profile."
5907
+ onRunTestMultiStage={onRunTestMultiStage}
5908
+ showMultiStageTest
5909
+ />
5910
+ );
5911
+ expect(header.getByTestId("ai-traces-run-multi-stage")).toBeDisabled();
5912
+ assert.equal(onRunTestMultiStage.mock.calls.length, 0);
5913
+
5914
+ const body = renderWithTheme(
5486
5915
  <AiTracesListView
5487
5916
  {...datasetDefaults}
5488
5917
  evaluatorId=""
5489
5918
  evaluators={[]}
5490
- filters={emptyTraceFilters()}
5919
+ filterValues={{}}
5491
5920
  multiStageBlockedMessage="Save a Gemini API key on Profile."
5492
5921
  page={1}
5493
5922
  selectedIds={[]}
@@ -5495,42 +5924,28 @@ describe("AiTracesListView", () => {
5495
5924
  total={0}
5496
5925
  traces={[]}
5497
5926
  {...idleHandlers}
5498
- onRunTestMultiStage={onRunTestMultiStage}
5499
5927
  />
5500
5928
  );
5501
-
5502
- expect(getByTestId("ai-traces-multi-stage-blocked")).toHaveTextContent(
5929
+ expect(body.getByTestId("ai-traces-multi-stage-blocked")).toHaveTextContent(
5503
5930
  "Save a Gemini API key on Profile."
5504
5931
  );
5505
- expect(getByTestId("ai-traces-run-multi-stage")).toBeDisabled();
5506
- assert.equal(onRunTestMultiStage.mock.calls.length, 0);
5507
5932
  });
5508
5933
 
5509
- it("hides the multi-stage smoke action without local trace storage", () => {
5934
+ it("hides the test trace action without local trace storage", () => {
5510
5935
  const {queryByTestId} = renderWithTheme(
5511
- <AiTracesListView
5512
- {...datasetDefaults}
5513
- evaluatorId=""
5514
- evaluators={[]}
5515
- filters={emptyTraceFilters()}
5516
- page={1}
5517
- selectedIds={[]}
5518
- total={0}
5519
- traces={[]}
5520
- {...idleHandlers}
5521
- />
5936
+ <AiTracesHeaderActions onRunTestMultiStage={() => undefined} />
5522
5937
  );
5523
5938
 
5524
5939
  assert.notExists(queryByTestId("ai-traces-run-multi-stage"));
5525
5940
  });
5526
5941
 
5527
- it("renders an error row with the error line and prompt count", () => {
5942
+ it("renders an error row with the error line and step count", () => {
5528
5943
  const {getByText} = renderWithTheme(
5529
5944
  <AiTracesListView
5530
5945
  {...datasetDefaults}
5531
5946
  evaluatorId=""
5532
5947
  evaluators={[]}
5533
- filters={emptyTraceFilters()}
5948
+ filterValues={{}}
5534
5949
  page={1}
5535
5950
  selectedIds={[]}
5536
5951
  total={1}
@@ -5539,17 +5954,17 @@ describe("AiTracesListView", () => {
5539
5954
  />
5540
5955
  );
5541
5956
  expect(getByText("model timeout")).toBeTruthy();
5542
- expect(getByText("2")).toBeTruthy();
5957
+ expect(getByText("1 step")).toBeTruthy();
5543
5958
  expect(getByText("failed-call")).toBeTruthy();
5544
5959
  });
5545
5960
 
5546
- it("uses distinct primary and accent colors for prompt-run status dots", () => {
5547
- const {getByLabelText, getByTestId} = renderWithTheme(
5961
+ it("uses the shared OK and Error status badges", () => {
5962
+ const {getByTestId, getByText} = renderWithTheme(
5548
5963
  <AiTracesListView
5549
5964
  {...datasetDefaults}
5550
5965
  evaluatorId=""
5551
5966
  evaluators={[]}
5552
- filters={emptyTraceFilters()}
5967
+ filterValues={{}}
5553
5968
  page={1}
5554
5969
  selectedIds={[]}
5555
5970
  total={2}
@@ -5557,14 +5972,10 @@ describe("AiTracesListView", () => {
5557
5972
  {...idleHandlers}
5558
5973
  />
5559
5974
  );
5560
- const primaryDotColor = getByTestId("ai-traces-status-ok").props.style.backgroundColor;
5561
- const accentDotColor = getByTestId("ai-traces-status-error").props.style.backgroundColor;
5562
-
5563
- assert.isString(primaryDotColor);
5564
- assert.isString(accentDotColor);
5565
- assert.notEqual(primaryDotColor, accentDotColor);
5566
- expect(getByLabelText("Trace status: ok")).toBeTruthy();
5567
- expect(getByLabelText("Trace status: error")).toBeTruthy();
5975
+ expect(getByTestId("ai-traces-status-ok")).toBeTruthy();
5976
+ expect(getByTestId("ai-traces-status-error")).toBeTruthy();
5977
+ expect(getByText("OK")).toBeTruthy();
5978
+ expect(getByText("Error")).toBeTruthy();
5568
5979
  });
5569
5980
 
5570
5981
  it("renders a sensitive badge on sensitive traces", () => {
@@ -5573,7 +5984,7 @@ describe("AiTracesListView", () => {
5573
5984
  {...datasetDefaults}
5574
5985
  evaluatorId=""
5575
5986
  evaluators={[]}
5576
- filters={emptyTraceFilters()}
5987
+ filterValues={{}}
5577
5988
  page={1}
5578
5989
  selectedIds={[]}
5579
5990
  total={1}
@@ -5582,7 +5993,7 @@ describe("AiTracesListView", () => {
5582
5993
  />
5583
5994
  );
5584
5995
  expect(getByTestId("ai-traces-sensitive-badge")).toBeTruthy();
5585
- expect(getByText("3")).toBeTruthy();
5996
+ expect(getByText("3 steps")).toBeTruthy();
5586
5997
  expect(getByText("2")).toBeTruthy();
5587
5998
  });
5588
5999
 
@@ -5592,7 +6003,7 @@ describe("AiTracesListView", () => {
5592
6003
  {...datasetDefaults}
5593
6004
  evaluatorId="eval-1"
5594
6005
  evaluators={[{id: "eval-1", name: "correctness", type: "human"}]}
5595
- filters={emptyTraceFilters()}
6006
+ filterValues={{}}
5596
6007
  page={1}
5597
6008
  selectedIds={[sensitiveTrace.id, okTrace.id]}
5598
6009
  total={2}
@@ -5612,12 +6023,12 @@ describe("AiTracesListView", () => {
5612
6023
 
5613
6024
  it("toggles selection, filters, dataset modal, and pagination", async () => {
5614
6025
  const onToggleSelect = mock(() => undefined);
5615
- const onFiltersChange = mock(() => undefined);
6026
+ const onFilterValuesChange = mock((_values: Record<string, unknown>) => undefined);
5616
6027
  const onClearSelection = mock(() => undefined);
5617
6028
  const onPageChange = mock(() => undefined);
5618
6029
  const onAddToDataset = mock(() => undefined);
5619
6030
  const onDismissDatasetModal = mock(() => undefined);
5620
- const {getByTestId, getByText, UNSAFE_root} = renderWithTheme(
6031
+ const {getByTestId, getByText} = renderWithTheme(
5621
6032
  <AiTracesListView
5622
6033
  addToDatasetError="Could not add traces to the dataset."
5623
6034
  datasetId="ds-1"
@@ -5626,8 +6037,7 @@ describe("AiTracesListView", () => {
5626
6037
  enqueueError="enqueue failed"
5627
6038
  evaluatorId="eval-1"
5628
6039
  evaluators={[{id: "eval-1", name: "correctness", type: "human"}]}
5629
- filters={emptyTraceFilters()}
5630
- more
6040
+ filterValues={{}}
5631
6041
  onAddToDataset={onAddToDataset}
5632
6042
  onClearSelection={onClearSelection}
5633
6043
  onDatasetChange={() => undefined}
@@ -5635,12 +6045,12 @@ describe("AiTracesListView", () => {
5635
6045
  onDismissReviewModal={() => undefined}
5636
6046
  onEnqueueReview={() => undefined}
5637
6047
  onEvaluatorChange={() => undefined}
5638
- onFiltersChange={onFiltersChange}
6048
+ onFilterValuesChange={onFilterValuesChange}
5639
6049
  onOpenAddToDataset={() => undefined}
5640
6050
  onOpenReview={() => undefined}
5641
6051
  onOpenTrace={() => undefined}
5642
6052
  onPageChange={onPageChange}
5643
- onRunTestMultiStage={() => undefined}
6053
+ onSortChange={() => undefined}
5644
6054
  onToggleSelect={onToggleSelect}
5645
6055
  page={1}
5646
6056
  promptOptions={["summarize", "safety"]}
@@ -5657,22 +6067,19 @@ describe("AiTracesListView", () => {
5657
6067
  });
5658
6068
  assert.isAtLeast(onToggleSelect.mock.calls.length, 1);
5659
6069
 
5660
- const promptSelect = UNSAFE_root.findAllByType(SelectField).find(
5661
- (field) => field.props.testID === "ai-traces-filter-prompt"
5662
- );
5663
- const scoreSelect = UNSAFE_root.findAllByType(SelectField).find(
5664
- (field) => field.props.testID === "ai-traces-filter-has-score"
5665
- );
5666
- const sensitiveSelect = UNSAFE_root.findAllByType(SelectField).find(
5667
- (field) => field.props.testID === "ai-traces-filter-sensitive"
5668
- );
5669
- assert.isDefined(promptSelect);
5670
- assert.isDefined(scoreSelect);
5671
- assert.isDefined(sensitiveSelect);
5672
- fireEvent(promptSelect!, "onChange", "summarize");
5673
- fireEvent(scoreSelect!, "onChange", "false");
5674
- fireEvent(sensitiveSelect!, "onChange", "true");
5675
- assert.isAtLeast(onFiltersChange.mock.calls.length, 3);
6070
+ await act(async () => {
6071
+ fireEvent(getByTestId("ai-traces-table"), "filterValuesChange", {
6072
+ hasScore: false,
6073
+ prompt: ["summarize"],
6074
+ sensitive: true,
6075
+ });
6076
+ await Promise.resolve();
6077
+ });
6078
+ assert.deepEqual(onFilterValuesChange.mock.calls[0]?.[0], {
6079
+ hasScore: false,
6080
+ prompt: ["summarize"],
6081
+ sensitive: true,
6082
+ });
5676
6083
 
5677
6084
  expect(getByText("enqueue failed")).toBeTruthy();
5678
6085
  expect(getByTestId("ai-traces-add-dataset-error")).toBeTruthy();
@@ -5681,7 +6088,27 @@ describe("AiTracesListView", () => {
5681
6088
  expect(getByTestId("ai-traces-review-modal")).toHaveTextContent(
5682
6089
  /human evaluator defines the score fields/
5683
6090
  );
5684
- expect(getByText("40 traces · more pages")).toBeTruthy();
6091
+ expect(getByText("40 traces")).toBeTruthy();
6092
+ });
6093
+
6094
+ it("links to datasets instead of a fake option when there are none", () => {
6095
+ const {getByTestId, getByText, queryByTestId} = renderWithTheme(
6096
+ <AiTracesListView
6097
+ {...datasetDefaults}
6098
+ datasetModalOpen
6099
+ evaluatorId=""
6100
+ evaluators={[]}
6101
+ filterValues={{}}
6102
+ page={1}
6103
+ selectedIds={[okTrace.id]}
6104
+ total={1}
6105
+ traces={[okTrace]}
6106
+ {...idleHandlers}
6107
+ />
6108
+ );
6109
+ expect(getByTestId("ai-traces-dataset-none")).toBeTruthy();
6110
+ expect(getByText("Create a dataset")).toBeTruthy();
6111
+ assert.notExists(queryByTestId("ai-traces-dataset-picker"));
5685
6112
  });
5686
6113
 
5687
6114
  it("wires evaluator change, page change, and dataset modal dismiss", async () => {
@@ -5698,8 +6125,7 @@ describe("AiTracesListView", () => {
5698
6125
  {id: "eval-1", name: "correctness", type: "human"},
5699
6126
  {id: "eval-2", name: "tone", type: "human"},
5700
6127
  ]}
5701
- filters={emptyTraceFilters()}
5702
- more
6128
+ filterValues={{}}
5703
6129
  onAddToDataset={() => undefined}
5704
6130
  onClearSelection={() => undefined}
5705
6131
  onDatasetChange={() => undefined}
@@ -5707,12 +6133,12 @@ describe("AiTracesListView", () => {
5707
6133
  onDismissReviewModal={() => undefined}
5708
6134
  onEnqueueReview={() => undefined}
5709
6135
  onEvaluatorChange={onEvaluatorChange}
5710
- onFiltersChange={() => undefined}
6136
+ onFilterValuesChange={() => undefined}
5711
6137
  onOpenAddToDataset={() => undefined}
5712
6138
  onOpenReview={() => undefined}
5713
6139
  onOpenTrace={() => undefined}
5714
6140
  onPageChange={onPageChange}
5715
- onRunTestMultiStage={() => undefined}
6141
+ onSortChange={() => undefined}
5716
6142
  onToggleSelect={() => undefined}
5717
6143
  page={1}
5718
6144
  promptOptions={["summarize", "safety"]}
@@ -5741,15 +6167,16 @@ describe("AiTracesListView", () => {
5741
6167
  assert.equal(onDismissDatasetModal.mock.calls.length, 1);
5742
6168
  });
5743
6169
 
5744
- it("wires time and status filters and opens traces from the table", async () => {
5745
- const onFiltersChange = mock(() => undefined);
6170
+ it("wires sort and column filters and opens traces from the table", async () => {
6171
+ const onFilterValuesChange = mock((_values: Record<string, unknown>) => undefined);
6172
+ const onSortChange = mock((_sort: string) => undefined);
5746
6173
  const onOpenTrace = mock(() => undefined);
5747
- const {getByTestId, UNSAFE_root} = renderWithTheme(
6174
+ const {getByTestId} = renderWithTheme(
5748
6175
  <AiTracesListView
5749
6176
  {...datasetDefaults}
5750
6177
  evaluatorId=""
5751
6178
  evaluators={[]}
5752
- filters={emptyTraceFilters()}
6179
+ filterValues={{}}
5753
6180
  onAddToDataset={() => undefined}
5754
6181
  onClearSelection={() => undefined}
5755
6182
  onDatasetChange={() => undefined}
@@ -5757,12 +6184,12 @@ describe("AiTracesListView", () => {
5757
6184
  onDismissReviewModal={() => undefined}
5758
6185
  onEnqueueReview={() => undefined}
5759
6186
  onEvaluatorChange={() => undefined}
5760
- onFiltersChange={onFiltersChange}
6187
+ onFilterValuesChange={onFilterValuesChange}
5761
6188
  onOpenAddToDataset={() => undefined}
5762
6189
  onOpenReview={() => undefined}
5763
6190
  onOpenTrace={onOpenTrace}
5764
6191
  onPageChange={() => undefined}
5765
- onRunTestMultiStage={() => undefined}
6192
+ onSortChange={onSortChange}
5766
6193
  onToggleSelect={() => undefined}
5767
6194
  page={1}
5768
6195
  selectedIds={[]}
@@ -5770,15 +6197,17 @@ describe("AiTracesListView", () => {
5770
6197
  traces={[okTrace]}
5771
6198
  />
5772
6199
  );
5773
- fireEvent.changeText(getByTestId("ai-traces-filter-from"), "2026-09-01");
5774
- fireEvent.changeText(getByTestId("ai-traces-filter-to"), "2026-09-02");
5775
- const statusSelect = UNSAFE_root.findAllByType(SelectField).find(
5776
- (field) => field.props.testID === "ai-traces-filter-status"
5777
- );
5778
- fireEvent(statusSelect!, "onChange", "error");
5779
- fireEvent.changeText(getByTestId("ai-traces-filter-user"), "user-1");
5780
- fireEvent.changeText(getByTestId("ai-traces-filter-session"), "sess-1");
5781
- assert.isAtLeast(onFiltersChange.mock.calls.length, 3);
6200
+ const table = getByTestId("ai-traces-table");
6201
+ await act(async () => {
6202
+ fireEvent(table, "setSortColumn", {column: 6, direction: "desc"});
6203
+ fireEvent(table, "filterValuesChange", {status: ["error"], userId: "user-1"});
6204
+ await Promise.resolve();
6205
+ });
6206
+ assert.deepEqual(onSortChange.mock.calls[0]?.[0], "-cost");
6207
+ assert.deepEqual(onFilterValuesChange.mock.calls[0]?.[0], {
6208
+ status: ["error"],
6209
+ userId: "user-1",
6210
+ });
5782
6211
  await act(async () => {
5783
6212
  fireEvent.press(getByTestId("ai-traces-open-trace-ok"));
5784
6213
  await Promise.resolve();
@@ -5794,24 +6223,27 @@ describe("ReviewScoreField", () => {
5794
6223
  routerPush.mockClear();
5795
6224
  });
5796
6225
  describe("ReviewScoreField", () => {
5797
- it("renders boolean dimensions as Pass and Fail controls", async () => {
6226
+ it("renders boolean dimensions as one Yes/No control", async () => {
5798
6227
  const onChange = mock(() => undefined);
5799
- const {getByTestId, getByText} = renderWithTheme(
6228
+ const {getByTestId, getByText, queryByText} = renderWithTheme(
5800
6229
  <ReviewScoreField
5801
- dimension={{dataType: "boolean", key: "correct", required: true}}
6230
+ dimension={{dataType: "boolean", key: "is_correct", required: true}}
5802
6231
  onChange={onChange}
6232
+ value={false}
5803
6233
  />
5804
6234
  );
5805
- expect(getByTestId("ai-review-score-boolean-correct")).toBeTruthy();
5806
- expect(getByText("Pass")).toBeTruthy();
5807
- expect(getByText("Fail")).toBeTruthy();
6235
+ expect(getByTestId("ai-review-score-boolean-is_correct")).toBeTruthy();
6236
+ expect(getByTestId("ai-review-score-is_correct-answer")).toBeTruthy();
6237
+ expect(getByText("Is correct")).toBeTruthy();
6238
+ expect(queryByText("Pass")).toBeNull();
6239
+ expect(queryByText("Fail")).toBeNull();
5808
6240
  await act(async () => {
5809
- fireEvent.press(getByTestId("ai-review-score-correct-pass"));
6241
+ fireEvent.press(getByTestId("ai-review-score-is_correct-yes"));
5810
6242
  await new Promise((resolve) => setTimeout(resolve, 50));
5811
6243
  });
5812
6244
  expect(onChange).toHaveBeenCalledWith(true);
5813
6245
  await act(async () => {
5814
- fireEvent.press(getByTestId("ai-review-score-correct-fail"));
6246
+ fireEvent.press(getByTestId("ai-review-score-is_correct-no"));
5815
6247
  await new Promise((resolve) => setTimeout(resolve, 50));
5816
6248
  });
5817
6249
  expect(onChange).toHaveBeenCalledWith(false);
@@ -5827,7 +6259,7 @@ describe("ReviewScoreField", () => {
5827
6259
  />
5828
6260
  );
5829
6261
  expect(getByTestId("ai-review-score-numeric-helpfulness")).toBeTruthy();
5830
- expect(getByText("helpfulness")).toBeTruthy();
6262
+ expect(getByText("Helpfulness")).toBeTruthy();
5831
6263
  expect(getByText("0")).toBeTruthy();
5832
6264
  expect(getByText("1")).toBeTruthy();
5833
6265
  fireEvent(UNSAFE_getByType(SliderComponent), "valueChange", 0.8);
@@ -5951,7 +6383,6 @@ describe("AiExperimentResultsView", () => {
5951
6383
  onSelectVersion={() => undefined}
5952
6384
  promoteConfirmOpen={false}
5953
6385
  promoteVersion={2}
5954
- selectedVersion={2}
5955
6386
  />
5956
6387
  );
5957
6388
  expect(getByTestId("ai-experiment-results-running")).toBeTruthy();
@@ -5966,16 +6397,13 @@ describe("AiExperimentResultsView", () => {
5966
6397
  onOpenPromoteConfirm={() => undefined}
5967
6398
  onPromote={() => undefined}
5968
6399
  onSelectVersion={() => undefined}
5969
- promoteBlockedMessage="gate failed for v2 quality.correct"
5970
6400
  promoteConfirmOpen={false}
5971
6401
  promoteVersion={2}
5972
- selectedVersion={2}
5973
6402
  />
5974
6403
  );
5975
- expect(getByTestId("ai-experiment-gates-failing")).toBeTruthy();
5976
- assert.include(
5977
- String(getByTestId("ai-experiment-promote-blocked").props.children),
5978
- "quality.correct"
6404
+ expect(getByTestId("ai-experiment-gates-failing")).toHaveTextContent(
6405
+ /v2 fails 1 gate: quality: correct ≥ 0\.8 \(got 0\.40\)/
5979
6406
  );
6407
+ expect(getByTestId("ai-experiment-gates-v2-verdict")).toHaveTextContent("Fails 1 of 1 gate");
5980
6408
  });
5981
6409
  });