attention-manifest-protocol 0.4.0 → 0.4.2

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 (627) hide show
  1. package/CHANGELOG.md +250 -226
  2. package/CHANGELOG.zh-CN.md +63 -39
  3. package/README.md +22 -1
  4. package/README.zh-CN.md +22 -1
  5. package/docs/probes/calibration-imported.json +141 -141
  6. package/docs/probes/eval-recorded-replay.json +597 -597
  7. package/docs/probes/eval-replay.json +124 -124
  8. package/docs/probes/eval-summary.json +42 -42
  9. package/docs/probes/runtime-eval.json +4230 -4230
  10. package/lib/attention/attention.d.ts +153 -0
  11. package/lib/attention/attention.js +209 -0
  12. package/lib/attention/budget.d.ts +31 -0
  13. package/lib/attention/budget.js +55 -0
  14. package/lib/attention/cognition.d.ts +230 -0
  15. package/lib/attention/cognition.js +245 -0
  16. package/lib/attention/index.d.ts +8 -0
  17. package/lib/attention/index.js +7 -0
  18. package/lib/attention/interrupts.d.ts +97 -0
  19. package/lib/attention/interrupts.js +151 -0
  20. package/lib/attention/resource.d.ts +167 -0
  21. package/lib/attention/resource.js +148 -0
  22. package/lib/attention/social.d.ts +74 -0
  23. package/lib/attention/social.js +153 -0
  24. package/lib/attention/socialTypes.d.ts +102 -0
  25. package/lib/attention/socialTypes.js +1 -0
  26. package/lib/authz/authz.d.ts +75 -0
  27. package/lib/authz/authz.js +176 -0
  28. package/lib/authz/index.d.ts +1 -0
  29. package/lib/authz/index.js +1 -0
  30. package/lib/bayes/calibration.d.ts +67 -0
  31. package/lib/bayes/calibration.js +114 -0
  32. package/lib/bayes/calibrationRegistry.d.ts +39 -0
  33. package/lib/bayes/calibrationRegistry.js +61 -0
  34. package/lib/bayes/calibrationSelection.d.ts +40 -0
  35. package/lib/bayes/calibrationSelection.js +89 -0
  36. package/lib/bayes/engine.d.ts +163 -0
  37. package/lib/bayes/engine.js +354 -0
  38. package/lib/bayes/index.d.ts +6 -0
  39. package/lib/bayes/index.js +6 -0
  40. package/lib/bayes/reliability.d.ts +27 -0
  41. package/lib/bayes/reliability.js +38 -0
  42. package/lib/bayes/scopedPriors.d.ts +34 -0
  43. package/lib/bayes/scopedPriors.js +70 -0
  44. package/lib/boundary/frame.d.ts +63 -0
  45. package/lib/boundary/frame.js +239 -0
  46. package/lib/boundary/ids.d.ts +8 -0
  47. package/lib/boundary/ids.js +12 -0
  48. package/lib/boundary/index.d.ts +12 -0
  49. package/lib/boundary/index.js +8 -0
  50. package/lib/boundary/refTable.d.ts +49 -0
  51. package/lib/boundary/refTable.js +92 -0
  52. package/lib/boundary/toolCall.d.ts +33 -0
  53. package/lib/boundary/toolCall.js +173 -0
  54. package/lib/concept/concept.d.ts +67 -0
  55. package/lib/concept/concept.js +1 -0
  56. package/lib/concept/conceptBudget.d.ts +56 -0
  57. package/lib/concept/conceptBudget.js +281 -0
  58. package/lib/concept/conceptBudgetTypes.d.ts +74 -0
  59. package/lib/concept/conceptBudgetTypes.js +1 -0
  60. package/lib/concept/index.d.ts +3 -0
  61. package/lib/concept/index.js +3 -0
  62. package/lib/concurrency/idempotency.d.ts +16 -0
  63. package/lib/concurrency/idempotency.js +21 -0
  64. package/lib/concurrency/index.d.ts +5 -0
  65. package/lib/concurrency/index.js +5 -0
  66. package/lib/concurrency/mutex.d.ts +13 -0
  67. package/lib/concurrency/mutex.js +26 -0
  68. package/lib/concurrency/namedLocks.d.ts +7 -0
  69. package/lib/concurrency/namedLocks.js +31 -0
  70. package/lib/concurrency/retry.d.ts +23 -0
  71. package/lib/concurrency/retry.js +38 -0
  72. package/lib/concurrency/worker.d.ts +42 -0
  73. package/lib/concurrency/worker.js +67 -0
  74. package/lib/context/agentContext.d.ts +58 -0
  75. package/lib/context/agentContext.js +197 -0
  76. package/lib/context/ast.d.ts +98 -0
  77. package/lib/context/ast.js +414 -0
  78. package/lib/context/contentStore.d.ts +16 -0
  79. package/lib/context/contentStore.js +61 -0
  80. package/lib/context/context.d.ts +15 -0
  81. package/lib/context/context.js +39 -0
  82. package/lib/context/contextIndex.d.ts +40 -0
  83. package/lib/context/contextIndex.js +64 -0
  84. package/lib/context/document.d.ts +102 -0
  85. package/lib/context/document.js +22 -0
  86. package/lib/context/fileStorePath.d.ts +1 -0
  87. package/lib/context/fileStorePath.js +13 -0
  88. package/lib/context/index.d.ts +22 -0
  89. package/lib/context/index.js +11 -0
  90. package/lib/context/lifecycle.d.ts +91 -0
  91. package/lib/context/lifecycle.js +163 -0
  92. package/lib/context/projections.d.ts +20 -0
  93. package/lib/context/projections.js +127 -0
  94. package/lib/context/workspace.d.ts +111 -0
  95. package/lib/context/workspace.js +318 -0
  96. package/lib/context/workspaceProtocol.d.ts +30 -0
  97. package/lib/context/workspaceProtocol.js +49 -0
  98. package/lib/context/workspaceService.d.ts +63 -0
  99. package/lib/context/workspaceService.js +352 -0
  100. package/lib/cooperation/board.d.ts +47 -0
  101. package/lib/cooperation/board.js +66 -0
  102. package/lib/cooperation/collaboration.d.ts +55 -0
  103. package/lib/cooperation/collaboration.js +1 -0
  104. package/lib/cooperation/index.d.ts +6 -0
  105. package/lib/cooperation/index.js +6 -0
  106. package/lib/cooperation/merge.d.ts +69 -0
  107. package/lib/cooperation/merge.js +109 -0
  108. package/lib/cooperation/metrics.d.ts +39 -0
  109. package/lib/cooperation/metrics.js +17 -0
  110. package/lib/cooperation/session.d.ts +75 -0
  111. package/lib/cooperation/session.js +74 -0
  112. package/lib/cooperation/unified.d.ts +38 -0
  113. package/lib/cooperation/unified.js +40 -0
  114. package/lib/database/adapter/adapters.d.ts +24 -0
  115. package/lib/database/adapter/adapters.js +31 -0
  116. package/lib/database/adapter/index.d.ts +4 -0
  117. package/lib/database/adapter/index.js +4 -0
  118. package/lib/database/adapter/runtimeSink.d.ts +20 -0
  119. package/lib/database/adapter/runtimeSink.js +50 -0
  120. package/lib/database/adapter/sessionStore.d.ts +11 -0
  121. package/lib/database/adapter/sessionStore.js +23 -0
  122. package/lib/database/adapter/turnStore.d.ts +10 -0
  123. package/lib/database/adapter/turnStore.js +15 -0
  124. package/lib/database/entity/agent.d.ts +133 -0
  125. package/lib/database/entity/agent.js +61 -0
  126. package/lib/database/entity/entity.d.ts +715 -0
  127. package/lib/database/entity/entity.js +372 -0
  128. package/lib/database/entity/handle.d.ts +31 -0
  129. package/lib/database/entity/handle.js +53 -0
  130. package/lib/database/entity/index.d.ts +32 -0
  131. package/lib/database/entity/index.js +22 -0
  132. package/lib/database/entity/message.d.ts +27 -0
  133. package/lib/database/entity/message.js +52 -0
  134. package/lib/database/entity/meta.d.ts +11 -0
  135. package/lib/database/entity/meta.js +1 -0
  136. package/lib/database/entity/object.d.ts +23 -0
  137. package/lib/database/entity/object.js +24 -0
  138. package/lib/database/entity/outbox.d.ts +9 -0
  139. package/lib/database/entity/outbox.js +5 -0
  140. package/lib/database/entity/process.d.ts +30 -0
  141. package/lib/database/entity/process.js +40 -0
  142. package/lib/database/entity/registry.d.ts +81 -0
  143. package/lib/database/entity/registry.js +91 -0
  144. package/lib/database/entity/runtimeApproval.d.ts +23 -0
  145. package/lib/database/entity/runtimeApproval.js +5 -0
  146. package/lib/database/entity/runtimeSession.d.ts +7 -0
  147. package/lib/database/entity/runtimeSession.js +5 -0
  148. package/lib/database/entity/runtimeTurn.d.ts +9 -0
  149. package/lib/database/entity/runtimeTurn.js +5 -0
  150. package/lib/database/entity/thread.d.ts +35 -0
  151. package/lib/database/entity/thread.js +55 -0
  152. package/lib/database/entity/window.d.ts +39 -0
  153. package/lib/database/entity/window.js +56 -0
  154. package/lib/database/entity/worker.d.ts +42 -0
  155. package/lib/database/entity/worker.js +58 -0
  156. package/lib/database/index.d.ts +6 -0
  157. package/lib/database/index.js +6 -0
  158. package/lib/database/repository/addressSpaceRepository.d.ts +18 -0
  159. package/lib/database/repository/addressSpaceRepository.js +40 -0
  160. package/lib/database/repository/agentRepository.d.ts +41 -0
  161. package/lib/database/repository/agentRepository.js +398 -0
  162. package/lib/database/repository/base.d.ts +31 -0
  163. package/lib/database/repository/base.js +23 -0
  164. package/lib/database/repository/executionRepository.d.ts +64 -0
  165. package/lib/database/repository/executionRepository.js +379 -0
  166. package/lib/database/repository/handleRepository.d.ts +35 -0
  167. package/lib/database/repository/handleRepository.js +57 -0
  168. package/lib/database/repository/index.d.ts +20 -0
  169. package/lib/database/repository/index.js +17 -0
  170. package/lib/database/repository/messageRepository.d.ts +33 -0
  171. package/lib/database/repository/messageRepository.js +45 -0
  172. package/lib/database/repository/objectRepository.d.ts +43 -0
  173. package/lib/database/repository/objectRepository.js +60 -0
  174. package/lib/database/repository/outboxRepository.d.ts +15 -0
  175. package/lib/database/repository/outboxRepository.js +51 -0
  176. package/lib/database/repository/processRepository.d.ts +31 -0
  177. package/lib/database/repository/processRepository.js +48 -0
  178. package/lib/database/repository/registryRepository.d.ts +72 -0
  179. package/lib/database/repository/registryRepository.js +95 -0
  180. package/lib/database/repository/repository.d.ts +322 -0
  181. package/lib/database/repository/repository.js +332 -0
  182. package/lib/database/repository/runtimeApprovalRepository.d.ts +14 -0
  183. package/lib/database/repository/runtimeApprovalRepository.js +35 -0
  184. package/lib/database/repository/runtimeSessionRepository.d.ts +9 -0
  185. package/lib/database/repository/runtimeSessionRepository.js +21 -0
  186. package/lib/database/repository/runtimeTurnRepository.d.ts +10 -0
  187. package/lib/database/repository/runtimeTurnRepository.js +32 -0
  188. package/lib/database/repository/socialRepository.d.ts +22 -0
  189. package/lib/database/repository/socialRepository.js +155 -0
  190. package/lib/database/repository/threadRepository.d.ts +29 -0
  191. package/lib/database/repository/threadRepository.js +48 -0
  192. package/lib/database/repository/windowRepository.d.ts +46 -0
  193. package/lib/database/repository/windowRepository.js +68 -0
  194. package/lib/database/repository/workerRepository.d.ts +38 -0
  195. package/lib/database/repository/workerRepository.js +61 -0
  196. package/lib/database/service/database.d.ts +55 -0
  197. package/lib/database/service/database.js +77 -0
  198. package/lib/database/service/handleService.d.ts +20 -0
  199. package/lib/database/service/handleService.js +34 -0
  200. package/lib/database/service/index.d.ts +16 -0
  201. package/lib/database/service/index.js +11 -0
  202. package/lib/database/service/messageService.d.ts +26 -0
  203. package/lib/database/service/messageService.js +40 -0
  204. package/lib/database/service/objectService.d.ts +32 -0
  205. package/lib/database/service/objectService.js +31 -0
  206. package/lib/database/service/processService.d.ts +22 -0
  207. package/lib/database/service/processService.js +45 -0
  208. package/lib/database/service/registryServices.d.ts +43 -0
  209. package/lib/database/service/registryServices.js +60 -0
  210. package/lib/database/service/service.d.ts +131 -0
  211. package/lib/database/service/service.js +153 -0
  212. package/lib/database/service/stepService.d.ts +23 -0
  213. package/lib/database/service/stepService.js +35 -0
  214. package/lib/database/service/threadService.d.ts +23 -0
  215. package/lib/database/service/threadService.js +48 -0
  216. package/lib/database/service/windowService.d.ts +15 -0
  217. package/lib/database/service/windowService.js +22 -0
  218. package/lib/database/service/workerService.d.ts +28 -0
  219. package/lib/database/service/workerService.js +34 -0
  220. package/lib/database/sql/index.d.ts +3 -0
  221. package/lib/database/sql/index.js +2 -0
  222. package/lib/database/sql/schema.d.ts +5 -0
  223. package/lib/database/sql/schema.js +416 -0
  224. package/lib/database/sql/sql.d.ts +290 -0
  225. package/lib/database/sql/sql.js +430 -0
  226. package/lib/database/store/database.d.ts +75 -0
  227. package/lib/database/store/database.js +143 -0
  228. package/lib/database/store/index.d.ts +3 -0
  229. package/lib/database/store/index.js +2 -0
  230. package/lib/database/store/store.d.ts +145 -0
  231. package/lib/database/store/store.js +192 -0
  232. package/lib/delegate/index.d.ts +2 -0
  233. package/lib/delegate/index.js +2 -0
  234. package/lib/delegate/team.d.ts +92 -0
  235. package/lib/delegate/team.js +200 -0
  236. package/lib/delegate/teamTypes.d.ts +43 -0
  237. package/lib/delegate/teamTypes.js +1 -0
  238. package/lib/diagnosis/checklist.d.ts +16 -0
  239. package/lib/diagnosis/checklist.js +61 -0
  240. package/lib/diagnosis/context.d.ts +19 -0
  241. package/lib/diagnosis/context.js +79 -0
  242. package/lib/diagnosis/frame.d.ts +34 -0
  243. package/lib/diagnosis/frame.js +230 -0
  244. package/lib/diagnosis/index.d.ts +5 -0
  245. package/lib/diagnosis/index.js +5 -0
  246. package/lib/diagnosis/router.d.ts +22 -0
  247. package/lib/diagnosis/router.js +47 -0
  248. package/lib/diagnosis/types.d.ts +78 -0
  249. package/lib/diagnosis/types.js +2 -0
  250. package/lib/error/agentError.d.ts +9 -0
  251. package/lib/error/agentError.js +13 -0
  252. package/lib/error/ampError.d.ts +14 -0
  253. package/lib/error/ampError.js +19 -0
  254. package/lib/error/authzError.d.ts +10 -0
  255. package/lib/error/authzError.js +11 -0
  256. package/lib/error/boundaryRejection.d.ts +16 -0
  257. package/lib/error/boundaryRejection.js +14 -0
  258. package/lib/error/index.d.ts +7 -0
  259. package/lib/error/index.js +7 -0
  260. package/lib/error/kernelError.d.ts +11 -0
  261. package/lib/error/kernelError.js +12 -0
  262. package/lib/error/mailboxError.d.ts +5 -0
  263. package/lib/error/mailboxError.js +6 -0
  264. package/lib/error/windowError.d.ts +8 -0
  265. package/lib/error/windowError.js +9 -0
  266. package/lib/evaluation/agreement.d.ts +22 -0
  267. package/lib/evaluation/agreement.js +82 -0
  268. package/lib/evaluation/index.d.ts +2 -0
  269. package/lib/evaluation/index.js +2 -0
  270. package/lib/evaluation/labels.d.ts +56 -0
  271. package/lib/evaluation/labels.js +206 -0
  272. package/lib/evidence/evidenceGraph.d.ts +37 -0
  273. package/lib/evidence/evidenceGraph.js +165 -0
  274. package/lib/evidence/index.d.ts +4 -0
  275. package/lib/evidence/index.js +2 -0
  276. package/lib/evidence/revalidation.d.ts +70 -0
  277. package/lib/evidence/revalidation.js +146 -0
  278. package/lib/execution/exec.d.ts +151 -0
  279. package/lib/execution/exec.js +282 -0
  280. package/lib/execution/handles.d.ts +25 -0
  281. package/lib/execution/handles.js +45 -0
  282. package/lib/execution/index.d.ts +3 -0
  283. package/lib/execution/index.js +3 -0
  284. package/lib/execution/pin.d.ts +60 -0
  285. package/lib/execution/pin.js +103 -0
  286. package/lib/frame/frame.d.ts +61 -0
  287. package/lib/frame/frame.js +1 -0
  288. package/lib/frame/index.d.ts +1 -0
  289. package/lib/frame/index.js +1 -0
  290. package/lib/goal/goal.d.ts +19 -0
  291. package/lib/goal/goal.js +21 -0
  292. package/lib/goal/index.d.ts +2 -0
  293. package/lib/goal/index.js +1 -0
  294. package/lib/goal/plan.d.ts +125 -0
  295. package/lib/goal/plan.js +60 -0
  296. package/lib/governance/attentionManifest.d.ts +279 -0
  297. package/lib/governance/attentionManifest.js +467 -0
  298. package/lib/governance/audit.d.ts +123 -0
  299. package/lib/governance/audit.js +263 -0
  300. package/lib/governance/budget.d.ts +219 -0
  301. package/lib/governance/budget.js +424 -0
  302. package/lib/governance/context.d.ts +159 -0
  303. package/lib/governance/context.js +229 -0
  304. package/lib/governance/control.d.ts +65 -0
  305. package/lib/governance/control.js +89 -0
  306. package/lib/governance/cooperation.d.ts +163 -0
  307. package/lib/governance/cooperation.js +350 -0
  308. package/lib/governance/credential.d.ts +117 -0
  309. package/lib/governance/credential.js +229 -0
  310. package/lib/governance/httpServer.d.ts +18 -0
  311. package/lib/governance/httpServer.js +74 -0
  312. package/lib/governance/index.d.ts +32 -0
  313. package/lib/governance/index.js +32 -0
  314. package/lib/governance/legal.d.ts +222 -0
  315. package/lib/governance/legal.js +371 -0
  316. package/lib/governance/matrix.d.ts +170 -0
  317. package/lib/governance/matrix.js +365 -0
  318. package/lib/governance/perspectives.d.ts +98 -0
  319. package/lib/governance/perspectives.js +340 -0
  320. package/lib/governance/signing.d.ts +131 -0
  321. package/lib/governance/signing.js +241 -0
  322. package/lib/governance/store.d.ts +33 -0
  323. package/lib/governance/store.js +89 -0
  324. package/lib/governance/switching.d.ts +183 -0
  325. package/lib/governance/switching.js +257 -0
  326. package/lib/governance/toolPolicy.d.ts +37 -0
  327. package/lib/governance/toolPolicy.js +42 -0
  328. package/lib/governance/transport.d.ts +76 -0
  329. package/lib/governance/transport.js +124 -0
  330. package/lib/governance/types.d.ts +218 -0
  331. package/lib/governance/types.js +72 -0
  332. package/lib/governance/workflow.d.ts +174 -0
  333. package/lib/governance/workflow.js +612 -0
  334. package/lib/index.d.ts +11 -0
  335. package/lib/index.js +11 -0
  336. package/lib/interaction/index.d.ts +1 -0
  337. package/lib/interaction/index.js +1 -0
  338. package/lib/interaction/interaction.d.ts +83 -0
  339. package/lib/interaction/interaction.js +256 -0
  340. package/lib/ipc/index.d.ts +4 -0
  341. package/lib/ipc/index.js +3 -0
  342. package/lib/ipc/mailbox.d.ts +37 -0
  343. package/lib/ipc/mailbox.js +77 -0
  344. package/lib/ipc/memorySocialStore.d.ts +14 -0
  345. package/lib/ipc/memorySocialStore.js +83 -0
  346. package/lib/ipc/social.d.ts +80 -0
  347. package/lib/ipc/social.js +1 -0
  348. package/lib/kernel/index.d.ts +2 -0
  349. package/lib/kernel/index.js +1 -0
  350. package/lib/kernel/scheduler.d.ts +195 -0
  351. package/lib/kernel/scheduler.js +334 -0
  352. package/lib/ledger/checkpoint.d.ts +116 -0
  353. package/lib/ledger/checkpoint.js +223 -0
  354. package/lib/ledger/index.d.ts +4 -0
  355. package/lib/ledger/index.js +4 -0
  356. package/lib/ledger/ledger.d.ts +21 -0
  357. package/lib/ledger/ledger.js +23 -0
  358. package/lib/ledger/persistence.d.ts +46 -0
  359. package/lib/ledger/persistence.js +106 -0
  360. package/lib/ledger/share.d.ts +29 -0
  361. package/lib/ledger/share.js +39 -0
  362. package/lib/lock/index.d.ts +2 -0
  363. package/lib/lock/index.js +1 -0
  364. package/lib/lock/lease.d.ts +23 -0
  365. package/lib/lock/lease.js +42 -0
  366. package/lib/manifest/agentCard.d.ts +35 -0
  367. package/lib/manifest/agentCard.js +38 -0
  368. package/lib/manifest/cardSign.d.ts +25 -0
  369. package/lib/manifest/cardSign.js +70 -0
  370. package/lib/manifest/federation.d.ts +64 -0
  371. package/lib/manifest/federation.js +187 -0
  372. package/lib/manifest/federationTypes.d.ts +51 -0
  373. package/lib/manifest/federationTypes.js +1 -0
  374. package/lib/manifest/index.d.ts +8 -0
  375. package/lib/manifest/index.js +8 -0
  376. package/lib/manifest/keys.d.ts +221 -0
  377. package/lib/manifest/keys.js +484 -0
  378. package/lib/manifest/manifest.d.ts +102 -0
  379. package/lib/manifest/manifest.js +1 -0
  380. package/lib/manifest/sign.d.ts +38 -0
  381. package/lib/manifest/sign.js +90 -0
  382. package/lib/manifest/trust.d.ts +54 -0
  383. package/lib/manifest/trust.js +87 -0
  384. package/lib/mission/index.d.ts +2 -0
  385. package/lib/mission/index.js +1 -0
  386. package/lib/mission/missionQueue.d.ts +19 -0
  387. package/lib/mission/missionQueue.js +62 -0
  388. package/lib/module/index.d.ts +9 -0
  389. package/lib/module/index.js +9 -0
  390. package/lib/module/llm/deepseek.d.ts +43 -0
  391. package/lib/module/llm/deepseek.js +162 -0
  392. package/lib/module/llm/llm.d.ts +64 -0
  393. package/lib/module/llm/llm.js +16 -0
  394. package/lib/module/mcp/client.d.ts +32 -0
  395. package/lib/module/mcp/client.js +84 -0
  396. package/lib/module/mcp/http.d.ts +32 -0
  397. package/lib/module/mcp/http.js +83 -0
  398. package/lib/module/mcp/protocol.d.ts +62 -0
  399. package/lib/module/mcp/protocol.js +20 -0
  400. package/lib/module/mcp/server.d.ts +22 -0
  401. package/lib/module/mcp/server.js +138 -0
  402. package/lib/module/mcp/transport.d.ts +19 -0
  403. package/lib/module/mcp/transport.js +16 -0
  404. package/lib/module/mcp/workspaceServer.d.ts +20 -0
  405. package/lib/module/mcp/workspaceServer.js +90 -0
  406. package/lib/module/sandbox/sandbox.d.ts +24 -0
  407. package/lib/module/sandbox/sandbox.js +5 -0
  408. package/lib/module/tool/mcpExecutor.d.ts +18 -0
  409. package/lib/module/tool/mcpExecutor.js +41 -0
  410. package/lib/module/tool/policy.d.ts +30 -0
  411. package/lib/module/tool/policy.js +23 -0
  412. package/lib/module/tool/redact.d.ts +9 -0
  413. package/lib/module/tool/redact.js +19 -0
  414. package/lib/module/tool/tool.d.ts +26 -0
  415. package/lib/module/tool/tool.js +24 -0
  416. package/lib/module/tool/workspaceExecutor.d.ts +12 -0
  417. package/lib/module/tool/workspaceExecutor.js +25 -0
  418. package/lib/policy/guard.d.ts +115 -0
  419. package/lib/policy/guard.js +154 -0
  420. package/lib/policy/index.d.ts +2 -0
  421. package/lib/policy/index.js +2 -0
  422. package/lib/policy/policy.d.ts +249 -0
  423. package/lib/policy/policy.js +364 -0
  424. package/lib/process/agent.d.ts +295 -0
  425. package/lib/process/agent.js +1 -0
  426. package/lib/process/agentService.d.ts +87 -0
  427. package/lib/process/agentService.js +128 -0
  428. package/lib/process/agentStore.d.ts +35 -0
  429. package/lib/process/agentStore.js +328 -0
  430. package/lib/process/executionStore.d.ts +79 -0
  431. package/lib/process/executionStore.js +71 -0
  432. package/lib/process/index.d.ts +5 -0
  433. package/lib/process/index.js +5 -0
  434. package/lib/process/process.d.ts +120 -0
  435. package/lib/process/process.js +111 -0
  436. package/lib/process/transitions.d.ts +11 -0
  437. package/lib/process/transitions.js +8 -0
  438. package/lib/progress/index.d.ts +2 -0
  439. package/lib/progress/index.js +1 -0
  440. package/lib/progress/progress.d.ts +26 -0
  441. package/lib/progress/progress.js +42 -0
  442. package/lib/protocol/a2a.d.ts +51 -0
  443. package/lib/protocol/a2a.js +79 -0
  444. package/lib/protocol/channel.d.ts +25 -0
  445. package/lib/protocol/channel.js +27 -0
  446. package/lib/protocol/envelope.d.ts +180 -0
  447. package/lib/protocol/envelope.js +495 -0
  448. package/lib/protocol/httpChannel.d.ts +33 -0
  449. package/lib/protocol/httpChannel.js +59 -0
  450. package/lib/protocol/index.d.ts +6 -0
  451. package/lib/protocol/index.js +6 -0
  452. package/lib/protocol/protocol.d.ts +120 -0
  453. package/lib/protocol/protocol.js +1 -0
  454. package/lib/protocol/wire.d.ts +12 -0
  455. package/lib/protocol/wire.js +55 -0
  456. package/lib/receipt/index.d.ts +1 -0
  457. package/lib/receipt/index.js +1 -0
  458. package/lib/receipt/receipt.d.ts +43 -0
  459. package/lib/receipt/receipt.js +1 -0
  460. package/lib/registry/content.d.ts +10 -0
  461. package/lib/registry/content.js +58 -0
  462. package/lib/registry/index.d.ts +4 -0
  463. package/lib/registry/index.js +2 -0
  464. package/lib/registry/registry.d.ts +109 -0
  465. package/lib/registry/registry.js +299 -0
  466. package/lib/runtime/action.d.ts +46 -0
  467. package/lib/runtime/action.js +39 -0
  468. package/lib/runtime/behavior.d.ts +110 -0
  469. package/lib/runtime/behavior.js +179 -0
  470. package/lib/runtime/behaviorTuning.d.ts +59 -0
  471. package/lib/runtime/behaviorTuning.js +95 -0
  472. package/lib/runtime/cognitiveRuntime.d.ts +189 -0
  473. package/lib/runtime/cognitiveRuntime.js +490 -0
  474. package/lib/runtime/escalation.d.ts +22 -0
  475. package/lib/runtime/escalation.js +15 -0
  476. package/lib/runtime/governedTask.d.ts +57 -0
  477. package/lib/runtime/governedTask.js +150 -0
  478. package/lib/runtime/index.d.ts +15 -0
  479. package/lib/runtime/index.js +15 -0
  480. package/lib/runtime/kernelRuntime.d.ts +33 -0
  481. package/lib/runtime/kernelRuntime.js +105 -0
  482. package/lib/runtime/operation.d.ts +30 -0
  483. package/lib/runtime/operation.js +1 -0
  484. package/lib/runtime/replay.d.ts +24 -0
  485. package/lib/runtime/replay.js +38 -0
  486. package/lib/runtime/routing.d.ts +12 -0
  487. package/lib/runtime/routing.js +44 -0
  488. package/lib/runtime/safety.d.ts +15 -0
  489. package/lib/runtime/safety.js +28 -0
  490. package/lib/runtime/session.d.ts +147 -0
  491. package/lib/runtime/session.js +214 -0
  492. package/lib/runtime/sessionStore.d.ts +24 -0
  493. package/lib/runtime/sessionStore.js +20 -0
  494. package/lib/runtime/telemetry.d.ts +24 -0
  495. package/lib/runtime/telemetry.js +33 -0
  496. package/lib/runtime/turnStore.d.ts +16 -0
  497. package/lib/runtime/turnStore.js +15 -0
  498. package/lib/scenario/index.d.ts +1 -0
  499. package/lib/scenario/index.js +1 -0
  500. package/lib/scenario/scenario.d.ts +52 -0
  501. package/lib/scenario/scenario.js +210 -0
  502. package/lib/semantic/canonical.d.ts +6 -0
  503. package/lib/semantic/canonical.js +22 -0
  504. package/lib/semantic/index.d.ts +2 -0
  505. package/lib/semantic/index.js +2 -0
  506. package/lib/semantic/sha256.d.ts +1 -0
  507. package/lib/semantic/sha256.js +66 -0
  508. package/lib/storage/appendLog.d.ts +145 -0
  509. package/lib/storage/appendLog.js +299 -0
  510. package/lib/storage/fileAppendSink.d.ts +7 -0
  511. package/lib/storage/fileAppendSink.js +34 -0
  512. package/lib/storage/index.d.ts +2 -0
  513. package/lib/storage/index.js +2 -0
  514. package/lib/store/bindCache.d.ts +9 -0
  515. package/lib/store/bindCache.js +18 -0
  516. package/lib/store/cache.d.ts +48 -0
  517. package/lib/store/cache.js +162 -0
  518. package/lib/store/context.d.ts +10 -0
  519. package/lib/store/context.js +27 -0
  520. package/lib/store/handleStore.d.ts +9 -0
  521. package/lib/store/handleStore.js +25 -0
  522. package/lib/store/index.d.ts +9 -0
  523. package/lib/store/index.js +8 -0
  524. package/lib/store/messageStore.d.ts +9 -0
  525. package/lib/store/messageStore.js +25 -0
  526. package/lib/store/objectStore.d.ts +9 -0
  527. package/lib/store/objectStore.js +25 -0
  528. package/lib/store/processStore.d.ts +9 -0
  529. package/lib/store/processStore.js +25 -0
  530. package/lib/store/threadStore.d.ts +9 -0
  531. package/lib/store/threadStore.js +25 -0
  532. package/lib/store/windowStore.d.ts +9 -0
  533. package/lib/store/windowStore.js +25 -0
  534. package/lib/structure/abstractSyntaxTree.d.ts +181 -0
  535. package/lib/structure/abstractSyntaxTree.js +400 -0
  536. package/lib/structure/avlTree.d.ts +125 -0
  537. package/lib/structure/avlTree.js +369 -0
  538. package/lib/structure/binarySearchTree.d.ts +125 -0
  539. package/lib/structure/binarySearchTree.js +306 -0
  540. package/lib/structure/binaryTree.d.ts +174 -0
  541. package/lib/structure/binaryTree.js +495 -0
  542. package/lib/structure/bloomFilter.d.ts +126 -0
  543. package/lib/structure/bloomFilter.js +177 -0
  544. package/lib/structure/compare.d.ts +55 -0
  545. package/lib/structure/compare.js +96 -0
  546. package/lib/structure/cuckooFilter.d.ts +149 -0
  547. package/lib/structure/cuckooFilter.js +267 -0
  548. package/lib/structure/deque.d.ts +117 -0
  549. package/lib/structure/deque.js +205 -0
  550. package/lib/structure/filterKey.d.ts +19 -0
  551. package/lib/structure/filterKey.js +28 -0
  552. package/lib/structure/hash.d.ts +129 -0
  553. package/lib/structure/hash.js +241 -0
  554. package/lib/structure/heap.d.ts +152 -0
  555. package/lib/structure/heap.js +227 -0
  556. package/lib/structure/index.d.ts +20 -0
  557. package/lib/structure/index.js +20 -0
  558. package/lib/structure/iterator.d.ts +6 -0
  559. package/lib/structure/iterator.js +16 -0
  560. package/lib/structure/lru.d.ts +235 -0
  561. package/lib/structure/lru.js +524 -0
  562. package/lib/structure/ordered.d.ts +89 -0
  563. package/lib/structure/ordered.js +336 -0
  564. package/lib/structure/priority.d.ts +499 -0
  565. package/lib/structure/priority.js +756 -0
  566. package/lib/structure/queue.d.ts +90 -0
  567. package/lib/structure/queue.js +154 -0
  568. package/lib/structure/redBlackTree.d.ts +142 -0
  569. package/lib/structure/redBlackTree.js +644 -0
  570. package/lib/structure/segmentTree.d.ts +129 -0
  571. package/lib/structure/segmentTree.js +205 -0
  572. package/lib/structure/stack.d.ts +77 -0
  573. package/lib/structure/stack.js +107 -0
  574. package/lib/structure/unordered.d.ts +99 -0
  575. package/lib/structure/unordered.js +341 -0
  576. package/lib/thread/index.d.ts +2 -0
  577. package/lib/thread/index.js +2 -0
  578. package/lib/thread/thread.d.ts +107 -0
  579. package/lib/thread/thread.js +81 -0
  580. package/lib/thread/transitions.d.ts +8 -0
  581. package/lib/thread/transitions.js +9 -0
  582. package/lib/types/common.d.ts +80 -0
  583. package/lib/types/common.js +5 -0
  584. package/lib/types/index.d.ts +23 -0
  585. package/lib/types/index.js +1 -0
  586. package/lib/warrant/epistemic.d.ts +141 -0
  587. package/lib/warrant/epistemic.js +1 -0
  588. package/lib/warrant/index.d.ts +3 -0
  589. package/lib/warrant/index.js +3 -0
  590. package/lib/warrant/inquiry.d.ts +69 -0
  591. package/lib/warrant/inquiry.js +119 -0
  592. package/lib/warrant/warrant.d.ts +46 -0
  593. package/lib/warrant/warrant.js +153 -0
  594. package/lib/window/compaction.d.ts +57 -0
  595. package/lib/window/compaction.js +334 -0
  596. package/lib/window/compactionTypes.d.ts +113 -0
  597. package/lib/window/compactionTypes.js +1 -0
  598. package/lib/window/index.d.ts +7 -0
  599. package/lib/window/index.js +3 -0
  600. package/lib/window/page.d.ts +16 -0
  601. package/lib/window/page.js +2 -0
  602. package/lib/window/window.d.ts +68 -0
  603. package/lib/window/window.js +194 -0
  604. package/package.json +22 -1
  605. package/src/authz/index.ts +1 -0
  606. package/src/concept/index.ts +3 -0
  607. package/src/concurrency/index.ts +5 -0
  608. package/src/cooperation/index.ts +6 -0
  609. package/src/delegate/index.ts +2 -0
  610. package/src/error/index.ts +7 -0
  611. package/src/evaluation/index.ts +2 -0
  612. package/src/execution/index.ts +3 -0
  613. package/src/frame/index.ts +1 -0
  614. package/src/index.ts +11 -0
  615. package/src/ledger/index.ts +4 -0
  616. package/src/manifest/index.ts +8 -0
  617. package/src/policy/index.ts +2 -0
  618. package/src/protocol/index.ts +6 -0
  619. package/src/receipt/index.ts +1 -0
  620. package/src/semantic/index.ts +2 -0
  621. package/src/storage/index.ts +2 -0
  622. package/src/structure/index.ts +20 -0
  623. package/src/thread/index.ts +2 -0
  624. package/src/warrant/index.ts +3 -0
  625. package/src/window/index.ts +7 -4
  626. package/tools/rewrite-declaration-extensions.ts +98 -0
  627. package/tsconfig.build.json +14 -0
package/docs/probes/eval-recorded-replay.json CHANGED
@@ -1,597 +1,597 @@
1
- {
2
- "generatedAt": "2026-10-28T19:55:30.936Z",
3
- "kind": "recorded-replay",
4
- "model": "deepseek-flash",
5
- "note": "recorded answers replayed through the runtime; labels are fixture labels, not an independent human study",
6
- "metrics": {
7
- "runs": 40,
8
- "accuracy": 0.825,
9
- "textEce": 0.31409611637991663,
10
- "textBrier": 0.24285764964591255,
11
- "calibratedEce": 0.2814990155194531,
12
- "calibratedBrier": 0.2229779176013041,
13
- "calibratedMethod": "temperature",
14
- "calibrationStatus": "activated",
15
- "calibrationTemperature": 0.25,
16
- "calibrationCiLower": -0.03446510913785705,
17
- "calibrationCiUpper": -0.03041775787017087,
18
- "oracleEce": 0.22222222222222185,
19
- "oracleBrier": 0.04938271604938271,
20
- "labeled": 10,
21
- "labelAgreement": 1,
22
- "tokens": 8922,
23
- "costUsd": 0.00104298
24
- },
25
- "conditions": [
26
- {
27
- "key": "objective/bare",
28
- "runs": 5,
29
- "accuracy": 0.8,
30
- "textEce": 0.2880486731887464,
31
- "textBrier": 0.2433100286183028,
32
- "oracleEce": 0.22222222222222224,
33
- "oracleBrier": 0.04938271604938271,
34
- "tokens": 271,
35
- "costUsd": 0.00004605
36
- },
37
- {
38
- "key": "context/bare",
39
- "runs": 5,
40
- "accuracy": 0.2,
41
- "textEce": 0.30943746315244475,
42
- "textBrier": 0.25608953409472635,
43
- "oracleEce": 0.22222222222222224,
44
- "oracleBrier": 0.04938271604938271,
45
- "tokens": 235,
46
- "costUsd": 0.000053700000000000004
47
- },
48
- {
49
- "key": "objective/person",
50
- "runs": 5,
51
- "accuracy": 0.8,
52
- "textEce": 0.2880486731887464,
53
- "textBrier": 0.2433100286183028,
54
- "oracleEce": 0.22222222222222224,
55
- "oracleBrier": 0.04938271604938271,
56
- "tokens": 1236,
57
- "costUsd": 0.00019079999999999998
58
- },
59
- {
60
- "key": "context/person",
61
- "runs": 5,
62
- "accuracy": 0.8,
63
- "textEce": 0.2905625368475553,
64
- "textBrier": 0.24409421466944345,
65
- "oracleEce": 0.22222222222222224,
66
- "oracleBrier": 0.04938271604938271,
67
- "tokens": 1192,
68
- "costUsd": 0.00019364999999999996
69
- },
70
- {
71
- "key": "objective/person+attention",
72
- "runs": 5,
73
- "accuracy": 1,
74
- "textEce": 0.48804867318874634,
75
- "textBrier": 0.23819431607262684,
76
- "oracleEce": 0.2222222222222222,
77
- "oracleBrier": 0.04938271604938271,
78
- "tokens": 1591,
79
- "costUsd": 0.00014996999999999998
80
- },
81
- {
82
- "key": "context/person+attention",
83
- "runs": 5,
84
- "accuracy": 1,
85
- "textEce": 0.4897245822946189,
86
- "textBrier": 0.23983437951063563,
87
- "oracleEce": 0.2222222222222222,
88
- "oracleBrier": 0.04938271604938271,
89
- "tokens": 1543,
90
- "costUsd": 0.00015041999999999996
91
- },
92
- {
93
- "key": "objective/person+attention+scenario",
94
- "runs": 5,
95
- "accuracy": 1,
96
- "textEce": 0.48804867318874634,
97
- "textBrier": 0.23819431607262684,
98
- "oracleEce": 0.2222222222222222,
99
- "oracleBrier": 0.04938271604938271,
100
- "tokens": 1451,
101
- "costUsd": 0.00012897
102
- },
103
- {
104
- "key": "context/person+attention+scenario",
105
- "runs": 5,
106
- "accuracy": 1,
107
- "textEce": 0.4897245822946189,
108
- "textBrier": 0.23983437951063563,
109
- "oracleEce": 0.2222222222222222,
110
- "oracleBrier": 0.04938271604938271,
111
- "tokens": 1403,
112
- "costUsd": 0.00012942
113
- }
114
- ],
115
- "cases": [
116
- {
117
- "suite": "objective",
118
- "condition": "bare",
119
- "task": "unique-rows",
120
- "actual": true,
121
- "humanLabel": "correct",
122
- "answer": "14",
123
- "textCorrectness": 0.51278928136419,
124
- "oracleCorrectness": 0.7777777777777778,
125
- "tokens": 46,
126
- "costUsd": 0.00000735
127
- },
128
- {
129
- "suite": "objective",
130
- "condition": "bare",
131
- "task": "syllogism",
132
- "actual": true,
133
- "humanLabel": null,
134
- "answer": "No",
135
- "textCorrectness": 0.5085995085995085,
136
- "oracleCorrectness": 0.7777777777777778,
137
- "tokens": 44,
138
- "costUsd": 0.00000705
139
- },
140
- {
141
- "suite": "objective",
142
- "condition": "bare",
143
- "task": "array-expression",
144
- "actual": true,
145
- "humanLabel": null,
146
- "answer": "[4,6]",
147
- "textCorrectness": 0.51278928136419,
148
- "oracleCorrectness": 0.7777777777777778,
149
- "tokens": 62,
150
- "costUsd": 0.00001155
151
- },
152
- {
153
- "suite": "objective",
154
- "condition": "bare",
155
- "task": "incident-minutes",
156
- "actual": true,
157
- "humanLabel": null,
158
- "answer": "38",
159
- "textCorrectness": 0.51278928136419,
160
- "oracleCorrectness": 0.7777777777777778,
161
- "tokens": 53,
162
- "costUsd": 0.0000084
163
- },
164
- {
165
- "suite": "objective",
166
- "condition": "bare",
167
- "task": "bayes",
168
- "actual": false,
169
- "humanLabel": "incorrect",
170
- "answer": "8.3%",
171
- "textCorrectness": 0.51278928136419,
172
- "oracleCorrectness": 0.2222222222222222,
173
- "tokens": 66,
174
- "costUsd": 0.0000117
175
- },
176
- {
177
- "suite": "context",
178
- "condition": "bare",
179
- "task": "memory-penalty",
180
- "actual": false,
181
- "humanLabel": null,
182
- "answer": "Being too verbose",
183
- "textCorrectness": 0.5085995085995085,
184
- "oracleCorrectness": 0.2222222222222222,
185
- "tokens": 44,
186
- "costUsd": 0.00000795
187
- },
188
- {
189
- "suite": "context",
190
- "condition": "bare",
191
- "task": "role-obligation",
192
- "actual": false,
193
- "humanLabel": "incorrect",
194
- "answer": "I am a helpful AI assistant, and one of my obligations is to provide accurate and safe information.",
195
- "textCorrectness": 0.5085995085995085,
196
- "oracleCorrectness": 0.2222222222222222,
197
- "tokens": 60,
198
- "costUsd": 0.000018
199
- },
200
- {
201
- "suite": "context",
202
- "condition": "bare",
203
- "task": "attention-slots",
204
- "actual": false,
205
- "humanLabel": null,
206
- "answer": "I don’t have enough context to determine the foreground slots or safety floor.",
207
- "textCorrectness": 0.5085995085995085,
208
- "oracleCorrectness": 0.2222222222222222,
209
- "tokens": 59,
210
- "costUsd": 0.00001605
211
- },
212
- {
213
- "suite": "context",
214
- "condition": "bare",
215
- "task": "stress-level",
216
- "actual": false,
217
- "humanLabel": null,
218
- "answer": "0",
219
- "textCorrectness": 0.51278928136419,
220
- "oracleCorrectness": 0.2222222222222222,
221
- "tokens": 34,
222
- "costUsd": 0.00000555
223
- },
224
- {
225
- "suite": "context",
226
- "condition": "bare",
227
- "task": "fabrication",
228
- "actual": true,
229
- "humanLabel": null,
230
- "answer": "No",
231
- "textCorrectness": 0.5085995085995085,
232
- "oracleCorrectness": 0.7777777777777778,
233
- "tokens": 38,
234
- "costUsd": 0.0000061499999999999996
235
- },
236
- {
237
- "suite": "objective",
238
- "condition": "person",
239
- "task": "unique-rows",
240
- "actual": true,
241
- "humanLabel": null,
242
- "answer": "14",
243
- "textCorrectness": 0.51278928136419,
244
- "oracleCorrectness": 0.7777777777777778,
245
- "tokens": 239,
246
- "costUsd": 0.0000363
247
- },
248
- {
249
- "suite": "objective",
250
- "condition": "person",
251
- "task": "syllogism",
252
- "actual": true,
253
- "humanLabel": null,
254
- "answer": "No",
255
- "textCorrectness": 0.5085995085995085,
256
- "oracleCorrectness": 0.7777777777777778,
257
- "tokens": 237,
258
- "costUsd": 0.000036
259
- },
260
- {
261
- "suite": "objective",
262
- "condition": "person",
263
- "task": "array-expression",
264
- "actual": true,
265
- "humanLabel": null,
266
- "answer": "[4,6]",
267
- "textCorrectness": 0.51278928136419,
268
- "oracleCorrectness": 0.7777777777777778,
269
- "tokens": 255,
270
- "costUsd": 0.000040499999999999995
271
- },
272
- {
273
- "suite": "objective",
274
- "condition": "person",
275
- "task": "incident-minutes",
276
- "actual": true,
277
- "humanLabel": null,
278
- "answer": "38",
279
- "textCorrectness": 0.51278928136419,
280
- "oracleCorrectness": 0.7777777777777778,
281
- "tokens": 246,
282
- "costUsd": 0.00003735
283
- },
284
- {
285
- "suite": "objective",
286
- "condition": "person",
287
- "task": "bayes",
288
- "actual": false,
289
- "humanLabel": "incorrect",
290
- "answer": "8.3%",
291
- "textCorrectness": 0.51278928136419,
292
- "oracleCorrectness": 0.2222222222222222,
293
- "tokens": 259,
294
- "costUsd": 0.00004065
295
- },
296
- {
297
- "suite": "context",
298
- "condition": "person",
299
- "task": "memory-penalty",
300
- "actual": true,
301
- "humanLabel": "correct",
302
- "answer": "Adding unrequested explanation.",
303
- "textCorrectness": 0.5085995085995085,
304
- "oracleCorrectness": 0.7777777777777778,
305
- "tokens": 240,
306
- "costUsd": 0.0000387
307
- },
308
- {
309
- "suite": "context",
310
- "condition": "person",
311
- "task": "role-obligation",
312
- "actual": true,
313
- "humanLabel": null,
314
- "answer": "My active role is Analyst, and one obligation is to ground claims in evidence.",
315
- "textCorrectness": 0.5085995085995085,
316
- "oracleCorrectness": 0.7777777777777778,
317
- "tokens": 249,
318
- "costUsd": 0.00004455
319
- },
320
- {
321
- "suite": "context",
322
- "condition": "person",
323
- "task": "attention-slots",
324
- "actual": false,
325
- "humanLabel": "incorrect",
326
- "answer": "I don't have that information.",
327
- "textCorrectness": 0.5085995085995085,
328
- "oracleCorrectness": 0.2222222222222222,
329
- "tokens": 243,
330
- "costUsd": 0.0000396
331
- },
332
- {
333
- "suite": "context",
334
- "condition": "person",
335
- "task": "stress-level",
336
- "actual": true,
337
- "humanLabel": null,
338
- "answer": "0.35",
339
- "textCorrectness": 0.51278928136419,
340
- "oracleCorrectness": 0.7777777777777778,
341
- "tokens": 229,
342
- "costUsd": 0.0000357
343
- },
344
- {
345
- "suite": "context",
346
- "condition": "person",
347
- "task": "fabrication",
348
- "actual": true,
349
- "humanLabel": null,
350
- "answer": "No",
351
- "textCorrectness": 0.5085995085995085,
352
- "oracleCorrectness": 0.7777777777777778,
353
- "tokens": 231,
354
- "costUsd": 0.0000351
355
- },
356
- {
357
- "suite": "objective",
358
- "condition": "person+attention",
359
- "task": "unique-rows",
360
- "actual": true,
361
- "humanLabel": null,
362
- "answer": "14",
363
- "textCorrectness": 0.51278928136419,
364
- "oracleCorrectness": 0.7777777777777778,
365
- "tokens": 310,
366
- "costUsd": 0.000028134
367
- },
368
- {
369
- "suite": "objective",
370
- "condition": "person+attention",
371
- "task": "syllogism",
372
- "actual": true,
373
- "humanLabel": null,
374
- "answer": "No",
375
- "textCorrectness": 0.5085995085995085,
376
- "oracleCorrectness": 0.7777777777777778,
377
- "tokens": 308,
378
- "costUsd": 0.000027833999999999998
379
- },
380
- {
381
- "suite": "objective",
382
- "condition": "person+attention",
383
- "task": "array-expression",
384
- "actual": true,
385
- "humanLabel": null,
386
- "answer": "[4,6]",
387
- "textCorrectness": 0.51278928136419,
388
- "oracleCorrectness": 0.7777777777777778,
389
- "tokens": 326,
390
- "costUsd": 0.000032334
391
- },
392
- {
393
- "suite": "objective",
394
- "condition": "person+attention",
395
- "task": "incident-minutes",
396
- "actual": true,
397
- "humanLabel": null,
398
- "answer": "38",
399
- "textCorrectness": 0.51278928136419,
400
- "oracleCorrectness": 0.7777777777777778,
401
- "tokens": 317,
402
- "costUsd": 0.000029183999999999997
403
- },
404
- {
405
- "suite": "objective",
406
- "condition": "person+attention",
407
- "task": "bayes",
408
- "actual": true,
409
- "humanLabel": null,
410
- "answer": "7.5%",
411
- "textCorrectness": 0.51278928136419,
412
- "oracleCorrectness": 0.7777777777777778,
413
- "tokens": 330,
414
- "costUsd": 0.000032483999999999996
415
- },
416
- {
417
- "suite": "context",
418
- "condition": "person+attention",
419
- "task": "memory-penalty",
420
- "actual": true,
421
- "humanLabel": null,
422
- "answer": "Adding unrequested explanation.",
423
- "textCorrectness": 0.5085995085995085,
424
- "oracleCorrectness": 0.7777777777777778,
425
- "tokens": 311,
426
- "costUsd": 0.000030533999999999996
427
- },
428
- {
429
- "suite": "context",
430
- "condition": "person+attention",
431
- "task": "role-obligation",
432
- "actual": true,
433
- "humanLabel": null,
434
- "answer": "My active role is Analyst, and one obligation is to ground claims in evidence.",
435
- "textCorrectness": 0.5085995085995085,
436
- "oracleCorrectness": 0.7777777777777778,
437
- "tokens": 320,
438
- "costUsd": 0.000036383999999999996
439
- },
440
- {
441
- "suite": "context",
442
- "condition": "person+attention",
443
- "task": "attention-slots",
444
- "actual": true,
445
- "humanLabel": "correct",
446
- "answer": "2\n1",
447
- "textCorrectness": 0.51278928136419,
448
- "oracleCorrectness": 0.7777777777777778,
449
- "tokens": 310,
450
- "costUsd": 0.000029033999999999997
451
- },
452
- {
453
- "suite": "context",
454
- "condition": "person+attention",
455
- "task": "stress-level",
456
- "actual": true,
457
- "humanLabel": "correct",
458
- "answer": "0.35",
459
- "textCorrectness": 0.51278928136419,
460
- "oracleCorrectness": 0.7777777777777778,
461
- "tokens": 300,
462
- "costUsd": 0.000027533999999999998
463
- },
464
- {
465
- "suite": "context",
466
- "condition": "person+attention",
467
- "task": "fabrication",
468
- "actual": true,
469
- "humanLabel": null,
470
- "answer": "No",
471
- "textCorrectness": 0.5085995085995085,
472
- "oracleCorrectness": 0.7777777777777778,
473
- "tokens": 302,
474
- "costUsd": 0.000026933999999999997
475
- },
476
- {
477
- "suite": "objective",
478
- "condition": "person+attention+scenario",
479
- "task": "unique-rows",
480
- "actual": true,
481
- "humanLabel": null,
482
- "answer": "14",
483
- "textCorrectness": 0.51278928136419,
484
- "oracleCorrectness": 0.7777777777777778,
485
- "tokens": 282,
486
- "costUsd": 0.000023933999999999998
487
- },
488
- {
489
- "suite": "objective",
490
- "condition": "person+attention+scenario",
491
- "task": "syllogism",
492
- "actual": true,
493
- "humanLabel": null,
494
- "answer": "No",
495
- "textCorrectness": 0.5085995085995085,
496
- "oracleCorrectness": 0.7777777777777778,
497
- "tokens": 280,
498
- "costUsd": 0.000023633999999999998
499
- },
500
- {
501
- "suite": "objective",
502
- "condition": "person+attention+scenario",
503
- "task": "array-expression",
504
- "actual": true,
505
- "humanLabel": null,
506
- "answer": "[4,6]",
507
- "textCorrectness": 0.51278928136419,
508
- "oracleCorrectness": 0.7777777777777778,
509
- "tokens": 298,
510
- "costUsd": 0.000028134
511
- },
512
- {
513
- "suite": "objective",
514
- "condition": "person+attention+scenario",
515
- "task": "incident-minutes",
516
- "actual": true,
517
- "humanLabel": null,
518
- "answer": "38",
519
- "textCorrectness": 0.51278928136419,
520
- "oracleCorrectness": 0.7777777777777778,
521
- "tokens": 289,
522
- "costUsd": 0.000024984
523
- },
524
- {
525
- "suite": "objective",
526
- "condition": "person+attention+scenario",
527
- "task": "bayes",
528
- "actual": true,
529
- "humanLabel": "correct",
530
- "answer": "7.5%",
531
- "textCorrectness": 0.51278928136419,
532
- "oracleCorrectness": 0.7777777777777778,
533
- "tokens": 302,
534
- "costUsd": 0.000028284
535
- },
536
- {
537
- "suite": "context",
538
- "condition": "person+attention+scenario",
539
- "task": "memory-penalty",
540
- "actual": true,
541
- "humanLabel": null,
542
- "answer": "Adding unrequested explanation.",
543
- "textCorrectness": 0.5085995085995085,
544
- "oracleCorrectness": 0.7777777777777778,
545
- "tokens": 283,
546
- "costUsd": 0.000026333999999999996
547
- },
548
- {
549
- "suite": "context",
550
- "condition": "person+attention+scenario",
551
- "task": "role-obligation",
552
- "actual": true,
553
- "humanLabel": null,
554
- "answer": "My active role is Analyst, and one obligation is to ground claims in evidence.",
555
- "textCorrectness": 0.5085995085995085,
556
- "oracleCorrectness": 0.7777777777777778,
557
- "tokens": 292,
558
- "costUsd": 0.000032183999999999995
559
- },
560
- {
561
- "suite": "context",
562
- "condition": "person+attention+scenario",
563
- "task": "attention-slots",
564
- "actual": true,
565
- "humanLabel": null,
566
- "answer": "2 1",
567
- "textCorrectness": 0.51278928136419,
568
- "oracleCorrectness": 0.7777777777777778,
569
- "tokens": 282,
570
- "costUsd": 0.000024833999999999996
571
- },
572
- {
573
- "suite": "context",
574
- "condition": "person+attention+scenario",
575
- "task": "stress-level",
576
- "actual": true,
577
- "humanLabel": null,
578
- "answer": "0.35",
579
- "textCorrectness": 0.51278928136419,
580
- "oracleCorrectness": 0.7777777777777778,
581
- "tokens": 272,
582
- "costUsd": 0.000023333999999999997
583
- },
584
- {
585
- "suite": "context",
586
- "condition": "person+attention+scenario",
587
- "task": "fabrication",
588
- "actual": true,
589
- "humanLabel": "correct",
590
- "answer": "No",
591
- "textCorrectness": 0.5085995085995085,
592
- "oracleCorrectness": 0.7777777777777778,
593
- "tokens": 274,
594
- "costUsd": 0.000022734
595
- }
596
- ]
597
- }
1
+ {
2
+ "generatedAt": "2026-10-28T19:55:30.936Z",
3
+ "kind": "recorded-replay",
4
+ "model": "deepseek-flash",
5
+ "note": "recorded answers replayed through the runtime; labels are fixture labels, not an independent human study",
6
+ "metrics": {
7
+ "runs": 40,
8
+ "accuracy": 0.825,
9
+ "textEce": 0.31409611637991663,
10
+ "textBrier": 0.24285764964591255,
11
+ "calibratedEce": 0.2814990155194531,
12
+ "calibratedBrier": 0.2229779176013041,
13
+ "calibratedMethod": "temperature",
14
+ "calibrationStatus": "activated",
15
+ "calibrationTemperature": 0.25,
16
+ "calibrationCiLower": -0.03446510913785705,
17
+ "calibrationCiUpper": -0.03041775787017087,
18
+ "oracleEce": 0.22222222222222185,
19
+ "oracleBrier": 0.04938271604938271,
20
+ "labeled": 10,
21
+ "labelAgreement": 1,
22
+ "tokens": 8922,
23
+ "costUsd": 0.00104298
24
+ },
25
+ "conditions": [
26
+ {
27
+ "key": "objective/bare",
28
+ "runs": 5,
29
+ "accuracy": 0.8,
30
+ "textEce": 0.2880486731887464,
31
+ "textBrier": 0.2433100286183028,
32
+ "oracleEce": 0.22222222222222224,
33
+ "oracleBrier": 0.04938271604938271,
34
+ "tokens": 271,
35
+ "costUsd": 0.00004605
36
+ },
37
+ {
38
+ "key": "context/bare",
39
+ "runs": 5,
40
+ "accuracy": 0.2,
41
+ "textEce": 0.30943746315244475,
42
+ "textBrier": 0.25608953409472635,
43
+ "oracleEce": 0.22222222222222224,
44
+ "oracleBrier": 0.04938271604938271,
45
+ "tokens": 235,
46
+ "costUsd": 0.000053700000000000004
47
+ },
48
+ {
49
+ "key": "objective/person",
50
+ "runs": 5,
51
+ "accuracy": 0.8,
52
+ "textEce": 0.2880486731887464,
53
+ "textBrier": 0.2433100286183028,
54
+ "oracleEce": 0.22222222222222224,
55
+ "oracleBrier": 0.04938271604938271,
56
+ "tokens": 1236,
57
+ "costUsd": 0.00019079999999999998
58
+ },
59
+ {
60
+ "key": "context/person",
61
+ "runs": 5,
62
+ "accuracy": 0.8,
63
+ "textEce": 0.2905625368475553,
64
+ "textBrier": 0.24409421466944345,
65
+ "oracleEce": 0.22222222222222224,
66
+ "oracleBrier": 0.04938271604938271,
67
+ "tokens": 1192,
68
+ "costUsd": 0.00019364999999999996
69
+ },
70
+ {
71
+ "key": "objective/person+attention",
72
+ "runs": 5,
73
+ "accuracy": 1,
74
+ "textEce": 0.48804867318874634,
75
+ "textBrier": 0.23819431607262684,
76
+ "oracleEce": 0.2222222222222222,
77
+ "oracleBrier": 0.04938271604938271,
78
+ "tokens": 1591,
79
+ "costUsd": 0.00014996999999999998
80
+ },
81
+ {
82
+ "key": "context/person+attention",
83
+ "runs": 5,
84
+ "accuracy": 1,
85
+ "textEce": 0.4897245822946189,
86
+ "textBrier": 0.23983437951063563,
87
+ "oracleEce": 0.2222222222222222,
88
+ "oracleBrier": 0.04938271604938271,
89
+ "tokens": 1543,
90
+ "costUsd": 0.00015041999999999996
91
+ },
92
+ {
93
+ "key": "objective/person+attention+scenario",
94
+ "runs": 5,
95
+ "accuracy": 1,
96
+ "textEce": 0.48804867318874634,
97
+ "textBrier": 0.23819431607262684,
98
+ "oracleEce": 0.2222222222222222,
99
+ "oracleBrier": 0.04938271604938271,
100
+ "tokens": 1451,
101
+ "costUsd": 0.00012897
102
+ },
103
+ {
104
+ "key": "context/person+attention+scenario",
105
+ "runs": 5,
106
+ "accuracy": 1,
107
+ "textEce": 0.4897245822946189,
108
+ "textBrier": 0.23983437951063563,
109
+ "oracleEce": 0.2222222222222222,
110
+ "oracleBrier": 0.04938271604938271,
111
+ "tokens": 1403,
112
+ "costUsd": 0.00012942
113
+ }
114
+ ],
115
+ "cases": [
116
+ {
117
+ "suite": "objective",
118
+ "condition": "bare",
119
+ "task": "unique-rows",
120
+ "actual": true,
121
+ "humanLabel": "correct",
122
+ "answer": "14",
123
+ "textCorrectness": 0.51278928136419,
124
+ "oracleCorrectness": 0.7777777777777778,
125
+ "tokens": 46,
126
+ "costUsd": 0.00000735
127
+ },
128
+ {
129
+ "suite": "objective",
130
+ "condition": "bare",
131
+ "task": "syllogism",
132
+ "actual": true,
133
+ "humanLabel": null,
134
+ "answer": "No",
135
+ "textCorrectness": 0.5085995085995085,
136
+ "oracleCorrectness": 0.7777777777777778,
137
+ "tokens": 44,
138
+ "costUsd": 0.00000705
139
+ },
140
+ {
141
+ "suite": "objective",
142
+ "condition": "bare",
143
+ "task": "array-expression",
144
+ "actual": true,
145
+ "humanLabel": null,
146
+ "answer": "[4,6]",
147
+ "textCorrectness": 0.51278928136419,
148
+ "oracleCorrectness": 0.7777777777777778,
149
+ "tokens": 62,
150
+ "costUsd": 0.00001155
151
+ },
152
+ {
153
+ "suite": "objective",
154
+ "condition": "bare",
155
+ "task": "incident-minutes",
156
+ "actual": true,
157
+ "humanLabel": null,
158
+ "answer": "38",
159
+ "textCorrectness": 0.51278928136419,
160
+ "oracleCorrectness": 0.7777777777777778,
161
+ "tokens": 53,
162
+ "costUsd": 0.0000084
163
+ },
164
+ {
165
+ "suite": "objective",
166
+ "condition": "bare",
167
+ "task": "bayes",
168
+ "actual": false,
169
+ "humanLabel": "incorrect",
170
+ "answer": "8.3%",
171
+ "textCorrectness": 0.51278928136419,
172
+ "oracleCorrectness": 0.2222222222222222,
173
+ "tokens": 66,
174
+ "costUsd": 0.0000117
175
+ },
176
+ {
177
+ "suite": "context",
178
+ "condition": "bare",
179
+ "task": "memory-penalty",
180
+ "actual": false,
181
+ "humanLabel": null,
182
+ "answer": "Being too verbose",
183
+ "textCorrectness": 0.5085995085995085,
184
+ "oracleCorrectness": 0.2222222222222222,
185
+ "tokens": 44,
186
+ "costUsd": 0.00000795
187
+ },
188
+ {
189
+ "suite": "context",
190
+ "condition": "bare",
191
+ "task": "role-obligation",
192
+ "actual": false,
193
+ "humanLabel": "incorrect",
194
+ "answer": "I am a helpful AI assistant, and one of my obligations is to provide accurate and safe information.",
195
+ "textCorrectness": 0.5085995085995085,
196
+ "oracleCorrectness": 0.2222222222222222,
197
+ "tokens": 60,
198
+ "costUsd": 0.000018
199
+ },
200
+ {
201
+ "suite": "context",
202
+ "condition": "bare",
203
+ "task": "attention-slots",
204
+ "actual": false,
205
+ "humanLabel": null,
206
+ "answer": "I don’t have enough context to determine the foreground slots or safety floor.",
207
+ "textCorrectness": 0.5085995085995085,
208
+ "oracleCorrectness": 0.2222222222222222,
209
+ "tokens": 59,
210
+ "costUsd": 0.00001605
211
+ },
212
+ {
213
+ "suite": "context",
214
+ "condition": "bare",
215
+ "task": "stress-level",
216
+ "actual": false,
217
+ "humanLabel": null,
218
+ "answer": "0",
219
+ "textCorrectness": 0.51278928136419,
220
+ "oracleCorrectness": 0.2222222222222222,
221
+ "tokens": 34,
222
+ "costUsd": 0.00000555
223
+ },
224
+ {
225
+ "suite": "context",
226
+ "condition": "bare",
227
+ "task": "fabrication",
228
+ "actual": true,
229
+ "humanLabel": null,
230
+ "answer": "No",
231
+ "textCorrectness": 0.5085995085995085,
232
+ "oracleCorrectness": 0.7777777777777778,
233
+ "tokens": 38,
234
+ "costUsd": 0.0000061499999999999996
235
+ },
236
+ {
237
+ "suite": "objective",
238
+ "condition": "person",
239
+ "task": "unique-rows",
240
+ "actual": true,
241
+ "humanLabel": null,
242
+ "answer": "14",
243
+ "textCorrectness": 0.51278928136419,
244
+ "oracleCorrectness": 0.7777777777777778,
245
+ "tokens": 239,
246
+ "costUsd": 0.0000363
247
+ },
248
+ {
249
+ "suite": "objective",
250
+ "condition": "person",
251
+ "task": "syllogism",
252
+ "actual": true,
253
+ "humanLabel": null,
254
+ "answer": "No",
255
+ "textCorrectness": 0.5085995085995085,
256
+ "oracleCorrectness": 0.7777777777777778,
257
+ "tokens": 237,
258
+ "costUsd": 0.000036
259
+ },
260
+ {
261
+ "suite": "objective",
262
+ "condition": "person",
263
+ "task": "array-expression",
264
+ "actual": true,
265
+ "humanLabel": null,
266
+ "answer": "[4,6]",
267
+ "textCorrectness": 0.51278928136419,
268
+ "oracleCorrectness": 0.7777777777777778,
269
+ "tokens": 255,
270
+ "costUsd": 0.000040499999999999995
271
+ },
272
+ {
273
+ "suite": "objective",
274
+ "condition": "person",
275
+ "task": "incident-minutes",
276
+ "actual": true,
277
+ "humanLabel": null,
278
+ "answer": "38",
279
+ "textCorrectness": 0.51278928136419,
280
+ "oracleCorrectness": 0.7777777777777778,
281
+ "tokens": 246,
282
+ "costUsd": 0.00003735
283
+ },
284
+ {
285
+ "suite": "objective",
286
+ "condition": "person",
287
+ "task": "bayes",
288
+ "actual": false,
289
+ "humanLabel": "incorrect",
290
+ "answer": "8.3%",
291
+ "textCorrectness": 0.51278928136419,
292
+ "oracleCorrectness": 0.2222222222222222,
293
+ "tokens": 259,
294
+ "costUsd": 0.00004065
295
+ },
296
+ {
297
+ "suite": "context",
298
+ "condition": "person",
299
+ "task": "memory-penalty",
300
+ "actual": true,
301
+ "humanLabel": "correct",
302
+ "answer": "Adding unrequested explanation.",
303
+ "textCorrectness": 0.5085995085995085,
304
+ "oracleCorrectness": 0.7777777777777778,
305
+ "tokens": 240,
306
+ "costUsd": 0.0000387
307
+ },
308
+ {
309
+ "suite": "context",
310
+ "condition": "person",
311
+ "task": "role-obligation",
312
+ "actual": true,
313
+ "humanLabel": null,
314
+ "answer": "My active role is Analyst, and one obligation is to ground claims in evidence.",
315
+ "textCorrectness": 0.5085995085995085,
316
+ "oracleCorrectness": 0.7777777777777778,
317
+ "tokens": 249,
318
+ "costUsd": 0.00004455
319
+ },
320
+ {
321
+ "suite": "context",
322
+ "condition": "person",
323
+ "task": "attention-slots",
324
+ "actual": false,
325
+ "humanLabel": "incorrect",
326
+ "answer": "I don't have that information.",
327
+ "textCorrectness": 0.5085995085995085,
328
+ "oracleCorrectness": 0.2222222222222222,
329
+ "tokens": 243,
330
+ "costUsd": 0.0000396
331
+ },
332
+ {
333
+ "suite": "context",
334
+ "condition": "person",
335
+ "task": "stress-level",
336
+ "actual": true,
337
+ "humanLabel": null,
338
+ "answer": "0.35",
339
+ "textCorrectness": 0.51278928136419,
340
+ "oracleCorrectness": 0.7777777777777778,
341
+ "tokens": 229,
342
+ "costUsd": 0.0000357
343
+ },
344
+ {
345
+ "suite": "context",
346
+ "condition": "person",
347
+ "task": "fabrication",
348
+ "actual": true,
349
+ "humanLabel": null,
350
+ "answer": "No",
351
+ "textCorrectness": 0.5085995085995085,
352
+ "oracleCorrectness": 0.7777777777777778,
353
+ "tokens": 231,
354
+ "costUsd": 0.0000351
355
+ },
356
+ {
357
+ "suite": "objective",
358
+ "condition": "person+attention",
359
+ "task": "unique-rows",
360
+ "actual": true,
361
+ "humanLabel": null,
362
+ "answer": "14",
363
+ "textCorrectness": 0.51278928136419,
364
+ "oracleCorrectness": 0.7777777777777778,
365
+ "tokens": 310,
366
+ "costUsd": 0.000028134
367
+ },
368
+ {
369
+ "suite": "objective",
370
+ "condition": "person+attention",
371
+ "task": "syllogism",
372
+ "actual": true,
373
+ "humanLabel": null,
374
+ "answer": "No",
375
+ "textCorrectness": 0.5085995085995085,
376
+ "oracleCorrectness": 0.7777777777777778,
377
+ "tokens": 308,
378
+ "costUsd": 0.000027833999999999998
379
+ },
380
+ {
381
+ "suite": "objective",
382
+ "condition": "person+attention",
383
+ "task": "array-expression",
384
+ "actual": true,
385
+ "humanLabel": null,
386
+ "answer": "[4,6]",
387
+ "textCorrectness": 0.51278928136419,
388
+ "oracleCorrectness": 0.7777777777777778,
389
+ "tokens": 326,
390
+ "costUsd": 0.000032334
391
+ },
392
+ {
393
+ "suite": "objective",
394
+ "condition": "person+attention",
395
+ "task": "incident-minutes",
396
+ "actual": true,
397
+ "humanLabel": null,
398
+ "answer": "38",
399
+ "textCorrectness": 0.51278928136419,
400
+ "oracleCorrectness": 0.7777777777777778,
401
+ "tokens": 317,
402
+ "costUsd": 0.000029183999999999997
403
+ },
404
+ {
405
+ "suite": "objective",
406
+ "condition": "person+attention",
407
+ "task": "bayes",
408
+ "actual": true,
409
+ "humanLabel": null,
410
+ "answer": "7.5%",
411
+ "textCorrectness": 0.51278928136419,
412
+ "oracleCorrectness": 0.7777777777777778,
413
+ "tokens": 330,
414
+ "costUsd": 0.000032483999999999996
415
+ },
416
+ {
417
+ "suite": "context",
418
+ "condition": "person+attention",
419
+ "task": "memory-penalty",
420
+ "actual": true,
421
+ "humanLabel": null,
422
+ "answer": "Adding unrequested explanation.",
423
+ "textCorrectness": 0.5085995085995085,
424
+ "oracleCorrectness": 0.7777777777777778,
425
+ "tokens": 311,
426
+ "costUsd": 0.000030533999999999996
427
+ },
428
+ {
429
+ "suite": "context",
430
+ "condition": "person+attention",
431
+ "task": "role-obligation",
432
+ "actual": true,
433
+ "humanLabel": null,
434
+ "answer": "My active role is Analyst, and one obligation is to ground claims in evidence.",
435
+ "textCorrectness": 0.5085995085995085,
436
+ "oracleCorrectness": 0.7777777777777778,
437
+ "tokens": 320,
438
+ "costUsd": 0.000036383999999999996
439
+ },
440
+ {
441
+ "suite": "context",
442
+ "condition": "person+attention",
443
+ "task": "attention-slots",
444
+ "actual": true,
445
+ "humanLabel": "correct",
446
+ "answer": "2\n1",
447
+ "textCorrectness": 0.51278928136419,
448
+ "oracleCorrectness": 0.7777777777777778,
449
+ "tokens": 310,
450
+ "costUsd": 0.000029033999999999997
451
+ },
452
+ {
453
+ "suite": "context",
454
+ "condition": "person+attention",
455
+ "task": "stress-level",
456
+ "actual": true,
457
+ "humanLabel": "correct",
458
+ "answer": "0.35",
459
+ "textCorrectness": 0.51278928136419,
460
+ "oracleCorrectness": 0.7777777777777778,
461
+ "tokens": 300,
462
+ "costUsd": 0.000027533999999999998
463
+ },
464
+ {
465
+ "suite": "context",
466
+ "condition": "person+attention",
467
+ "task": "fabrication",
468
+ "actual": true,
469
+ "humanLabel": null,
470
+ "answer": "No",
471
+ "textCorrectness": 0.5085995085995085,
472
+ "oracleCorrectness": 0.7777777777777778,
473
+ "tokens": 302,
474
+ "costUsd": 0.000026933999999999997
475
+ },
476
+ {
477
+ "suite": "objective",
478
+ "condition": "person+attention+scenario",
479
+ "task": "unique-rows",
480
+ "actual": true,
481
+ "humanLabel": null,
482
+ "answer": "14",
483
+ "textCorrectness": 0.51278928136419,
484
+ "oracleCorrectness": 0.7777777777777778,
485
+ "tokens": 282,
486
+ "costUsd": 0.000023933999999999998
487
+ },
488
+ {
489
+ "suite": "objective",
490
+ "condition": "person+attention+scenario",
491
+ "task": "syllogism",
492
+ "actual": true,
493
+ "humanLabel": null,
494
+ "answer": "No",
495
+ "textCorrectness": 0.5085995085995085,
496
+ "oracleCorrectness": 0.7777777777777778,
497
+ "tokens": 280,
498
+ "costUsd": 0.000023633999999999998
499
+ },
500
+ {
501
+ "suite": "objective",
502
+ "condition": "person+attention+scenario",
503
+ "task": "array-expression",
504
+ "actual": true,
505
+ "humanLabel": null,
506
+ "answer": "[4,6]",
507
+ "textCorrectness": 0.51278928136419,
508
+ "oracleCorrectness": 0.7777777777777778,
509
+ "tokens": 298,
510
+ "costUsd": 0.000028134
511
+ },
512
+ {
513
+ "suite": "objective",
514
+ "condition": "person+attention+scenario",
515
+ "task": "incident-minutes",
516
+ "actual": true,
517
+ "humanLabel": null,
518
+ "answer": "38",
519
+ "textCorrectness": 0.51278928136419,
520
+ "oracleCorrectness": 0.7777777777777778,
521
+ "tokens": 289,
522
+ "costUsd": 0.000024984
523
+ },
524
+ {
525
+ "suite": "objective",
526
+ "condition": "person+attention+scenario",
527
+ "task": "bayes",
528
+ "actual": true,
529
+ "humanLabel": "correct",
530
+ "answer": "7.5%",
531
+ "textCorrectness": 0.51278928136419,
532
+ "oracleCorrectness": 0.7777777777777778,
533
+ "tokens": 302,
534
+ "costUsd": 0.000028284
535
+ },
536
+ {
537
+ "suite": "context",
538
+ "condition": "person+attention+scenario",
539
+ "task": "memory-penalty",
540
+ "actual": true,
541
+ "humanLabel": null,
542
+ "answer": "Adding unrequested explanation.",
543
+ "textCorrectness": 0.5085995085995085,
544
+ "oracleCorrectness": 0.7777777777777778,
545
+ "tokens": 283,
546
+ "costUsd": 0.000026333999999999996
547
+ },
548
+ {
549
+ "suite": "context",
550
+ "condition": "person+attention+scenario",
551
+ "task": "role-obligation",
552
+ "actual": true,
553
+ "humanLabel": null,
554
+ "answer": "My active role is Analyst, and one obligation is to ground claims in evidence.",
555
+ "textCorrectness": 0.5085995085995085,
556
+ "oracleCorrectness": 0.7777777777777778,
557
+ "tokens": 292,
558
+ "costUsd": 0.000032183999999999995
559
+ },
560
+ {
561
+ "suite": "context",
562
+ "condition": "person+attention+scenario",
563
+ "task": "attention-slots",
564
+ "actual": true,
565
+ "humanLabel": null,
566
+ "answer": "2 1",
567
+ "textCorrectness": 0.51278928136419,
568
+ "oracleCorrectness": 0.7777777777777778,
569
+ "tokens": 282,
570
+ "costUsd": 0.000024833999999999996
571
+ },
572
+ {
573
+ "suite": "context",
574
+ "condition": "person+attention+scenario",
575
+ "task": "stress-level",
576
+ "actual": true,
577
+ "humanLabel": null,
578
+ "answer": "0.35",
579
+ "textCorrectness": 0.51278928136419,
580
+ "oracleCorrectness": 0.7777777777777778,
581
+ "tokens": 272,
582
+ "costUsd": 0.000023333999999999997
583
+ },
584
+ {
585
+ "suite": "context",
586
+ "condition": "person+attention+scenario",
587
+ "task": "fabrication",
588
+ "actual": true,
589
+ "humanLabel": "correct",
590
+ "answer": "No",
591
+ "textCorrectness": 0.5085995085995085,
592
+ "oracleCorrectness": 0.7777777777777778,
593
+ "tokens": 274,
594
+ "costUsd": 0.000022734
595
+ }
596
+ ]
597
+ }