self-bench 0.3.6 → 0.3.8

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 (1126) hide show
  1. package/.dockerignore +11 -1
  2. package/Dockerfile +9 -9
  3. package/Dockerfile.sandbox +5 -4
  4. package/README.md +27 -12
  5. package/bun.lock +462 -95
  6. package/compose.yaml +64 -20
  7. package/dist/agent-feed.d.ts +8 -0
  8. package/dist/agent-feed.d.ts.map +1 -0
  9. package/dist/agent-feed.js +56 -0
  10. package/dist/agent-feed.js.map +1 -0
  11. package/dist/api/http.d.ts +18 -0
  12. package/dist/api/http.d.ts.map +1 -0
  13. package/dist/api/http.js +111 -0
  14. package/dist/api/http.js.map +1 -0
  15. package/dist/api/run-request.d.ts +37 -0
  16. package/dist/api/run-request.d.ts.map +1 -0
  17. package/dist/api/run-request.js +59 -0
  18. package/dist/api/run-request.js.map +1 -0
  19. package/dist/api/status.d.ts +4 -0
  20. package/dist/api/status.d.ts.map +1 -0
  21. package/dist/api/status.js +36 -0
  22. package/dist/api/status.js.map +1 -0
  23. package/dist/api/viewer-routes.d.ts +9 -0
  24. package/dist/api/viewer-routes.d.ts.map +1 -0
  25. package/dist/api/viewer-routes.js +98 -0
  26. package/dist/api/viewer-routes.js.map +1 -0
  27. package/dist/api-main.js +5 -1
  28. package/dist/api-main.js.map +1 -1
  29. package/dist/api.d.ts +7 -25
  30. package/dist/api.d.ts.map +1 -1
  31. package/dist/api.js +80 -148
  32. package/dist/api.js.map +1 -1
  33. package/dist/archive.d.ts +14 -0
  34. package/dist/archive.d.ts.map +1 -0
  35. package/dist/archive.js +114 -0
  36. package/dist/archive.js.map +1 -0
  37. package/dist/artifacts/common.d.ts +15 -0
  38. package/dist/artifacts/common.d.ts.map +1 -0
  39. package/dist/artifacts/common.js +58 -0
  40. package/dist/artifacts/common.js.map +1 -0
  41. package/dist/artifacts/gcs.d.ts +18 -0
  42. package/dist/artifacts/gcs.d.ts.map +1 -0
  43. package/dist/artifacts/gcs.js +178 -0
  44. package/dist/artifacts/gcs.js.map +1 -0
  45. package/dist/artifacts/local.d.ts +17 -0
  46. package/dist/artifacts/local.d.ts.map +1 -0
  47. package/dist/artifacts/local.js +205 -0
  48. package/dist/artifacts/local.js.map +1 -0
  49. package/dist/artifacts/types.d.ts +18 -0
  50. package/dist/artifacts/types.d.ts.map +1 -0
  51. package/dist/artifacts/types.js +2 -0
  52. package/dist/artifacts/types.js.map +1 -0
  53. package/dist/artifacts.d.ts +5 -28
  54. package/dist/artifacts.d.ts.map +1 -1
  55. package/dist/artifacts.js +5 -302
  56. package/dist/artifacts.js.map +1 -1
  57. package/dist/audit.d.ts.map +1 -1
  58. package/dist/audit.js +8 -2
  59. package/dist/audit.js.map +1 -1
  60. package/dist/auth/api-key-routes.d.ts +17 -0
  61. package/dist/auth/api-key-routes.d.ts.map +1 -0
  62. package/dist/auth/api-key-routes.js +57 -0
  63. package/dist/auth/api-key-routes.js.map +1 -0
  64. package/dist/auth/api-keys.d.ts +47 -0
  65. package/dist/auth/api-keys.d.ts.map +1 -0
  66. package/dist/auth/api-keys.js +102 -0
  67. package/dist/auth/api-keys.js.map +1 -0
  68. package/dist/auth/config.d.ts +17 -0
  69. package/dist/auth/config.d.ts.map +1 -0
  70. package/dist/auth/config.js +38 -0
  71. package/dist/auth/config.js.map +1 -0
  72. package/dist/auth/cookies.d.ts +12 -0
  73. package/dist/auth/cookies.d.ts.map +1 -0
  74. package/dist/auth/cookies.js +45 -0
  75. package/dist/auth/cookies.js.map +1 -0
  76. package/dist/auth/crypto.d.ts +19 -0
  77. package/dist/auth/crypto.d.ts.map +1 -0
  78. package/dist/auth/crypto.js +48 -0
  79. package/dist/auth/crypto.js.map +1 -0
  80. package/dist/auth/github.d.ts +37 -0
  81. package/dist/auth/github.d.ts.map +1 -0
  82. package/dist/auth/github.js +127 -0
  83. package/dist/auth/github.js.map +1 -0
  84. package/dist/auth/routes.d.ts +41 -0
  85. package/dist/auth/routes.d.ts.map +1 -0
  86. package/dist/auth/routes.js +153 -0
  87. package/dist/auth/routes.js.map +1 -0
  88. package/dist/auth/session-expired.d.ts +4 -0
  89. package/dist/auth/session-expired.d.ts.map +1 -0
  90. package/dist/auth/session-expired.js +17 -0
  91. package/dist/auth/session-expired.js.map +1 -0
  92. package/dist/auth/session.d.ts +23 -0
  93. package/dist/auth/session.d.ts.map +1 -0
  94. package/dist/auth/session.js +56 -0
  95. package/dist/auth/session.js.map +1 -0
  96. package/dist/auth/users.d.ts +49 -0
  97. package/dist/auth/users.d.ts.map +1 -0
  98. package/dist/auth/users.js +125 -0
  99. package/dist/auth/users.js.map +1 -0
  100. package/dist/build-metadata.js +1 -1
  101. package/dist/cli/api-client.d.ts +8 -0
  102. package/dist/cli/api-client.d.ts.map +1 -0
  103. package/dist/cli/api-client.js +71 -0
  104. package/dist/cli/api-client.js.map +1 -0
  105. package/dist/cli/associate.d.ts +2 -0
  106. package/dist/cli/associate.d.ts.map +1 -0
  107. package/dist/cli/associate.js +51 -0
  108. package/dist/cli/associate.js.map +1 -0
  109. package/dist/cli/help.d.ts +2 -0
  110. package/dist/cli/help.d.ts.map +1 -0
  111. package/dist/cli/help.js +52 -0
  112. package/dist/cli/help.js.map +1 -0
  113. package/dist/cli/main.d.ts +2 -0
  114. package/dist/cli/main.d.ts.map +1 -0
  115. package/dist/cli/main.js +55 -0
  116. package/dist/cli/main.js.map +1 -0
  117. package/dist/cli/replay.d.ts +3 -0
  118. package/dist/cli/replay.d.ts.map +1 -0
  119. package/dist/cli/replay.js +59 -0
  120. package/dist/cli/replay.js.map +1 -0
  121. package/dist/cli/repository.d.ts +6 -0
  122. package/dist/cli/repository.d.ts.map +1 -0
  123. package/dist/cli/repository.js +36 -0
  124. package/dist/cli/repository.js.map +1 -0
  125. package/dist/cli/run.d.ts +2 -0
  126. package/dist/cli/run.d.ts.map +1 -0
  127. package/dist/cli/run.js +93 -0
  128. package/dist/cli/run.js.map +1 -0
  129. package/dist/cli/stack-environment.d.ts +26 -0
  130. package/dist/cli/stack-environment.d.ts.map +1 -0
  131. package/dist/cli/stack-environment.js +86 -0
  132. package/dist/cli/stack-environment.js.map +1 -0
  133. package/dist/cli/stack.d.ts +6 -0
  134. package/dist/cli/stack.d.ts.map +1 -0
  135. package/dist/cli/stack.js +131 -0
  136. package/dist/cli/stack.js.map +1 -0
  137. package/dist/cli/values.d.ts +8 -0
  138. package/dist/cli/values.d.ts.map +1 -0
  139. package/dist/cli/values.js +30 -0
  140. package/dist/cli/values.js.map +1 -0
  141. package/dist/cli/view.d.ts +2 -0
  142. package/dist/cli/view.d.ts.map +1 -0
  143. package/dist/cli/view.js +40 -0
  144. package/dist/cli/view.js.map +1 -0
  145. package/dist/cli.js +2 -429
  146. package/dist/cli.js.map +1 -1
  147. package/dist/config.d.ts +16 -2
  148. package/dist/config.d.ts.map +1 -1
  149. package/dist/config.js +60 -22
  150. package/dist/config.js.map +1 -1
  151. package/dist/contracts/common.d.ts +22 -0
  152. package/dist/contracts/common.d.ts.map +1 -0
  153. package/dist/contracts/common.js +29 -0
  154. package/dist/contracts/common.js.map +1 -0
  155. package/dist/contracts/results.d.ts +66 -0
  156. package/dist/contracts/results.d.ts.map +1 -0
  157. package/dist/contracts/results.js +2 -0
  158. package/dist/contracts/results.js.map +1 -0
  159. package/dist/contracts/run.d.ts +145 -0
  160. package/dist/contracts/run.d.ts.map +1 -0
  161. package/dist/contracts/run.js +74 -0
  162. package/dist/contracts/run.js.map +1 -0
  163. package/dist/contracts/task.d.ts +232 -0
  164. package/dist/contracts/task.d.ts.map +1 -0
  165. package/dist/contracts/task.js +198 -0
  166. package/dist/contracts/task.js.map +1 -0
  167. package/dist/contracts/verify.d.ts +331 -0
  168. package/dist/contracts/verify.d.ts.map +1 -0
  169. package/dist/contracts/verify.js +84 -0
  170. package/dist/contracts/verify.js.map +1 -0
  171. package/dist/contracts.d.ts +5 -243
  172. package/dist/contracts.d.ts.map +1 -1
  173. package/dist/contracts.js +5 -128
  174. package/dist/contracts.js.map +1 -1
  175. package/dist/db/client.d.ts +12 -0
  176. package/dist/db/client.d.ts.map +1 -0
  177. package/dist/db/client.js +16 -0
  178. package/dist/db/client.js.map +1 -0
  179. package/dist/db/schema.d.ts +1256 -0
  180. package/dist/db/schema.d.ts.map +1 -0
  181. package/dist/db/schema.js +128 -0
  182. package/dist/db/schema.js.map +1 -0
  183. package/dist/environment.d.ts +9 -0
  184. package/dist/environment.d.ts.map +1 -0
  185. package/dist/environment.js +101 -0
  186. package/dist/environment.js.map +1 -0
  187. package/dist/evaluation/account.d.ts +30 -0
  188. package/dist/evaluation/account.d.ts.map +1 -0
  189. package/dist/evaluation/account.js +34 -0
  190. package/dist/evaluation/account.js.map +1 -0
  191. package/dist/evaluation/activities.d.ts +9 -0
  192. package/dist/evaluation/activities.d.ts.map +1 -0
  193. package/dist/evaluation/activities.js +40 -0
  194. package/dist/evaluation/activities.js.map +1 -0
  195. package/dist/evaluation/catalog-pricing.d.ts +3 -0
  196. package/dist/evaluation/catalog-pricing.d.ts.map +1 -0
  197. package/dist/evaluation/catalog-pricing.js +37 -0
  198. package/dist/evaluation/catalog-pricing.js.map +1 -0
  199. package/dist/evaluation/catalog.d.ts +17 -0
  200. package/dist/evaluation/catalog.d.ts.map +1 -0
  201. package/dist/evaluation/catalog.js +126 -0
  202. package/dist/evaluation/catalog.js.map +1 -0
  203. package/dist/evaluation/codex-login-process.d.ts +12 -0
  204. package/dist/evaluation/codex-login-process.d.ts.map +1 -0
  205. package/dist/evaluation/codex-login-process.js +121 -0
  206. package/dist/evaluation/codex-login-process.js.map +1 -0
  207. package/dist/evaluation/codex-login-routes.d.ts +5 -0
  208. package/dist/evaluation/codex-login-routes.d.ts.map +1 -0
  209. package/dist/evaluation/codex-login-routes.js +55 -0
  210. package/dist/evaluation/codex-login-routes.js.map +1 -0
  211. package/dist/evaluation/codex-login.d.ts +42 -0
  212. package/dist/evaluation/codex-login.d.ts.map +1 -0
  213. package/dist/evaluation/codex-login.js +143 -0
  214. package/dist/evaluation/codex-login.js.map +1 -0
  215. package/dist/evaluation/comparisons.d.ts +65 -0
  216. package/dist/evaluation/comparisons.d.ts.map +1 -0
  217. package/dist/evaluation/comparisons.js +161 -0
  218. package/dist/evaluation/comparisons.js.map +1 -0
  219. package/dist/evaluation/config.d.ts +43 -0
  220. package/dist/evaluation/config.d.ts.map +1 -0
  221. package/dist/evaluation/config.js +116 -0
  222. package/dist/evaluation/config.js.map +1 -0
  223. package/dist/evaluation/cost.d.ts +3 -0
  224. package/dist/evaluation/cost.d.ts.map +1 -0
  225. package/dist/evaluation/cost.js +95 -0
  226. package/dist/evaluation/cost.js.map +1 -0
  227. package/dist/evaluation/credential-execution.d.ts +10 -0
  228. package/dist/evaluation/credential-execution.d.ts.map +1 -0
  229. package/dist/evaluation/credential-execution.js +65 -0
  230. package/dist/evaluation/credential-execution.js.map +1 -0
  231. package/dist/evaluation/credentials.d.ts +40 -0
  232. package/dist/evaluation/credentials.d.ts.map +1 -0
  233. package/dist/evaluation/credentials.js +146 -0
  234. package/dist/evaluation/credentials.js.map +1 -0
  235. package/dist/evaluation/encrypted-records.d.ts +15 -0
  236. package/dist/evaluation/encrypted-records.d.ts.map +1 -0
  237. package/dist/evaluation/encrypted-records.js +57 -0
  238. package/dist/evaluation/encrypted-records.js.map +1 -0
  239. package/dist/evaluation/gateway-execution.d.ts +18 -0
  240. package/dist/evaluation/gateway-execution.d.ts.map +1 -0
  241. package/dist/evaluation/gateway-execution.js +38 -0
  242. package/dist/evaluation/gateway-execution.js.map +1 -0
  243. package/dist/evaluation/harbor-cost.d.ts +3 -0
  244. package/dist/evaluation/harbor-cost.d.ts.map +1 -0
  245. package/dist/evaluation/harbor-cost.js +39 -0
  246. package/dist/evaluation/harbor-cost.js.map +1 -0
  247. package/dist/evaluation/harbor_e2b.py +20 -0
  248. package/dist/evaluation/harbor_gateway.py +22 -0
  249. package/dist/evaluation/harnesses.d.ts +8 -0
  250. package/dist/evaluation/harnesses.d.ts.map +1 -0
  251. package/dist/evaluation/harnesses.js +10 -0
  252. package/dist/evaluation/harnesses.js.map +1 -0
  253. package/dist/evaluation/model-options.d.ts +9 -0
  254. package/dist/evaluation/model-options.d.ts.map +1 -0
  255. package/dist/evaluation/model-options.js +81 -0
  256. package/dist/evaluation/model-options.js.map +1 -0
  257. package/dist/evaluation/org-credential-routes.d.ts +5 -0
  258. package/dist/evaluation/org-credential-routes.d.ts.map +1 -0
  259. package/dist/evaluation/org-credential-routes.js +56 -0
  260. package/dist/evaluation/org-credential-routes.js.map +1 -0
  261. package/dist/evaluation/org-records.d.ts +4 -0
  262. package/dist/evaluation/org-records.d.ts.map +1 -0
  263. package/dist/evaluation/org-records.js +14 -0
  264. package/dist/evaluation/org-records.js.map +1 -0
  265. package/dist/evaluation/output.d.ts +9 -0
  266. package/dist/evaluation/output.d.ts.map +1 -0
  267. package/dist/evaluation/output.js +171 -0
  268. package/dist/evaluation/output.js.map +1 -0
  269. package/dist/evaluation/platform-routes.d.ts +5 -0
  270. package/dist/evaluation/platform-routes.d.ts.map +1 -0
  271. package/dist/evaluation/platform-routes.js +123 -0
  272. package/dist/evaluation/platform-routes.js.map +1 -0
  273. package/dist/evaluation/profile-routes.d.ts +16 -0
  274. package/dist/evaluation/profile-routes.d.ts.map +1 -0
  275. package/dist/evaluation/profile-routes.js +47 -0
  276. package/dist/evaluation/profile-routes.js.map +1 -0
  277. package/dist/evaluation/profiles.d.ts +48 -0
  278. package/dist/evaluation/profiles.d.ts.map +1 -0
  279. package/dist/evaluation/profiles.js +134 -0
  280. package/dist/evaluation/profiles.js.map +1 -0
  281. package/dist/evaluation/providers.d.ts +11 -0
  282. package/dist/evaluation/providers.d.ts.map +1 -0
  283. package/dist/evaluation/providers.js +30 -0
  284. package/dist/evaluation/providers.js.map +1 -0
  285. package/dist/evaluation/routes.d.ts +23 -0
  286. package/dist/evaluation/routes.d.ts.map +1 -0
  287. package/dist/evaluation/routes.js +212 -0
  288. package/dist/evaluation/routes.js.map +1 -0
  289. package/dist/evaluation/runner.d.ts +16 -0
  290. package/dist/evaluation/runner.d.ts.map +1 -0
  291. package/dist/evaluation/runner.js +241 -0
  292. package/dist/evaluation/runner.js.map +1 -0
  293. package/dist/evaluation/store.d.ts +8 -0
  294. package/dist/evaluation/store.d.ts.map +1 -0
  295. package/dist/evaluation/store.js +60 -0
  296. package/dist/evaluation/store.js.map +1 -0
  297. package/dist/evaluation/types.d.ts +98 -0
  298. package/dist/evaluation/types.d.ts.map +1 -0
  299. package/dist/evaluation/types.js +2 -0
  300. package/dist/evaluation/types.js.map +1 -0
  301. package/dist/evaluation/worker-main.d.ts +2 -0
  302. package/dist/evaluation/worker-main.d.ts.map +1 -0
  303. package/dist/evaluation/worker-main.js +26 -0
  304. package/dist/evaluation/worker-main.js.map +1 -0
  305. package/dist/evaluation/worker-records.d.ts +5 -0
  306. package/dist/evaluation/worker-records.d.ts.map +1 -0
  307. package/dist/evaluation/worker-records.js +11 -0
  308. package/dist/evaluation/worker-records.js.map +1 -0
  309. package/dist/evaluation/workflow.d.ts +3 -0
  310. package/dist/evaluation/workflow.d.ts.map +1 -0
  311. package/dist/evaluation/workflow.js +20 -0
  312. package/dist/evaluation/workflow.js.map +1 -0
  313. package/dist/execution-environment.d.ts +3 -0
  314. package/dist/execution-environment.d.ts.map +1 -0
  315. package/dist/execution-environment.js +9 -0
  316. package/dist/execution-environment.js.map +1 -0
  317. package/dist/extension-authoring.bundle.js +347 -0
  318. package/dist/extension-verifier.bundle.js +73 -0
  319. package/dist/extensions/authoring.d.ts.map +1 -1
  320. package/dist/extensions/authoring.js +70 -59
  321. package/dist/extensions/authoring.js.map +1 -1
  322. package/dist/extensions/shared/deliverable.d.ts +33 -0
  323. package/dist/extensions/shared/deliverable.d.ts.map +1 -0
  324. package/dist/extensions/shared/deliverable.js +123 -0
  325. package/dist/extensions/shared/deliverable.js.map +1 -0
  326. package/dist/extensions/shared/mailbox.d.ts +33 -0
  327. package/dist/extensions/shared/mailbox.d.ts.map +1 -0
  328. package/dist/extensions/shared/mailbox.js +102 -0
  329. package/dist/extensions/shared/mailbox.js.map +1 -0
  330. package/dist/extensions/shared/schemas.d.ts +90 -0
  331. package/dist/extensions/shared/schemas.d.ts.map +1 -0
  332. package/dist/extensions/shared/schemas.js +71 -0
  333. package/dist/extensions/shared/schemas.js.map +1 -0
  334. package/dist/extensions/shared/static-check.d.ts +38 -0
  335. package/dist/extensions/shared/static-check.d.ts.map +1 -0
  336. package/dist/extensions/shared/static-check.js +52 -0
  337. package/dist/extensions/shared/static-check.js.map +1 -0
  338. package/dist/extensions/verifier.d.ts +4 -0
  339. package/dist/extensions/verifier.d.ts.map +1 -0
  340. package/dist/extensions/verifier.js +70 -0
  341. package/dist/extensions/verifier.js.map +1 -0
  342. package/dist/github.d.ts +1 -1
  343. package/dist/github.d.ts.map +1 -1
  344. package/dist/github.js +3 -3
  345. package/dist/github.js.map +1 -1
  346. package/dist/harbor-environment.d.ts +13 -1
  347. package/dist/harbor-environment.d.ts.map +1 -1
  348. package/dist/harbor-environment.js +37 -4
  349. package/dist/harbor-environment.js.map +1 -1
  350. package/dist/harbor-results.d.ts +2 -0
  351. package/dist/harbor-results.d.ts.map +1 -1
  352. package/dist/harbor-results.js +2 -0
  353. package/dist/harbor-results.js.map +1 -1
  354. package/dist/harbor-task/compiler.d.ts +10 -0
  355. package/dist/harbor-task/compiler.d.ts.map +1 -0
  356. package/dist/harbor-task/compiler.js +174 -0
  357. package/dist/harbor-task/compiler.js.map +1 -0
  358. package/dist/harbor-task/constants.d.ts +3 -0
  359. package/dist/harbor-task/constants.d.ts.map +1 -0
  360. package/dist/harbor-task/constants.js +3 -0
  361. package/dist/harbor-task/constants.js.map +1 -0
  362. package/dist/harbor-task/dependencies.d.ts +3 -0
  363. package/dist/harbor-task/dependencies.d.ts.map +1 -0
  364. package/dist/harbor-task/dependencies.js +20 -0
  365. package/dist/harbor-task/dependencies.js.map +1 -0
  366. package/dist/harbor-task/paths.d.ts +6 -0
  367. package/dist/harbor-task/paths.d.ts.map +1 -0
  368. package/dist/harbor-task/paths.js +37 -0
  369. package/dist/harbor-task/paths.js.map +1 -0
  370. package/dist/harbor-task/render.d.ts +11 -0
  371. package/dist/harbor-task/render.d.ts.map +1 -0
  372. package/dist/harbor-task/render.js +194 -0
  373. package/dist/harbor-task/render.js.map +1 -0
  374. package/dist/harbor-task/runtime/command.sh +26 -0
  375. package/dist/harbor-task/runtime/junit.py +69 -0
  376. package/dist/harbor-task/runtime-assets.d.ts +2 -0
  377. package/dist/harbor-task/runtime-assets.d.ts.map +1 -0
  378. package/dist/harbor-task/runtime-assets.js +8 -0
  379. package/dist/harbor-task/runtime-assets.js.map +1 -0
  380. package/dist/harbor-task/test-patch.d.ts +4 -0
  381. package/dist/harbor-task/test-patch.d.ts.map +1 -0
  382. package/dist/harbor-task/test-patch.js +15 -0
  383. package/dist/harbor-task/test-patch.js.map +1 -0
  384. package/dist/harbor-task/verifier.d.ts +4 -0
  385. package/dist/harbor-task/verifier.d.ts.map +1 -0
  386. package/dist/harbor-task/verifier.js +105 -0
  387. package/dist/harbor-task/verifier.js.map +1 -0
  388. package/dist/harbor-task.d.ts +3 -11
  389. package/dist/harbor-task.d.ts.map +1 -1
  390. package/dist/harbor-task.js +2 -463
  391. package/dist/harbor-task.js.map +1 -1
  392. package/dist/log-excerpt.d.ts +15 -0
  393. package/dist/log-excerpt.d.ts.map +1 -0
  394. package/dist/log-excerpt.js +104 -0
  395. package/dist/log-excerpt.js.map +1 -0
  396. package/dist/patch-check.d.ts +26 -0
  397. package/dist/patch-check.d.ts.map +1 -0
  398. package/dist/patch-check.js +137 -0
  399. package/dist/patch-check.js.map +1 -0
  400. package/dist/pi-event-feed.d.ts +16 -0
  401. package/dist/pi-event-feed.d.ts.map +1 -0
  402. package/dist/pi-event-feed.js +86 -0
  403. package/dist/pi-event-feed.js.map +1 -0
  404. package/dist/pi-session.d.ts +32 -0
  405. package/dist/pi-session.d.ts.map +1 -0
  406. package/dist/pi-session.js +175 -0
  407. package/dist/pi-session.js.map +1 -0
  408. package/dist/process.d.ts +5 -0
  409. package/dist/process.d.ts.map +1 -1
  410. package/dist/process.js +31 -9
  411. package/dist/process.js.map +1 -1
  412. package/dist/provenance/github.d.ts +4 -0
  413. package/dist/provenance/github.d.ts.map +1 -0
  414. package/dist/provenance/github.js +65 -0
  415. package/dist/provenance/github.js.map +1 -0
  416. package/dist/provenance/local.d.ts +4 -0
  417. package/dist/provenance/local.d.ts.map +1 -0
  418. package/dist/provenance/local.js +82 -0
  419. package/dist/provenance/local.js.map +1 -0
  420. package/dist/provenance/redact.d.ts +2 -0
  421. package/dist/provenance/redact.d.ts.map +1 -0
  422. package/dist/provenance/redact.js +28 -0
  423. package/dist/provenance/redact.js.map +1 -0
  424. package/dist/provenance/selection.d.ts +4 -0
  425. package/dist/provenance/selection.d.ts.map +1 -0
  426. package/dist/provenance/selection.js +29 -0
  427. package/dist/provenance/selection.js.map +1 -0
  428. package/dist/provenance/session.d.ts +3 -0
  429. package/dist/provenance/session.d.ts.map +1 -0
  430. package/dist/provenance/session.js +214 -0
  431. package/dist/provenance/session.js.map +1 -0
  432. package/dist/provenance/shared.d.ts +7 -0
  433. package/dist/provenance/shared.d.ts.map +1 -0
  434. package/dist/provenance/shared.js +10 -0
  435. package/dist/provenance/shared.js.map +1 -0
  436. package/dist/provenance/types.d.ts +34 -0
  437. package/dist/provenance/types.d.ts.map +1 -0
  438. package/dist/provenance/types.js +22 -0
  439. package/dist/provenance/types.js.map +1 -0
  440. package/dist/provenance-associations/apply.d.ts +3 -0
  441. package/dist/provenance-associations/apply.d.ts.map +1 -0
  442. package/dist/provenance-associations/apply.js +66 -0
  443. package/dist/provenance-associations/apply.js.map +1 -0
  444. package/dist/provenance-associations/shared.d.ts +45 -0
  445. package/dist/provenance-associations/shared.d.ts.map +1 -0
  446. package/dist/provenance-associations/shared.js +42 -0
  447. package/dist/provenance-associations/shared.js.map +1 -0
  448. package/dist/provenance-associations.d.ts +3 -30
  449. package/dist/provenance-associations.d.ts.map +1 -1
  450. package/dist/provenance-associations.js +4 -103
  451. package/dist/provenance-associations.js.map +1 -1
  452. package/dist/provenance.d.ts +7 -41
  453. package/dist/provenance.d.ts.map +1 -1
  454. package/dist/provenance.js +6 -432
  455. package/dist/provenance.js.map +1 -1
  456. package/dist/providers.d.ts +25 -2
  457. package/dist/providers.d.ts.map +1 -1
  458. package/dist/providers.js +23 -2
  459. package/dist/providers.js.map +1 -1
  460. package/dist/repair.d.ts +1 -6
  461. package/dist/repair.d.ts.map +1 -1
  462. package/dist/repair.js +17 -27
  463. package/dist/repair.js.map +1 -1
  464. package/dist/review/assets/index-BHHztQ9x.js +1679 -0
  465. package/dist/review/assets/index-KQ1eFQ0t.css +1 -0
  466. package/dist/review/index.html +11 -8
  467. package/dist/runtime/command.sh +26 -0
  468. package/dist/runtime/junit.py +69 -0
  469. package/dist/sandbox/contracts.d.ts +36 -1
  470. package/dist/sandbox/contracts.d.ts.map +1 -1
  471. package/dist/sandbox/contracts.js +3 -0
  472. package/dist/sandbox/contracts.js.map +1 -1
  473. package/dist/sandbox/index.d.ts +1 -1
  474. package/dist/sandbox/index.d.ts.map +1 -1
  475. package/dist/sandbox/index.js +13 -2
  476. package/dist/sandbox/index.js.map +1 -1
  477. package/dist/sandbox/live.d.ts +18 -0
  478. package/dist/sandbox/live.d.ts.map +1 -0
  479. package/dist/sandbox/live.js +55 -0
  480. package/dist/sandbox/live.js.map +1 -0
  481. package/dist/sandbox/output-retry.d.ts +16 -0
  482. package/dist/sandbox/output-retry.d.ts.map +1 -0
  483. package/dist/sandbox/output-retry.js +36 -0
  484. package/dist/sandbox/output-retry.js.map +1 -0
  485. package/dist/sandbox/programs/author.js +16 -6
  486. package/dist/sandbox/programs/author.js.map +1 -1
  487. package/dist/sandbox/programs/check.d.ts +3 -0
  488. package/dist/sandbox/programs/check.d.ts.map +1 -0
  489. package/dist/sandbox/programs/check.js +76 -0
  490. package/dist/sandbox/programs/check.js.map +1 -0
  491. package/dist/sandbox/programs/prepare-task.d.ts +12 -0
  492. package/dist/sandbox/programs/prepare-task.d.ts.map +1 -0
  493. package/dist/sandbox/programs/{prepare-repair.js → prepare-task.js} +11 -9
  494. package/dist/sandbox/programs/prepare-task.js.map +1 -0
  495. package/dist/sandbox/programs/verifier.d.ts +3 -0
  496. package/dist/sandbox/programs/verifier.d.ts.map +1 -0
  497. package/dist/sandbox/programs/verifier.js +9 -0
  498. package/dist/sandbox/programs/verifier.js.map +1 -0
  499. package/dist/sandbox/providers/docker/executor.d.ts +4 -1
  500. package/dist/sandbox/providers/docker/executor.d.ts.map +1 -1
  501. package/dist/sandbox/providers/docker/executor.js +75 -25
  502. package/dist/sandbox/providers/docker/executor.js.map +1 -1
  503. package/dist/sandbox/providers/e2b/bytes.d.ts +3 -0
  504. package/dist/sandbox/providers/e2b/bytes.d.ts.map +1 -0
  505. package/dist/sandbox/providers/e2b/bytes.js +8 -0
  506. package/dist/sandbox/providers/e2b/bytes.js.map +1 -0
  507. package/dist/sandbox/providers/e2b/cleanup.d.ts +8 -0
  508. package/dist/sandbox/providers/e2b/cleanup.d.ts.map +1 -0
  509. package/dist/sandbox/providers/e2b/cleanup.js +124 -0
  510. package/dist/sandbox/providers/e2b/cleanup.js.map +1 -0
  511. package/dist/sandbox/providers/e2b/command.d.ts +23 -0
  512. package/dist/sandbox/providers/e2b/command.d.ts.map +1 -0
  513. package/dist/sandbox/providers/e2b/command.js +160 -0
  514. package/dist/sandbox/providers/e2b/command.js.map +1 -0
  515. package/dist/sandbox/providers/e2b/config.d.ts +13 -0
  516. package/dist/sandbox/providers/e2b/config.d.ts.map +1 -0
  517. package/dist/sandbox/providers/e2b/config.js +2 -0
  518. package/dist/sandbox/providers/e2b/config.js.map +1 -0
  519. package/dist/sandbox/providers/e2b/executor.d.ts +15 -0
  520. package/dist/sandbox/providers/e2b/executor.d.ts.map +1 -0
  521. package/dist/sandbox/providers/e2b/executor.js +207 -0
  522. package/dist/sandbox/providers/e2b/executor.js.map +1 -0
  523. package/dist/sandbox/providers/e2b/lifecycle.d.ts +8 -0
  524. package/dist/sandbox/providers/e2b/lifecycle.d.ts.map +1 -0
  525. package/dist/sandbox/providers/e2b/lifecycle.js +37 -0
  526. package/dist/sandbox/providers/e2b/lifecycle.js.map +1 -0
  527. package/dist/sandbox/providers/e2b/outcome.d.ts +11 -0
  528. package/dist/sandbox/providers/e2b/outcome.d.ts.map +1 -0
  529. package/dist/sandbox/providers/e2b/outcome.js +72 -0
  530. package/dist/sandbox/providers/e2b/outcome.js.map +1 -0
  531. package/dist/sandbox/providers/e2b/stage-files.d.ts +10 -0
  532. package/dist/sandbox/providers/e2b/stage-files.d.ts.map +1 -0
  533. package/dist/sandbox/providers/e2b/stage-files.js +45 -0
  534. package/dist/sandbox/providers/e2b/stage-files.js.map +1 -0
  535. package/dist/sandbox/providers/e2b/startup.d.ts +10 -0
  536. package/dist/sandbox/providers/e2b/startup.d.ts.map +1 -0
  537. package/dist/sandbox/providers/e2b/startup.js +26 -0
  538. package/dist/sandbox/providers/e2b/startup.js.map +1 -0
  539. package/dist/sandbox/providers/e2b/types.d.ts +9 -0
  540. package/dist/sandbox/providers/e2b/types.d.ts.map +1 -0
  541. package/dist/sandbox/providers/e2b/types.js +2 -0
  542. package/dist/sandbox/providers/e2b/types.js.map +1 -0
  543. package/dist/sandbox/providers/e2b/validation.d.ts +14 -0
  544. package/dist/sandbox/providers/e2b/validation.d.ts.map +1 -0
  545. package/dist/sandbox/providers/e2b/validation.js +60 -0
  546. package/dist/sandbox/providers/e2b/validation.js.map +1 -0
  547. package/dist/{modal-auth.d.ts → sandbox/providers/modal/auth.d.ts} +1 -1
  548. package/dist/sandbox/providers/modal/auth.d.ts.map +1 -0
  549. package/dist/{modal-auth.js → sandbox/providers/modal/auth.js} +1 -1
  550. package/dist/sandbox/providers/modal/auth.js.map +1 -0
  551. package/dist/sandbox/providers/modal/executor.d.ts +4 -1
  552. package/dist/sandbox/providers/modal/executor.d.ts.map +1 -1
  553. package/dist/sandbox/providers/modal/executor.js +33 -9
  554. package/dist/sandbox/providers/modal/executor.js.map +1 -1
  555. package/dist/sandbox/providers/modal/live.d.ts +7 -0
  556. package/dist/sandbox/providers/modal/live.d.ts.map +1 -0
  557. package/dist/sandbox/providers/modal/live.js +50 -0
  558. package/dist/sandbox/providers/modal/live.js.map +1 -0
  559. package/dist/sandbox/providers/vercel/command.d.ts +6 -0
  560. package/dist/sandbox/providers/vercel/command.d.ts.map +1 -1
  561. package/dist/sandbox/providers/vercel/command.js +44 -11
  562. package/dist/sandbox/providers/vercel/command.js.map +1 -1
  563. package/dist/sandbox/providers/vercel/executor.d.ts +6 -7
  564. package/dist/sandbox/providers/vercel/executor.d.ts.map +1 -1
  565. package/dist/sandbox/providers/vercel/executor.js +21 -187
  566. package/dist/sandbox/providers/vercel/executor.js.map +1 -1
  567. package/dist/sandbox/providers/vercel/lifecycle.d.ts +13 -0
  568. package/dist/sandbox/providers/vercel/lifecycle.d.ts.map +1 -0
  569. package/dist/sandbox/providers/vercel/lifecycle.js +140 -0
  570. package/dist/sandbox/providers/vercel/lifecycle.js.map +1 -0
  571. package/dist/sandbox/providers/vercel/validation.d.ts +11 -0
  572. package/dist/sandbox/providers/vercel/validation.d.ts.map +1 -0
  573. package/dist/sandbox/providers/vercel/validation.js +30 -0
  574. package/dist/sandbox/providers/vercel/validation.js.map +1 -0
  575. package/dist/sandbox/remote-files.d.ts +11 -0
  576. package/dist/sandbox/remote-files.d.ts.map +1 -0
  577. package/dist/sandbox/remote-files.js +41 -0
  578. package/dist/sandbox/remote-files.js.map +1 -0
  579. package/dist/sandbox/request-validation.d.ts +5 -0
  580. package/dist/sandbox/request-validation.d.ts.map +1 -0
  581. package/dist/sandbox/request-validation.js +43 -0
  582. package/dist/sandbox/request-validation.js.map +1 -0
  583. package/dist/sandbox/supervisor.d.ts +42 -0
  584. package/dist/sandbox/supervisor.d.ts.map +1 -0
  585. package/dist/sandbox/supervisor.js +126 -0
  586. package/dist/sandbox/supervisor.js.map +1 -0
  587. package/dist/sandbox/timeout.d.ts +6 -1
  588. package/dist/sandbox/timeout.d.ts.map +1 -1
  589. package/dist/sandbox/timeout.js +12 -0
  590. package/dist/sandbox/timeout.js.map +1 -1
  591. package/dist/sandbox-author.bundle.js +47 -14879
  592. package/dist/{sandbox-validation-repair.bundle.js → sandbox-check.bundle.js} +7261 -1893
  593. package/dist/sandbox-verifier.bundle.js +307 -0
  594. package/dist/setup/e2b/build.d.ts +24 -0
  595. package/dist/setup/e2b/build.d.ts.map +1 -0
  596. package/dist/setup/e2b/build.js +46 -0
  597. package/dist/setup/e2b/build.js.map +1 -0
  598. package/dist/setup/e2b/cli.d.ts +2 -0
  599. package/dist/setup/e2b/cli.d.ts.map +1 -0
  600. package/dist/setup/e2b/cli.js +51 -0
  601. package/dist/setup/e2b/cli.js.map +1 -0
  602. package/dist/setup/e2b/index.d.ts +5 -0
  603. package/dist/setup/e2b/index.d.ts.map +1 -0
  604. package/dist/setup/e2b/index.js +4 -0
  605. package/dist/setup/e2b/index.js.map +1 -0
  606. package/dist/setup/e2b/template.d.ts +4 -0
  607. package/dist/setup/e2b/template.d.ts.map +1 -0
  608. package/dist/setup/e2b/template.js +53 -0
  609. package/dist/setup/e2b/template.js.map +1 -0
  610. package/dist/setup/vercel/cli-helpers.d.ts +22 -0
  611. package/dist/setup/vercel/cli-helpers.d.ts.map +1 -0
  612. package/dist/setup/vercel/cli-helpers.js +87 -0
  613. package/dist/setup/vercel/cli-helpers.js.map +1 -0
  614. package/dist/setup/vercel/cli-runner.d.ts +14 -0
  615. package/dist/setup/vercel/cli-runner.d.ts.map +1 -0
  616. package/dist/setup/vercel/cli-runner.js +24 -0
  617. package/dist/setup/vercel/cli-runner.js.map +1 -0
  618. package/dist/setup/vercel/cli-types.d.ts +24 -0
  619. package/dist/setup/vercel/cli-types.d.ts.map +1 -0
  620. package/dist/setup/vercel/cli-types.js +18 -0
  621. package/dist/setup/vercel/cli-types.js.map +1 -0
  622. package/dist/setup/vercel/cli.d.ts +5 -31
  623. package/dist/setup/vercel/cli.d.ts.map +1 -1
  624. package/dist/setup/vercel/cli.js +15 -125
  625. package/dist/setup/vercel/cli.js.map +1 -1
  626. package/dist/setup/vercel/profile-files.d.ts +6 -0
  627. package/dist/setup/vercel/profile-files.d.ts.map +1 -0
  628. package/dist/setup/vercel/profile-files.js +100 -0
  629. package/dist/setup/vercel/profile-files.js.map +1 -0
  630. package/dist/setup/vercel/profile-schema.d.ts +48 -0
  631. package/dist/setup/vercel/profile-schema.d.ts.map +1 -0
  632. package/dist/setup/vercel/profile-schema.js +39 -0
  633. package/dist/setup/vercel/profile-schema.js.map +1 -0
  634. package/dist/setup/vercel/profile.d.ts +3 -19
  635. package/dist/setup/vercel/profile.d.ts.map +1 -1
  636. package/dist/setup/vercel/profile.js +4 -130
  637. package/dist/setup/vercel/profile.js.map +1 -1
  638. package/dist/setup/vercel/selection.d.ts +18 -0
  639. package/dist/setup/vercel/selection.d.ts.map +1 -0
  640. package/dist/setup/vercel/selection.js +113 -0
  641. package/dist/setup/vercel/selection.js.map +1 -0
  642. package/dist/setup/vercel/setup-types.d.ts +34 -0
  643. package/dist/setup/vercel/setup-types.d.ts.map +1 -0
  644. package/dist/setup/vercel/setup-types.js +2 -0
  645. package/dist/setup/vercel/setup-types.js.map +1 -0
  646. package/dist/setup/vercel/setup.d.ts +3 -28
  647. package/dist/setup/vercel/setup.d.ts.map +1 -1
  648. package/dist/setup/vercel/setup.js +3 -111
  649. package/dist/setup/vercel/setup.js.map +1 -1
  650. package/dist/site/batch-activity.d.ts +5 -0
  651. package/dist/site/batch-activity.d.ts.map +1 -0
  652. package/dist/site/batch-activity.js +31 -0
  653. package/dist/site/batch-activity.js.map +1 -0
  654. package/dist/site/batch-progress.d.ts +16 -0
  655. package/dist/site/batch-progress.d.ts.map +1 -0
  656. package/dist/site/batch-progress.js +52 -0
  657. package/dist/site/batch-progress.js.map +1 -0
  658. package/dist/site/batch-routes.d.ts +30 -0
  659. package/dist/site/batch-routes.d.ts.map +1 -0
  660. package/dist/site/batch-routes.js +117 -0
  661. package/dist/site/batch-routes.js.map +1 -0
  662. package/dist/site/batch-start.d.ts +60 -0
  663. package/dist/site/batch-start.d.ts.map +1 -0
  664. package/dist/site/batch-start.js +39 -0
  665. package/dist/site/batch-start.js.map +1 -0
  666. package/dist/site/connected-repos.d.ts +25 -0
  667. package/dist/site/connected-repos.d.ts.map +1 -0
  668. package/dist/site/connected-repos.js +109 -0
  669. package/dist/site/connected-repos.js.map +1 -0
  670. package/dist/site/evaluation-start.d.ts +4 -0
  671. package/dist/site/evaluation-start.d.ts.map +1 -0
  672. package/dist/site/evaluation-start.js +19 -0
  673. package/dist/site/evaluation-start.js.map +1 -0
  674. package/dist/site/generation-config.d.ts +4 -0
  675. package/dist/site/generation-config.d.ts.map +1 -0
  676. package/dist/site/generation-config.js +16 -0
  677. package/dist/site/generation-config.js.map +1 -0
  678. package/dist/site/generation-credentials.d.ts +6 -0
  679. package/dist/site/generation-credentials.d.ts.map +1 -0
  680. package/dist/site/generation-credentials.js +101 -0
  681. package/dist/site/generation-credentials.js.map +1 -0
  682. package/dist/site/generation-run.d.ts +6 -0
  683. package/dist/site/generation-run.d.ts.map +1 -0
  684. package/dist/site/generation-run.js +22 -0
  685. package/dist/site/generation-run.js.map +1 -0
  686. package/dist/site/generation-settings.d.ts +80 -0
  687. package/dist/site/generation-settings.d.ts.map +1 -0
  688. package/dist/site/generation-settings.js +84 -0
  689. package/dist/site/generation-settings.js.map +1 -0
  690. package/dist/site/generation-subscription.d.ts +3 -0
  691. package/dist/site/generation-subscription.d.ts.map +1 -0
  692. package/dist/site/generation-subscription.js +38 -0
  693. package/dist/site/generation-subscription.js.map +1 -0
  694. package/dist/site/github-repos.d.ts +35 -0
  695. package/dist/site/github-repos.d.ts.map +1 -0
  696. package/dist/site/github-repos.js +121 -0
  697. package/dist/site/github-repos.js.map +1 -0
  698. package/dist/site/pr-candidate.d.ts +26 -0
  699. package/dist/site/pr-candidate.d.ts.map +1 -0
  700. package/dist/site/pr-candidate.js +101 -0
  701. package/dist/site/pr-candidate.js.map +1 -0
  702. package/dist/site/pr-list.d.ts +13 -0
  703. package/dist/site/pr-list.d.ts.map +1 -0
  704. package/dist/site/pr-list.js +24 -0
  705. package/dist/site/pr-list.js.map +1 -0
  706. package/dist/site/pr-routes.d.ts +26 -0
  707. package/dist/site/pr-routes.d.ts.map +1 -0
  708. package/dist/site/pr-routes.js +139 -0
  709. package/dist/site/pr-routes.js.map +1 -0
  710. package/dist/site/repo-store.d.ts +40 -0
  711. package/dist/site/repo-store.d.ts.map +1 -0
  712. package/dist/site/repo-store.js +74 -0
  713. package/dist/site/repo-store.js.map +1 -0
  714. package/dist/site/run-store.d.ts +17 -0
  715. package/dist/site/run-store.d.ts.map +1 -0
  716. package/dist/site/run-store.js +42 -0
  717. package/dist/site/run-store.js.map +1 -0
  718. package/dist/site/runtime.d.ts +27 -0
  719. package/dist/site/runtime.d.ts.map +1 -0
  720. package/dist/site/runtime.js +97 -0
  721. package/dist/site/runtime.js.map +1 -0
  722. package/dist/site/task-deletion.d.ts +7 -0
  723. package/dist/site/task-deletion.d.ts.map +1 -0
  724. package/dist/site/task-deletion.js +29 -0
  725. package/dist/site/task-deletion.js.map +1 -0
  726. package/dist/site/task-start-reservation.d.ts +4 -0
  727. package/dist/site/task-start-reservation.d.ts.map +1 -0
  728. package/dist/site/task-start-reservation.js +18 -0
  729. package/dist/site/task-start-reservation.js.map +1 -0
  730. package/dist/site/task-start.d.ts +33 -0
  731. package/dist/site/task-start.d.ts.map +1 -0
  732. package/dist/site/task-start.js +50 -0
  733. package/dist/site/task-start.js.map +1 -0
  734. package/dist/site/task-status.d.ts +36 -0
  735. package/dist/site/task-status.d.ts.map +1 -0
  736. package/dist/site/task-status.js +113 -0
  737. package/dist/site/task-status.js.map +1 -0
  738. package/dist/site/task-store.d.ts +78 -0
  739. package/dist/site/task-store.d.ts.map +1 -0
  740. package/dist/site/task-store.js +186 -0
  741. package/dist/site/task-store.js.map +1 -0
  742. package/dist/site/task-sync.d.ts +30 -0
  743. package/dist/site/task-sync.d.ts.map +1 -0
  744. package/dist/site/task-sync.js +121 -0
  745. package/dist/site/task-sync.js.map +1 -0
  746. package/dist/site/tasks.d.ts +47 -0
  747. package/dist/site/tasks.d.ts.map +1 -0
  748. package/dist/site/tasks.js +164 -0
  749. package/dist/site/tasks.js.map +1 -0
  750. package/dist/site/temporal-status.d.ts +8 -0
  751. package/dist/site/temporal-status.d.ts.map +1 -0
  752. package/dist/site/temporal-status.js +41 -0
  753. package/dist/site/temporal-status.js.map +1 -0
  754. package/dist/site/tenant.d.ts +4 -0
  755. package/dist/site/tenant.d.ts.map +1 -0
  756. package/dist/site/tenant.js +6 -0
  757. package/dist/site/tenant.js.map +1 -0
  758. package/dist/static-check.d.ts +38 -0
  759. package/dist/static-check.d.ts.map +1 -0
  760. package/dist/static-check.js +131 -0
  761. package/dist/static-check.js.map +1 -0
  762. package/dist/submission-hash.d.ts +18 -0
  763. package/dist/submission-hash.d.ts.map +1 -0
  764. package/dist/submission-hash.js +16 -0
  765. package/dist/submission-hash.js.map +1 -0
  766. package/dist/subscription-auth.d.ts +0 -7
  767. package/dist/subscription-auth.d.ts.map +1 -1
  768. package/dist/subscription-auth.js +3 -23
  769. package/dist/subscription-auth.js.map +1 -1
  770. package/dist/temporal/activities/agent-feed.d.ts +5 -0
  771. package/dist/temporal/activities/agent-feed.d.ts.map +1 -0
  772. package/dist/temporal/activities/agent-feed.js +41 -0
  773. package/dist/temporal/activities/agent-feed.js.map +1 -0
  774. package/dist/temporal/activities/agent-scripts.d.ts +16 -0
  775. package/dist/temporal/activities/agent-scripts.d.ts.map +1 -0
  776. package/dist/temporal/activities/agent-scripts.js +162 -0
  777. package/dist/temporal/activities/agent-scripts.js.map +1 -0
  778. package/dist/temporal/activities/authoring-round.d.ts +13 -0
  779. package/dist/temporal/activities/authoring-round.d.ts.map +1 -0
  780. package/dist/temporal/activities/authoring-round.js +160 -0
  781. package/dist/temporal/activities/authoring-round.js.map +1 -0
  782. package/dist/temporal/activities/constants.d.ts +5 -0
  783. package/dist/temporal/activities/constants.d.ts.map +1 -0
  784. package/dist/temporal/activities/constants.js +5 -0
  785. package/dist/temporal/activities/constants.js.map +1 -0
  786. package/dist/temporal/activities/discovery.d.ts +17 -0
  787. package/dist/temporal/activities/discovery.d.ts.map +1 -0
  788. package/dist/temporal/activities/discovery.js +153 -0
  789. package/dist/temporal/activities/discovery.js.map +1 -0
  790. package/dist/temporal/activities/drafts.d.ts +15 -0
  791. package/dist/temporal/activities/drafts.d.ts.map +1 -0
  792. package/dist/temporal/activities/drafts.js +51 -0
  793. package/dist/temporal/activities/drafts.js.map +1 -0
  794. package/dist/temporal/activities/excluded-source-prs.d.ts +9 -0
  795. package/dist/temporal/activities/excluded-source-prs.d.ts.map +1 -0
  796. package/dist/temporal/activities/excluded-source-prs.js +132 -0
  797. package/dist/temporal/activities/excluded-source-prs.js.map +1 -0
  798. package/dist/temporal/activities/export.d.ts +38 -0
  799. package/dist/temporal/activities/export.d.ts.map +1 -0
  800. package/dist/temporal/activities/export.js +79 -0
  801. package/dist/temporal/activities/export.js.map +1 -0
  802. package/dist/temporal/activities/factory.d.ts +5 -0
  803. package/dist/temporal/activities/factory.d.ts.map +1 -0
  804. package/dist/temporal/activities/factory.js +26 -0
  805. package/dist/temporal/activities/factory.js.map +1 -0
  806. package/dist/temporal/activities/gate-logs.d.ts +20 -0
  807. package/dist/temporal/activities/gate-logs.d.ts.map +1 -0
  808. package/dist/temporal/activities/gate-logs.js +62 -0
  809. package/dist/temporal/activities/gate-logs.js.map +1 -0
  810. package/dist/temporal/activities/generation-runtime.d.ts +6 -0
  811. package/dist/temporal/activities/generation-runtime.d.ts.map +1 -0
  812. package/dist/temporal/activities/generation-runtime.js +56 -0
  813. package/dist/temporal/activities/generation-runtime.js.map +1 -0
  814. package/dist/temporal/activities/harbor.d.ts +11 -0
  815. package/dist/temporal/activities/harbor.d.ts.map +1 -0
  816. package/dist/temporal/activities/harbor.js +112 -0
  817. package/dist/temporal/activities/harbor.js.map +1 -0
  818. package/dist/temporal/activities/modal-build-log.d.ts +12 -0
  819. package/dist/temporal/activities/modal-build-log.d.ts.map +1 -0
  820. package/dist/temporal/activities/modal-build-log.js +57 -0
  821. package/dist/temporal/activities/modal-build-log.js.map +1 -0
  822. package/dist/temporal/activities/prompts-authoring.d.ts +6 -0
  823. package/dist/temporal/activities/prompts-authoring.d.ts.map +1 -0
  824. package/dist/temporal/activities/prompts-authoring.js +87 -0
  825. package/dist/temporal/activities/prompts-authoring.js.map +1 -0
  826. package/dist/temporal/activities/prompts-verifier.d.ts +17 -0
  827. package/dist/temporal/activities/prompts-verifier.d.ts.map +1 -0
  828. package/dist/temporal/activities/prompts-verifier.js +66 -0
  829. package/dist/temporal/activities/prompts-verifier.js.map +1 -0
  830. package/dist/temporal/activities/provenance.d.ts +4 -0
  831. package/dist/temporal/activities/provenance.d.ts.map +1 -0
  832. package/dist/temporal/activities/provenance.js +18 -0
  833. package/dist/temporal/activities/provenance.js.map +1 -0
  834. package/dist/temporal/activities/replay.d.ts +20 -0
  835. package/dist/temporal/activities/replay.d.ts.map +1 -0
  836. package/dist/temporal/activities/replay.js +135 -0
  837. package/dist/temporal/activities/replay.js.map +1 -0
  838. package/dist/temporal/activities/round-outcome.d.ts +63 -0
  839. package/dist/temporal/activities/round-outcome.d.ts.map +1 -0
  840. package/dist/temporal/activities/round-outcome.js +127 -0
  841. package/dist/temporal/activities/round-outcome.js.map +1 -0
  842. package/dist/temporal/activities/runtime.d.ts +38 -0
  843. package/dist/temporal/activities/runtime.d.ts.map +1 -0
  844. package/dist/temporal/activities/runtime.js +146 -0
  845. package/dist/temporal/activities/runtime.js.map +1 -0
  846. package/dist/temporal/activities/session-verify.d.ts +45 -0
  847. package/dist/temporal/activities/session-verify.d.ts.map +1 -0
  848. package/dist/temporal/activities/session-verify.js +91 -0
  849. package/dist/temporal/activities/session-verify.js.map +1 -0
  850. package/dist/temporal/activities/submissions.d.ts +9 -0
  851. package/dist/temporal/activities/submissions.d.ts.map +1 -0
  852. package/dist/temporal/activities/submissions.js +28 -0
  853. package/dist/temporal/activities/submissions.js.map +1 -0
  854. package/dist/temporal/activities/task-compiler.d.ts +21 -0
  855. package/dist/temporal/activities/task-compiler.d.ts.map +1 -0
  856. package/dist/temporal/activities/task-compiler.js +63 -0
  857. package/dist/temporal/activities/task-compiler.js.map +1 -0
  858. package/dist/temporal/activities/types.d.ts +57 -0
  859. package/dist/temporal/activities/types.d.ts.map +1 -0
  860. package/dist/temporal/activities/types.js +2 -0
  861. package/dist/temporal/activities/types.js.map +1 -0
  862. package/dist/temporal/activities/verifier-material.d.ts +18 -0
  863. package/dist/temporal/activities/verifier-material.d.ts.map +1 -0
  864. package/dist/temporal/activities/verifier-material.js +49 -0
  865. package/dist/temporal/activities/verifier-material.js.map +1 -0
  866. package/dist/temporal/activities/verifier-outcome.d.ts +19 -0
  867. package/dist/temporal/activities/verifier-outcome.d.ts.map +1 -0
  868. package/dist/temporal/activities/verifier-outcome.js +70 -0
  869. package/dist/temporal/activities/verifier-outcome.js.map +1 -0
  870. package/dist/temporal/activities/verifier-round.d.ts +8 -0
  871. package/dist/temporal/activities/verifier-round.d.ts.map +1 -0
  872. package/dist/temporal/activities/verifier-round.js +110 -0
  873. package/dist/temporal/activities/verifier-round.js.map +1 -0
  874. package/dist/temporal/activities/verify-harbor.d.ts +15 -0
  875. package/dist/temporal/activities/verify-harbor.d.ts.map +1 -0
  876. package/dist/temporal/activities/verify-harbor.js +193 -0
  877. package/dist/temporal/activities/verify-harbor.js.map +1 -0
  878. package/dist/temporal/activities/verify.d.ts +11 -0
  879. package/dist/temporal/activities/verify.d.ts.map +1 -0
  880. package/dist/temporal/activities/verify.js +151 -0
  881. package/dist/temporal/activities/verify.js.map +1 -0
  882. package/dist/temporal/activities.d.ts +3 -51
  883. package/dist/temporal/activities.d.ts.map +1 -1
  884. package/dist/temporal/activities.js +2 -886
  885. package/dist/temporal/activities.js.map +1 -1
  886. package/dist/temporal/connection.d.ts.map +1 -1
  887. package/dist/temporal/connection.js +3 -2
  888. package/dist/temporal/connection.js.map +1 -1
  889. package/dist/temporal/worker-main.js +19 -3
  890. package/dist/temporal/worker-main.js.map +1 -1
  891. package/dist/temporal/workflow/activity-proxies.d.ts +3 -0
  892. package/dist/temporal/workflow/activity-proxies.d.ts.map +1 -0
  893. package/dist/temporal/workflow/activity-proxies.js +45 -0
  894. package/dist/temporal/workflow/activity-proxies.js.map +1 -0
  895. package/dist/temporal/workflow/authoring-stage.d.ts +5 -0
  896. package/dist/temporal/workflow/authoring-stage.d.ts.map +1 -0
  897. package/dist/temporal/workflow/authoring-stage.js +64 -0
  898. package/dist/temporal/workflow/authoring-stage.js.map +1 -0
  899. package/dist/temporal/workflow/candidate-tracker.d.ts +28 -0
  900. package/dist/temporal/workflow/candidate-tracker.d.ts.map +1 -0
  901. package/dist/temporal/workflow/candidate-tracker.js +85 -0
  902. package/dist/temporal/workflow/candidate-tracker.js.map +1 -0
  903. package/dist/temporal/workflow/candidate.d.ts +6 -0
  904. package/dist/temporal/workflow/candidate.d.ts.map +1 -0
  905. package/dist/temporal/workflow/candidate.js +54 -0
  906. package/dist/temporal/workflow/candidate.js.map +1 -0
  907. package/dist/temporal/workflow/discovery.d.ts +19 -0
  908. package/dist/temporal/workflow/discovery.d.ts.map +1 -0
  909. package/dist/temporal/workflow/discovery.js +137 -0
  910. package/dist/temporal/workflow/discovery.js.map +1 -0
  911. package/dist/temporal/workflow/failures.d.ts +5 -0
  912. package/dist/temporal/workflow/failures.d.ts.map +1 -0
  913. package/dist/temporal/workflow/failures.js +28 -0
  914. package/dist/temporal/workflow/failures.js.map +1 -0
  915. package/dist/temporal/workflow/run.d.ts +5 -0
  916. package/dist/temporal/workflow/run.d.ts.map +1 -0
  917. package/dist/temporal/workflow/run.js +154 -0
  918. package/dist/temporal/workflow/run.js.map +1 -0
  919. package/dist/temporal/workflow/stage.d.ts +26 -0
  920. package/dist/temporal/workflow/stage.d.ts.map +1 -0
  921. package/dist/temporal/workflow/stage.js +16 -0
  922. package/dist/temporal/workflow/stage.js.map +1 -0
  923. package/dist/temporal/workflow/verification-stage.d.ts +11 -0
  924. package/dist/temporal/workflow/verification-stage.d.ts.map +1 -0
  925. package/dist/temporal/workflow/verification-stage.js +20 -0
  926. package/dist/temporal/workflow/verification-stage.js.map +1 -0
  927. package/dist/temporal/workflow.d.ts +12 -4
  928. package/dist/temporal/workflow.d.ts.map +1 -1
  929. package/dist/temporal/workflow.js +38 -445
  930. package/dist/temporal/workflow.js.map +1 -1
  931. package/dist/verifier-fix.d.ts +20 -0
  932. package/dist/verifier-fix.d.ts.map +1 -0
  933. package/dist/verifier-fix.js +62 -0
  934. package/dist/verifier-fix.js.map +1 -0
  935. package/dist/verify-report.d.ts +9 -0
  936. package/dist/verify-report.d.ts.map +1 -0
  937. package/dist/verify-report.js +135 -0
  938. package/dist/verify-report.js.map +1 -0
  939. package/dist/viewer/archived-keys.d.ts +9 -0
  940. package/dist/viewer/archived-keys.d.ts.map +1 -0
  941. package/dist/viewer/archived-keys.js +36 -0
  942. package/dist/viewer/archived-keys.js.map +1 -0
  943. package/dist/viewer/archived.d.ts +20 -0
  944. package/dist/viewer/archived.d.ts.map +1 -0
  945. package/dist/viewer/archived.js +238 -0
  946. package/dist/viewer/archived.js.map +1 -0
  947. package/dist/viewer/artifacts.d.ts +8 -0
  948. package/dist/viewer/artifacts.d.ts.map +1 -0
  949. package/dist/viewer/artifacts.js +96 -0
  950. package/dist/viewer/artifacts.js.map +1 -0
  951. package/dist/viewer/bundle.d.ts +9 -0
  952. package/dist/viewer/bundle.d.ts.map +1 -0
  953. package/dist/viewer/bundle.js +79 -0
  954. package/dist/viewer/bundle.js.map +1 -0
  955. package/dist/viewer/candidates.d.ts +9 -0
  956. package/dist/viewer/candidates.d.ts.map +1 -0
  957. package/dist/viewer/candidates.js +137 -0
  958. package/dist/viewer/candidates.js.map +1 -0
  959. package/dist/viewer/local-server.d.ts +11 -0
  960. package/dist/viewer/local-server.d.ts.map +1 -0
  961. package/dist/viewer/local-server.js +64 -0
  962. package/dist/viewer/local-server.js.map +1 -0
  963. package/dist/viewer/task-files.d.ts +10 -0
  964. package/dist/viewer/task-files.d.ts.map +1 -0
  965. package/dist/viewer/task-files.js +120 -0
  966. package/dist/viewer/task-files.js.map +1 -0
  967. package/dist/viewer/types.d.ts +78 -0
  968. package/dist/viewer/types.d.ts.map +1 -0
  969. package/dist/viewer/types.js +36 -0
  970. package/dist/viewer/types.js.map +1 -0
  971. package/docs/api.md +168 -0
  972. package/docs/evaluations.md +42 -15
  973. package/docs/operations.md +254 -26
  974. package/docs/solver-evaluations.md +63 -0
  975. package/docs/task-construction.md +21 -11
  976. package/drizzle/0000_glossy_johnny_blaze.sql +97 -0
  977. package/drizzle/0001_evaluation_records.sql +5 -0
  978. package/drizzle/0002_task_deletion.sql +1 -0
  979. package/drizzle/0003_drop_repo_runs.sql +3 -0
  980. package/drizzle/0004_preserve_batch_runs.sql +8 -0
  981. package/drizzle/0005_api_keys.sql +15 -0
  982. package/drizzle/meta/0000_snapshot.json +776 -0
  983. package/drizzle/meta/0001_snapshot.json +807 -0
  984. package/drizzle/meta/0002_snapshot.json +813 -0
  985. package/drizzle/meta/0003_snapshot.json +726 -0
  986. package/drizzle/meta/0004_snapshot.json +813 -0
  987. package/drizzle/meta/0005_snapshot.json +919 -0
  988. package/drizzle/meta/_journal.json +48 -0
  989. package/package.json +39 -25
  990. package/src/extensions/authoring.ts +83 -72
  991. package/src/extensions/shared/deliverable.ts +153 -0
  992. package/src/extensions/shared/mailbox.ts +128 -0
  993. package/src/extensions/shared/schemas.ts +101 -0
  994. package/src/extensions/shared/static-check.ts +103 -0
  995. package/src/extensions/verifier.ts +88 -0
  996. package/src/skills/selfbench/SKILL.md +71 -13
  997. package/biome.json +0 -24
  998. package/dist/agent-smoke-main.d.ts +0 -3
  999. package/dist/agent-smoke-main.d.ts.map +0 -1
  1000. package/dist/agent-smoke-main.js +0 -55
  1001. package/dist/agent-smoke-main.js.map +0 -1
  1002. package/dist/agent-smoke.d.ts +0 -18
  1003. package/dist/agent-smoke.d.ts.map +0 -1
  1004. package/dist/agent-smoke.js +0 -103
  1005. package/dist/agent-smoke.js.map +0 -1
  1006. package/dist/codex-review.d.ts +0 -41
  1007. package/dist/codex-review.d.ts.map +0 -1
  1008. package/dist/codex-review.js +0 -193
  1009. package/dist/codex-review.js.map +0 -1
  1010. package/dist/eval-main.d.ts +0 -3
  1011. package/dist/eval-main.d.ts.map +0 -1
  1012. package/dist/eval-main.js +0 -81
  1013. package/dist/eval-main.js.map +0 -1
  1014. package/dist/evaluate.d.ts +0 -25
  1015. package/dist/evaluate.d.ts.map +0 -1
  1016. package/dist/evaluate.js +0 -214
  1017. package/dist/evaluate.js.map +0 -1
  1018. package/dist/modal-auth.d.ts.map +0 -1
  1019. package/dist/modal-auth.js.map +0 -1
  1020. package/dist/reaudit-main.d.ts +0 -3
  1021. package/dist/reaudit-main.d.ts.map +0 -1
  1022. package/dist/reaudit-main.js +0 -158
  1023. package/dist/reaudit-main.js.map +0 -1
  1024. package/dist/repair-main.d.ts +0 -3
  1025. package/dist/repair-main.d.ts.map +0 -1
  1026. package/dist/repair-main.js +0 -171
  1027. package/dist/repair-main.js.map +0 -1
  1028. package/dist/review/assets/index-CZ3G759O.js +0 -1568
  1029. package/dist/review/assets/index-DgSLzX8l.css +0 -1
  1030. package/dist/sandbox/programs/prepare-repair.d.ts +0 -7
  1031. package/dist/sandbox/programs/prepare-repair.d.ts.map +0 -1
  1032. package/dist/sandbox/programs/prepare-repair.js.map +0 -1
  1033. package/dist/sandbox/programs/repair.d.ts +0 -3
  1034. package/dist/sandbox/programs/repair.d.ts.map +0 -1
  1035. package/dist/sandbox/programs/repair.js +0 -100
  1036. package/dist/sandbox/programs/repair.js.map +0 -1
  1037. package/dist/sandbox/programs/review.d.ts +0 -2
  1038. package/dist/sandbox/programs/review.d.ts.map +0 -1
  1039. package/dist/sandbox/programs/review.js +0 -18
  1040. package/dist/sandbox/programs/review.js.map +0 -1
  1041. package/dist/sandbox/programs/validation-repair.d.ts +0 -3
  1042. package/dist/sandbox/programs/validation-repair.d.ts.map +0 -1
  1043. package/dist/sandbox/programs/validation-repair.js +0 -115
  1044. package/dist/sandbox/programs/validation-repair.js.map +0 -1
  1045. package/dist/sandbox-repair.bundle.js +0 -323
  1046. package/dist/sandbox-review.bundle.js +0 -14462
  1047. package/dist/validate-main.d.ts +0 -3
  1048. package/dist/validate-main.d.ts.map +0 -1
  1049. package/dist/validate-main.js +0 -143
  1050. package/dist/validate-main.js.map +0 -1
  1051. package/dist/validation-repair.d.ts +0 -10
  1052. package/dist/validation-repair.d.ts.map +0 -1
  1053. package/dist/validation-repair.js +0 -72
  1054. package/dist/validation-repair.js.map +0 -1
  1055. package/review/index.html +0 -14
  1056. package/review/src/App.tsx +0 -338
  1057. package/review/src/export-loader.test.ts +0 -57
  1058. package/review/src/export-loader.ts +0 -151
  1059. package/review/src/main.tsx +0 -15
  1060. package/review/src/styles.css +0 -162
  1061. package/review/src/types.ts +0 -47
  1062. package/review/tsconfig.json +0 -16
  1063. package/review/vite.config.ts +0 -20
  1064. package/scripts/build-sandbox-programs.ts +0 -22
  1065. package/scripts/verify-package.ts +0 -102
  1066. package/scripts/write-build-metadata.ts +0 -27
  1067. package/src/agent-smoke-main.ts +0 -64
  1068. package/src/agent-smoke.ts +0 -138
  1069. package/src/api-main.ts +0 -12
  1070. package/src/api.ts +0 -291
  1071. package/src/artifacts.ts +0 -357
  1072. package/src/audit.ts +0 -106
  1073. package/src/build-metadata.ts +0 -3
  1074. package/src/cli.ts +0 -504
  1075. package/src/codex-review.ts +0 -229
  1076. package/src/config.ts +0 -239
  1077. package/src/contracts.ts +0 -233
  1078. package/src/coupling.ts +0 -259
  1079. package/src/eval-main.ts +0 -93
  1080. package/src/evaluate.ts +0 -300
  1081. package/src/github.ts +0 -26
  1082. package/src/harbor-environment.ts +0 -17
  1083. package/src/harbor-results.ts +0 -144
  1084. package/src/harbor-task.ts +0 -533
  1085. package/src/hash.ts +0 -5
  1086. package/src/modal-auth.ts +0 -11
  1087. package/src/parallel.ts +0 -24
  1088. package/src/process.ts +0 -167
  1089. package/src/project-paths.ts +0 -15
  1090. package/src/provenance-associations.ts +0 -311
  1091. package/src/provenance.ts +0 -561
  1092. package/src/providers.ts +0 -22
  1093. package/src/reaudit-main.ts +0 -198
  1094. package/src/repair-main.ts +0 -209
  1095. package/src/repair.ts +0 -55
  1096. package/src/run-wait.ts +0 -40
  1097. package/src/sandbox/contracts.ts +0 -52
  1098. package/src/sandbox/index.ts +0 -23
  1099. package/src/sandbox/programs/author.ts +0 -19
  1100. package/src/sandbox/programs/prepare-repair.ts +0 -44
  1101. package/src/sandbox/programs/repair.ts +0 -132
  1102. package/src/sandbox/programs/review.ts +0 -19
  1103. package/src/sandbox/programs/validation-repair.ts +0 -153
  1104. package/src/sandbox/providers/docker/executor.ts +0 -115
  1105. package/src/sandbox/providers/modal/executor.ts +0 -217
  1106. package/src/sandbox/providers/vercel/command.ts +0 -127
  1107. package/src/sandbox/providers/vercel/executor.ts +0 -448
  1108. package/src/sandbox/providers/vercel/fetch.ts +0 -45
  1109. package/src/sandbox/timeout.ts +0 -56
  1110. package/src/setup/vercel/cli.ts +0 -403
  1111. package/src/setup/vercel/index.ts +0 -3
  1112. package/src/setup/vercel/probe.ts +0 -232
  1113. package/src/setup/vercel/profile.ts +0 -322
  1114. package/src/setup/vercel/runtime-image.ts +0 -204
  1115. package/src/setup/vercel/setup.ts +0 -419
  1116. package/src/subscription-auth.ts +0 -80
  1117. package/src/temporal/activities.ts +0 -1348
  1118. package/src/temporal/connection.ts +0 -23
  1119. package/src/temporal/worker-main.ts +0 -28
  1120. package/src/temporal/workflow.ts +0 -568
  1121. package/src/terminal-prompts.ts +0 -197
  1122. package/src/terminal-reporter.ts +0 -126
  1123. package/src/validate-main.ts +0 -177
  1124. package/src/validation-repair.ts +0 -94
  1125. package/tsconfig.build.json +0 -13
  1126. package/tsconfig.json +0 -21
@@ -1,3 +0,0 @@
1
- #!/usr/bin/env node
2
- export {};
3
- //# sourceMappingURL=validate-main.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"validate-main.d.ts","sourceRoot":"","sources":["../src/validate-main.ts"],"names":[],"mappings":""}
@@ -1,143 +0,0 @@
1
- #!/usr/bin/env node
2
- import { access, mkdir, readdir, writeFile } from "node:fs/promises";
3
- import { basename, join, resolve } from "node:path";
4
- import { parseArgs } from "node:util";
5
- import { harborChildEnvironment } from "./harbor-environment.js";
6
- import { harborInfrastructureError, readHarborJobResult } from "./harbor-results.js";
7
- import { parallelMap } from "./parallel.js";
8
- import { runCommand } from "./process.js";
9
- import { isHarborEnvironment } from "./providers.js";
10
- const parsed = parseArgs({
11
- options: {
12
- tasks: { type: "string" },
13
- jobs: { type: "string" },
14
- environment: { type: "string", default: "modal" },
15
- concurrency: { type: "string", default: "10" },
16
- help: { type: "boolean", short: "h" },
17
- },
18
- strict: true,
19
- });
20
- if (parsed.values.help) {
21
- console.log(`Run Harbor nop and oracle gates for expanded SelfBench tasks.
22
-
23
- Usage:
24
- self-bench-validate --tasks DIRECTORY --jobs DIRECTORY [options]
25
-
26
- Options:
27
- --environment NAME Harbor environment (default: modal)
28
- --concurrency N Concurrent tasks (default: 10)
29
- -h, --help Show this help`);
30
- process.exit(0);
31
- }
32
- const tasksDirectory = resolve(parsed.values.tasks ?? fail("--tasks is required"));
33
- const jobsDirectory = resolve(parsed.values.jobs ?? fail("--jobs is required"));
34
- const environment = parsed.values.environment ?? "modal";
35
- if (!isHarborEnvironment(environment)) {
36
- throw new Error("--environment must be modal or docker");
37
- }
38
- const concurrency = positiveInteger(parsed.values.concurrency, "--concurrency");
39
- const directories = (await Promise.all((await readdir(tasksDirectory)).map(async (name) => {
40
- const directory = join(tasksDirectory, name);
41
- return await access(join(directory, "task.toml")).then(() => directory, () => undefined);
42
- }))).filter((directory) => directory !== undefined);
43
- await mkdir(jobsDirectory, { recursive: true });
44
- const tasks = await parallelMap(directories.sort(), concurrency, async (taskDirectory) => {
45
- const taskId = basename(taskDirectory);
46
- console.error(`validating ${taskId}`);
47
- try {
48
- const nop = await runGate(taskDirectory, taskId, "nop", environment, jobsDirectory);
49
- const oracle = await runGate(taskDirectory, taskId, "oracle", environment, jobsDirectory);
50
- const accepted = nop.passed && oracle.passed;
51
- console.error(`${taskId}: ${accepted ? "accepted" : "rejected"}`);
52
- return { taskId, status: "validated", accepted, nop, oracle };
53
- }
54
- catch (error) {
55
- const message = error instanceof Error ? error.message : String(error);
56
- console.error(`${taskId}: error: ${message}`);
57
- return { taskId, status: "error", accepted: false, error: message };
58
- }
59
- });
60
- const report = {
61
- schemaVersion: 1,
62
- generatedAt: new Date().toISOString(),
63
- sourceTasks: tasksDirectory,
64
- environment,
65
- summary: {
66
- total: tasks.length,
67
- accepted: tasks.filter((task) => task.accepted).length,
68
- rejected: tasks.filter((task) => task.status === "validated" && !task.accepted).length,
69
- errors: tasks.filter((task) => task.status === "error").length,
70
- },
71
- tasks,
72
- };
73
- await writeFile(join(jobsDirectory, "validation-summary.json"), `${JSON.stringify(report, null, 2)}\n`);
74
- console.log(JSON.stringify(report.summary, null, 2));
75
- async function runGate(taskDirectory, taskId, agent, environment, jobsDirectory) {
76
- const jobName = `${taskId}-${agent}-${crypto.randomUUID().slice(0, 8)}`;
77
- const process = await runCommand("harbor", [
78
- "run",
79
- "--path",
80
- taskDirectory,
81
- "--agent",
82
- agent,
83
- "--env",
84
- environment,
85
- "--job-name",
86
- jobName,
87
- "--jobs-dir",
88
- jobsDirectory,
89
- "--n-concurrent",
90
- "1",
91
- "--max-retries",
92
- "1",
93
- "--delete",
94
- "--yes",
95
- "--quiet",
96
- ], {
97
- allowFailure: true,
98
- env: harborChildEnvironment(),
99
- timeoutMs: 4 * 60 * 60 * 1000,
100
- });
101
- if (process.exitCode !== 0) {
102
- throw new Error(`Harbor ${agent} exited ${process.exitCode}: ${process.stderr.slice(-1_000)}`);
103
- }
104
- const result = await readHarborJobResult(jobsDirectory, jobName);
105
- const infrastructure = harborInfrastructureError(result.trial);
106
- if (infrastructure) {
107
- throw new Error(`Harbor ${agent} infrastructure failure: ${infrastructure}`);
108
- }
109
- const rewards = rewardValues(result.trial);
110
- const passed = agent === "nop"
111
- ? rewards.fail_to_pass === 0 &&
112
- (rewards.pass_to_pass ?? 0) >= 1 &&
113
- (rewards.setup_completed ?? 0) >= 1
114
- : (rewards.patch_applied ?? 0) >= 1 &&
115
- (rewards.fail_to_pass ?? 0) >= 1 &&
116
- (rewards.pass_to_pass ?? 0) >= 1 &&
117
- (rewards.deterministic ?? 0) >= 1 &&
118
- (rewards.setup_completed ?? 0) >= 1;
119
- return { passed, rewards };
120
- }
121
- function rewardValues(value) {
122
- if (!isRecord(value) || !isRecord(value.verifier_result)) {
123
- return {};
124
- }
125
- const raw = value.verifier_result.rewards;
126
- return isRecord(raw)
127
- ? Object.fromEntries(Object.entries(raw).filter((entry) => typeof entry[1] === "number"))
128
- : {};
129
- }
130
- function positiveInteger(value, label) {
131
- const number = Number(value);
132
- if (!Number.isInteger(number) || number < 1) {
133
- throw new Error(`${label} must be a positive integer`);
134
- }
135
- return number;
136
- }
137
- function isRecord(value) {
138
- return typeof value === "object" && value !== null && !Array.isArray(value);
139
- }
140
- function fail(message) {
141
- throw new Error(message);
142
- }
143
- //# sourceMappingURL=validate-main.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"validate-main.js","sourceRoot":"","sources":["../src/validate-main.ts"],"names":[],"mappings":";AAEA,OAAO,EAAE,MAAM,EAAE,KAAK,EAAE,OAAO,EAAE,SAAS,EAAE,MAAM,kBAAkB,CAAC;AACrE,OAAO,EAAE,QAAQ,EAAE,IAAI,EAAE,OAAO,EAAE,MAAM,WAAW,CAAC;AACpD,OAAO,EAAE,SAAS,EAAE,MAAM,WAAW,CAAC;AACtC,OAAO,EAAE,sBAAsB,EAAE,MAAM,yBAAyB,CAAC;AACjE,OAAO,EAAE,yBAAyB,EAAE,mBAAmB,EAAE,MAAM,qBAAqB,CAAC;AACrF,OAAO,EAAE,WAAW,EAAE,MAAM,eAAe,CAAC;AAC5C,OAAO,EAAE,UAAU,EAAE,MAAM,cAAc,CAAC;AAC1C,OAAO,EAA0B,mBAAmB,EAAE,MAAM,gBAAgB,CAAC;AAE7E,MAAM,MAAM,GAAG,SAAS,CAAC;IACvB,OAAO,EAAE;QACP,KAAK,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;QACzB,IAAI,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE;QACxB,WAAW,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,OAAO,EAAE;QACjD,WAAW,EAAE,EAAE,IAAI,EAAE,QAAQ,EAAE,OAAO,EAAE,IAAI,EAAE;QAC9C,IAAI,EAAE,EAAE,IAAI,EAAE,SAAS,EAAE,KAAK,EAAE,GAAG,EAAE;KACtC;IACD,MAAM,EAAE,IAAI;CACb,CAAC,CAAC;AACH,IAAI,MAAM,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC;IACvB,OAAO,CAAC,GAAG,CAAC;;;;;;;;qCAQuB,CAAC,CAAC;IACrC,OAAO,CAAC,IAAI,CAAC,CAAC,CAAC,CAAC;AAClB,CAAC;AAED,MAAM,cAAc,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,KAAK,IAAI,IAAI,CAAC,qBAAqB,CAAC,CAAC,CAAC;AACnF,MAAM,aAAa,GAAG,OAAO,CAAC,MAAM,CAAC,MAAM,CAAC,IAAI,IAAI,IAAI,CAAC,oBAAoB,CAAC,CAAC,CAAC;AAChF,MAAM,WAAW,GAAG,MAAM,CAAC,MAAM,CAAC,WAAW,IAAI,OAAO,CAAC;AACzD,IAAI,CAAC,mBAAmB,CAAC,WAAW,CAAC,EAAE,CAAC;IACtC,MAAM,IAAI,KAAK,CAAC,uCAAuC,CAAC,CAAC;AAC3D,CAAC;AACD,MAAM,WAAW,GAAG,eAAe,CAAC,MAAM,CAAC,MAAM,CAAC,WAAW,EAAE,eAAe,CAAC,CAAC;AAChF,MAAM,WAAW,GAAG,CAClB,MAAM,OAAO,CAAC,GAAG,CACf,CACE,MAAM,OAAO,CAAC,cAAc,CAAC,CAC9B,CAAC,GAAG,CAAC,KAAK,EAAE,IAAI,EAAE,EAAE;IACnB,MAAM,SAAS,GAAG,IAAI,CAAC,cAAc,EAAE,IAAI,CAAC,CAAC;IAC7C,OAAO,MAAM,MAAM,CAAC,IAAI,CAAC,SAAS,EAAE,WAAW,CAAC,CAAC,CAAC,IAAI,CACpD,GAAG,EAAE,CAAC,SAAS,EACf,GAAG,EAAE,CAAC,SAAS,CAChB,CAAC;AACJ,CAAC,CAAC,CACH,CACF,CAAC,MAAM,CAAC,CAAC,SAAS,EAAuB,EAAE,CAAC,SAAS,KAAK,SAAS,CAAC,CAAC;AACtE,MAAM,KAAK,CAAC,aAAa,EAAE,EAAE,SAAS,EAAE,IAAI,EAAE,CAAC,CAAC;AAEhD,MAAM,KAAK,GAAG,MAAM,WAAW,CAAC,WAAW,CAAC,IAAI,EAAE,EAAE,WAAW,EAAE,KAAK,EAAE,aAAa,EAAE,EAAE;IACvF,MAAM,MAAM,GAAG,QAAQ,CAAC,aAAa,CAAC,CAAC;IACvC,OAAO,CAAC,KAAK,CAAC,cAAc,MAAM,EAAE,CAAC,CAAC;IACtC,IAAI,CAAC;QACH,MAAM,GAAG,GAAG,MAAM,OAAO,CAAC,aAAa,EAAE,MAAM,EAAE,KAAK,EAAE,WAAW,EAAE,aAAa,CAAC,CAAC;QACpF,MAAM,MAAM,GAAG,MAAM,OAAO,CAAC,aAAa,EAAE,MAAM,EAAE,QAAQ,EAAE,WAAW,EAAE,aAAa,CAAC,CAAC;QAC1F,MAAM,QAAQ,GAAG,GAAG,CAAC,MAAM,IAAI,MAAM,CAAC,MAAM,CAAC;QAC7C,OAAO,CAAC,KAAK,CAAC,GAAG,MAAM,KAAK,QAAQ,CAAC,CAAC,CAAC,UAAU,CAAC,CAAC,CAAC,UAAU,EAAE,CAAC,CAAC;QAClE,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,WAAoB,EAAE,QAAQ,EAAE,GAAG,EAAE,MAAM,EAAE,CAAC;IACzE,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,MAAM,OAAO,GAAG,KAAK,YAAY,KAAK,CAAC,CAAC,CAAC,KAAK,CAAC,OAAO,CAAC,CAAC,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;QACvE,OAAO,CAAC,KAAK,CAAC,GAAG,MAAM,YAAY,OAAO,EAAE,CAAC,CAAC;QAC9C,OAAO,EAAE,MAAM,EAAE,MAAM,EAAE,OAAgB,EAAE,QAAQ,EAAE,KAAK,EAAE,KAAK,EAAE,OAAO,EAAE,CAAC;IAC/E,CAAC;AACH,CAAC,CAAC,CAAC;AACH,MAAM,MAAM,GAAG;IACb,aAAa,EAAE,CAAC;IAChB,WAAW,EAAE,IAAI,IAAI,EAAE,CAAC,WAAW,EAAE;IACrC,WAAW,EAAE,cAAc;IAC3B,WAAW;IACX,OAAO,EAAE;QACP,KAAK,EAAE,KAAK,CAAC,MAAM;QACnB,QAAQ,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM;QACtD,QAAQ,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,KAAK,WAAW,IAAI,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC,MAAM;QACtF,MAAM,EAAE,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,IAAI,CAAC,MAAM,KAAK,OAAO,CAAC,CAAC,MAAM;KAC/D;IACD,KAAK;CACN,CAAC;AACF,MAAM,SAAS,CACb,IAAI,CAAC,aAAa,EAAE,yBAAyB,CAAC,EAC9C,GAAG,IAAI,CAAC,SAAS,CAAC,MAAM,EAAE,IAAI,EAAE,CAAC,CAAC,IAAI,CACvC,CAAC;AACF,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,SAAS,CAAC,MAAM,CAAC,OAAO,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC,CAAC;AAErD,KAAK,UAAU,OAAO,CACpB,aAAqB,EACrB,MAAc,EACd,KAAuB,EACvB,WAA8B,EAC9B,aAAqB;IAErB,MAAM,OAAO,GAAG,GAAG,MAAM,IAAI,KAAK,IAAI,MAAM,CAAC,UAAU,EAAE,CAAC,KAAK,CAAC,CAAC,EAAE,CAAC,CAAC,EAAE,CAAC;IACxE,MAAM,OAAO,GAAG,MAAM,UAAU,CAC9B,QAAQ,EACR;QACE,KAAK;QACL,QAAQ;QACR,aAAa;QACb,SAAS;QACT,KAAK;QACL,OAAO;QACP,WAAW;QACX,YAAY;QACZ,OAAO;QACP,YAAY;QACZ,aAAa;QACb,gBAAgB;QAChB,GAAG;QACH,eAAe;QACf,GAAG;QACH,UAAU;QACV,OAAO;QACP,SAAS;KACV,EACD;QACE,YAAY,EAAE,IAAI;QAClB,GAAG,EAAE,sBAAsB,EAAE;QAC7B,SAAS,EAAE,CAAC,GAAG,EAAE,GAAG,EAAE,GAAG,IAAI;KAC9B,CACF,CAAC;IACF,IAAI,OAAO,CAAC,QAAQ,KAAK,CAAC,EAAE,CAAC;QAC3B,MAAM,IAAI,KAAK,CAAC,UAAU,KAAK,WAAW,OAAO,CAAC,QAAQ,KAAK,OAAO,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC,KAAK,CAAC,EAAE,CAAC,CAAC;IACjG,CAAC;IACD,MAAM,MAAM,GAAG,MAAM,mBAAmB,CAAC,aAAa,EAAE,OAAO,CAAC,CAAC;IACjE,MAAM,cAAc,GAAG,yBAAyB,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;IAC/D,IAAI,cAAc,EAAE,CAAC;QACnB,MAAM,IAAI,KAAK,CAAC,UAAU,KAAK,4BAA4B,cAAc,EAAE,CAAC,CAAC;IAC/E,CAAC;IACD,MAAM,OAAO,GAAG,YAAY,CAAC,MAAM,CAAC,KAAK,CAAC,CAAC;IAC3C,MAAM,MAAM,GACV,KAAK,KAAK,KAAK;QACb,CAAC,CAAC,OAAO,CAAC,YAAY,KAAK,CAAC;YAC1B,CAAC,OAAO,CAAC,YAAY,IAAI,CAAC,CAAC,IAAI,CAAC;YAChC,CAAC,OAAO,CAAC,eAAe,IAAI,CAAC,CAAC,IAAI,CAAC;QACrC,CAAC,CAAC,CAAC,OAAO,CAAC,aAAa,IAAI,CAAC,CAAC,IAAI,CAAC;YACjC,CAAC,OAAO,CAAC,YAAY,IAAI,CAAC,CAAC,IAAI,CAAC;YAChC,CAAC,OAAO,CAAC,YAAY,IAAI,CAAC,CAAC,IAAI,CAAC;YAChC,CAAC,OAAO,CAAC,aAAa,IAAI,CAAC,CAAC,IAAI,CAAC;YACjC,CAAC,OAAO,CAAC,eAAe,IAAI,CAAC,CAAC,IAAI,CAAC,CAAC;IAC1C,OAAO,EAAE,MAAM,EAAE,OAAO,EAAE,CAAC;AAC7B,CAAC;AAED,SAAS,YAAY,CAAC,KAAc;IAClC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,eAAe,CAAC,EAAE,CAAC;QACzD,OAAO,EAAE,CAAC;IACZ,CAAC;IACD,MAAM,GAAG,GAAG,KAAK,CAAC,eAAe,CAAC,OAAO,CAAC;IAC1C,OAAO,QAAQ,CAAC,GAAG,CAAC;QAClB,CAAC,CAAC,MAAM,CAAC,WAAW,CAChB,MAAM,CAAC,OAAO,CAAC,GAAG,CAAC,CAAC,MAAM,CACxB,CAAC,KAAK,EAA6B,EAAE,CAAC,OAAO,KAAK,CAAC,CAAC,CAAC,KAAK,QAAQ,CACnE,CACF;QACH,CAAC,CAAC,EAAE,CAAC;AACT,CAAC;AAED,SAAS,eAAe,CAAC,KAAyB,EAAE,KAAa;IAC/D,MAAM,MAAM,GAAG,MAAM,CAAC,KAAK,CAAC,CAAC;IAC7B,IAAI,CAAC,MAAM,CAAC,SAAS,CAAC,MAAM,CAAC,IAAI,MAAM,GAAG,CAAC,EAAE,CAAC;QAC5C,MAAM,IAAI,KAAK,CAAC,GAAG,KAAK,6BAA6B,CAAC,CAAC;IACzD,CAAC;IACD,OAAO,MAAM,CAAC;AAChB,CAAC;AAED,SAAS,QAAQ,CAAC,KAAc;IAC9B,OAAO,OAAO,KAAK,KAAK,QAAQ,IAAI,KAAK,KAAK,IAAI,IAAI,CAAC,KAAK,CAAC,OAAO,CAAC,KAAK,CAAC,CAAC;AAC9E,CAAC;AAED,SAAS,IAAI,CAAC,OAAe;IAC3B,MAAM,IAAI,KAAK,CAAC,OAAO,CAAC,CAAC;AAC3B,CAAC"}
@@ -1,10 +0,0 @@
1
- import type { TaskDefinition } from "./contracts.js";
2
- export declare function validationRepairPaths(originalTestPatch: string): readonly string[];
3
- export declare function assertValidationRepair(original: TaskDefinition, repaired: TaskDefinition, originalTestPatch: string, changedPaths: readonly string[]): void;
4
- export declare function validationRepairPrompt(input: {
5
- readonly definition: TaskDefinition;
6
- readonly authenticRequest: string;
7
- readonly diagnostics: string;
8
- readonly allowedPaths: readonly string[];
9
- }): string;
10
- //# sourceMappingURL=validation-repair.d.ts.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"validation-repair.d.ts","sourceRoot":"","sources":["../src/validation-repair.ts"],"names":[],"mappings":"AAAA,OAAO,KAAK,EAAE,cAAc,EAAE,MAAM,gBAAgB,CAAC;AAGrD,wBAAgB,qBAAqB,CAAC,iBAAiB,EAAE,MAAM,GAAG,SAAS,MAAM,EAAE,CAUlF;AAcD,wBAAgB,sBAAsB,CACpC,QAAQ,EAAE,cAAc,EACxB,QAAQ,EAAE,cAAc,EACxB,iBAAiB,EAAE,MAAM,EACzB,YAAY,EAAE,SAAS,MAAM,EAAE,GAC9B,IAAI,CAwBN;AAED,wBAAgB,sBAAsB,CAAC,KAAK,EAAE;IAC5C,QAAQ,CAAC,UAAU,EAAE,cAAc,CAAC;IACpC,QAAQ,CAAC,gBAAgB,EAAE,MAAM,CAAC;IAClC,QAAQ,CAAC,WAAW,EAAE,MAAM,CAAC;IAC7B,QAAQ,CAAC,YAAY,EAAE,SAAS,MAAM,EAAE,CAAC;CAC1C,GAAG,MAAM,CA8BT"}
@@ -1,72 +0,0 @@
1
- import { patchPaths } from "./repair.js";
2
- export function validationRepairPaths(originalTestPatch) {
3
- const paths = patchPaths(originalTestPatch);
4
- if (paths.length === 0) {
5
- throw new Error("original held-out test patch changes no files");
6
- }
7
- const nonTestPaths = paths.filter((path) => !isTestOnlyPath(path));
8
- if (nonTestPaths.length > 0) {
9
- throw new Error(`validation repair requires test-only patch paths: ${nonTestPaths.join(", ")}`);
10
- }
11
- return paths;
12
- }
13
- function isTestOnlyPath(path) {
14
- const segments = path.toLowerCase().split("/");
15
- const filename = segments.at(-1) ?? "";
16
- return (segments.some((segment) => /^(?:tests?|__tests__|e2e|integration|fixtures?|selfbench(?:-tests|_tests)?|\.selfbench-tests)$/.test(segment)) || /(?:^|\.)(?:test|spec)\.[^.]+$/.test(filename));
17
- }
18
- export function assertValidationRepair(original, repaired, originalTestPatch, changedPaths) {
19
- const immutableKeys = [
20
- "schemaVersion",
21
- "difficulty",
22
- "taskId",
23
- "repo",
24
- "baseCommit",
25
- "workdir",
26
- "sourcePr",
27
- "sourceUrl",
28
- "prompt",
29
- ];
30
- for (const key of immutableKeys) {
31
- if (JSON.stringify(repaired[key]) !== JSON.stringify(original[key])) {
32
- throw new Error(`validation repair changed immutable definition field ${key}`);
33
- }
34
- }
35
- const allowed = new Set(validationRepairPaths(originalTestPatch));
36
- const outside = changedPaths.filter((path) => !allowed.has(path));
37
- if (outside.length > 0) {
38
- throw new Error(`validation repair changed files outside held-out tests: ${outside.join(", ")}`);
39
- }
40
- }
41
- export function validationRepairPrompt(input) {
42
- return `Repair the verifier harness and held-out tests for SelfBench task ${input.definition.taskId}.
43
-
44
- The repository is the exact base snapshot with the current held-out test patch already applied. You may edit only these existing held-out test files:
45
-
46
- ${input.allowedPaths.map((path) => `- ${path}`).join("\n")}
47
-
48
- The authentic engineer request is:
49
-
50
- <authentic_request>
51
- ${input.authenticRequest.trim()}
52
- </authentic_request>
53
-
54
- The failed nop/oracle validation diagnostics are:
55
-
56
- <validation_diagnostics>
57
- ${input.diagnostics.trim()}
58
- </validation_diagnostics>
59
-
60
- Fix the task so its repository-native verifier is rigorous and runnable. You may edit the allowed held-out tests and /work/definition.json. In definition.json you may change only setupCommand, testCommand, failToPass, passToPass, testPaths, toolchains, timeouts, and resources. Never change task identity, difficulty, repository, base commit, workdir, source pull request, prompt, or reference solution.
61
-
62
- The required validation split is:
63
- - nop: the base repository plus held-out tests must make failToPass fail while passToPass succeeds;
64
- - oracle: after /work/task/solution/gold.patch is applied, failToPass and passToPass must both succeed deterministically.
65
-
66
- Use the verifier diagnostics rather than guessing. Inspect repository package scripts and CI for the native test command. Keep {tests} as a list-safe placeholder; do not quote the whole placeholder, assign it to one scalar, or hard-code selected paths elsewhere. Use one test mode/bundler per command instead of chaining equivalent suites. Put dependency installation, native builds, fixture generation, and browser/runtime installation in setupCommand, not testCommand. Pin the repository's declared package manager and use frozen installs. Browser-backed tests must install required browser binaries and OS dependencies during setup. Run focused nop/oracle-style commands in the sandbox when feasible.
67
-
68
- Do not weaken, delete, or skip requested behavioral coverage merely to make commands exit zero. A passing base with no solution is not acceptable. If no rigorous runnable split exists, leave the files and definition unchanged and explain why in the final response.
69
-
70
- Inspect /work/gold.patch and /work/test.sh only to verify the intended behavior and oracle seam, never to couple assertions to private implementation details. Do not modify application code, the instruction, gold patch, or commit files. Finish with the repaired definition at /work/definition.json and any held-out test edits present in the working tree; do not commit.`;
71
- }
72
- //# sourceMappingURL=validation-repair.js.map
@@ -1 +0,0 @@
1
- {"version":3,"file":"validation-repair.js","sourceRoot":"","sources":["../src/validation-repair.ts"],"names":[],"mappings":"AACA,OAAO,EAAE,UAAU,EAAE,MAAM,aAAa,CAAC;AAEzC,MAAM,UAAU,qBAAqB,CAAC,iBAAyB;IAC7D,MAAM,KAAK,GAAG,UAAU,CAAC,iBAAiB,CAAC,CAAC;IAC5C,IAAI,KAAK,CAAC,MAAM,KAAK,CAAC,EAAE,CAAC;QACvB,MAAM,IAAI,KAAK,CAAC,+CAA+C,CAAC,CAAC;IACnE,CAAC;IACD,MAAM,YAAY,GAAG,KAAK,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,cAAc,CAAC,IAAI,CAAC,CAAC,CAAC;IACnE,IAAI,YAAY,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QAC5B,MAAM,IAAI,KAAK,CAAC,qDAAqD,YAAY,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC;IAClG,CAAC;IACD,OAAO,KAAK,CAAC;AACf,CAAC;AAED,SAAS,cAAc,CAAC,IAAY;IAClC,MAAM,QAAQ,GAAG,IAAI,CAAC,WAAW,EAAE,CAAC,KAAK,CAAC,GAAG,CAAC,CAAC;IAC/C,MAAM,QAAQ,GAAG,QAAQ,CAAC,EAAE,CAAC,CAAC,CAAC,CAAC,IAAI,EAAE,CAAC;IACvC,OAAO,CACL,QAAQ,CAAC,IAAI,CAAC,CAAC,OAAO,EAAE,EAAE,CACxB,gGAAgG,CAAC,IAAI,CACnG,OAAO,CACR,CACF,IAAI,+BAA+B,CAAC,IAAI,CAAC,QAAQ,CAAC,CACpD,CAAC;AACJ,CAAC;AAED,MAAM,UAAU,sBAAsB,CACpC,QAAwB,EACxB,QAAwB,EACxB,iBAAyB,EACzB,YAA+B;IAE/B,MAAM,aAAa,GAAG;QACpB,eAAe;QACf,YAAY;QACZ,QAAQ;QACR,MAAM;QACN,YAAY;QACZ,SAAS;QACT,UAAU;QACV,WAAW;QACX,QAAQ;KACA,CAAC;IACX,KAAK,MAAM,GAAG,IAAI,aAAa,EAAE,CAAC;QAChC,IAAI,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,KAAK,IAAI,CAAC,SAAS,CAAC,QAAQ,CAAC,GAAG,CAAC,CAAC,EAAE,CAAC;YACpE,MAAM,IAAI,KAAK,CAAC,wDAAwD,GAAG,EAAE,CAAC,CAAC;QACjF,CAAC;IACH,CAAC;IACD,MAAM,OAAO,GAAG,IAAI,GAAG,CAAC,qBAAqB,CAAC,iBAAiB,CAAC,CAAC,CAAC;IAClE,MAAM,OAAO,GAAG,YAAY,CAAC,MAAM,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,CAAC,OAAO,CAAC,GAAG,CAAC,IAAI,CAAC,CAAC,CAAC;IAClE,IAAI,OAAO,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACvB,MAAM,IAAI,KAAK,CACb,2DAA2D,OAAO,CAAC,IAAI,CAAC,IAAI,CAAC,EAAE,CAChF,CAAC;IACJ,CAAC;AACH,CAAC;AAED,MAAM,UAAU,sBAAsB,CAAC,KAKtC;IACC,OAAO,qEAAqE,KAAK,CAAC,UAAU,CAAC,MAAM;;;;EAInG,KAAK,CAAC,YAAY,CAAC,GAAG,CAAC,CAAC,IAAI,EAAE,EAAE,CAAC,KAAK,IAAI,EAAE,CAAC,CAAC,IAAI,CAAC,IAAI,CAAC;;;;;EAKxD,KAAK,CAAC,gBAAgB,CAAC,IAAI,EAAE;;;;;;EAM7B,KAAK,CAAC,WAAW,CAAC,IAAI,EAAE;;;;;;;;;;;;;kXAawV,CAAC;AACnX,CAAC"}
package/review/index.html DELETED
@@ -1,14 +0,0 @@
1
- <!doctype html>
2
- <html lang="en">
3
- <head>
4
- <meta charset="UTF-8" />
5
- <meta name="viewport" content="width=device-width, initial-scale=1.0" />
6
- <meta name="color-scheme" content="light dark" />
7
- <meta name="theme-color" content="#f4f5f7" />
8
- <title>SelfBench Review</title>
9
- </head>
10
- <body>
11
- <div id="root"></div>
12
- <script type="module" src="/src/main.tsx"></script>
13
- </body>
14
- </html>
@@ -1,338 +0,0 @@
1
- import { parsePatchFiles } from "@pierre/diffs";
2
- import { FileDiff } from "@pierre/diffs/react";
3
- import React from "react";
4
- import { buildCleanExport, loadExport } from "./export-loader";
5
- import type { ExportTask, LoadedExport, RunStatus, RunSummary } from "./types";
6
-
7
- export function App() {
8
- const [runs, setRuns] = React.useState<RunSummary[]>([]);
9
- const [runId, setRunId] = React.useState<string | null>(null);
10
- const [status, setStatus] = React.useState<RunStatus | null>(null);
11
- const [loaded, setLoaded] = React.useState<LoadedExport | null>(null);
12
- const [removed, setRemoved] = React.useState<Set<string>>(new Set());
13
- const [selectedTaskId, setSelectedTaskId] = React.useState<string | null>(null);
14
- const [error, setError] = React.useState<string | null>(null);
15
- const [busy, setBusy] = React.useState(false);
16
- const [token, setToken] = React.useState("");
17
- const fileInput = React.useRef<HTMLInputElement>(null);
18
- const apiFetch = React.useCallback(
19
- (path: string) =>
20
- fetch(path, token ? { headers: { Authorization: `Bearer ${token}` } } : undefined),
21
- [token],
22
- );
23
-
24
- const refreshRuns = React.useCallback(async () => {
25
- try {
26
- setError(null);
27
- const response = await apiFetch("/v1/runs");
28
- if (!response.ok) throw new Error(`Unable to list runs (${response.status})`);
29
- setRuns((await response.json()) as RunSummary[]);
30
- } catch (cause) {
31
- setError(cause instanceof Error ? cause.message : String(cause));
32
- }
33
- }, [apiFetch]);
34
-
35
- React.useEffect(() => {
36
- void refreshRuns();
37
- }, [refreshRuns]);
38
-
39
- const openRun = async (nextRunId: string) => {
40
- try {
41
- setBusy(true);
42
- setError(null);
43
- setRunId(nextRunId);
44
- setLoaded(null);
45
- setRemoved(new Set());
46
- const [statusResponse, exportResponse] = await Promise.all([
47
- apiFetch(`/v1/runs/${encodeURIComponent(nextRunId)}`),
48
- apiFetch(`/v1/runs/${encodeURIComponent(nextRunId)}/export`),
49
- ]);
50
- if (!statusResponse.ok) throw new Error(`Unable to load run (${statusResponse.status})`);
51
- if (!exportResponse.ok) throw new Error(`Export is not ready (${exportResponse.status})`);
52
- setStatus((await statusResponse.json()) as RunStatus);
53
- setLoaded(await loadExport(await exportResponse.blob()));
54
- } catch (cause) {
55
- setError(cause instanceof Error ? cause.message : String(cause));
56
- } finally {
57
- setBusy(false);
58
- }
59
- };
60
-
61
- const openFile = async (file: File) => {
62
- try {
63
- setBusy(true);
64
- setError(null);
65
- const next = await loadExport(file);
66
- setLoaded(next);
67
- setRunId(next.manifest.runId);
68
- setStatus({
69
- runId: next.manifest.runId,
70
- phase: "local export",
71
- requested: next.manifest.acceptedCount,
72
- accepted: next.manifest.acceptedCount,
73
- rejected: 0,
74
- tasks: [],
75
- });
76
- setRemoved(new Set());
77
- setSelectedTaskId(null);
78
- } catch (cause) {
79
- setError(cause instanceof Error ? cause.message : String(cause));
80
- } finally {
81
- setBusy(false);
82
- }
83
- };
84
-
85
- const selectedTask =
86
- loaded?.tasks.find((task) => task.taskId === selectedTaskId) ?? loaded?.tasks[0];
87
- const toggleRemoved = (taskId: string) =>
88
- setRemoved((current) => {
89
- const next = new Set(current);
90
- if (next.has(taskId)) next.delete(taskId);
91
- else next.add(taskId);
92
- return next;
93
- });
94
-
95
- const downloadClean = async () => {
96
- if (!loaded || !runId) return;
97
- const blob = await buildCleanExport(loaded, removed);
98
- const url = URL.createObjectURL(blob);
99
- const link = document.createElement("a");
100
- link.href = url;
101
- link.download = `selfbench-${runId}-cleaned.tar.gz`;
102
- link.click();
103
- URL.revokeObjectURL(url);
104
- };
105
-
106
- return (
107
- <main className="app-shell">
108
- <header className="topbar">
109
- <div>
110
- <p className="eyebrow">SELFBENCH / EXPORT REVIEW</p>
111
- <h1>Review accepted tasks before publishing.</h1>
112
- </div>
113
- <div className="topbar-actions">
114
- <input
115
- className="token-input"
116
- type="password"
117
- value={token}
118
- onChange={(event) => setToken(event.target.value)}
119
- placeholder="API token (session only)"
120
- aria-label="API token"
121
- />
122
- <input
123
- ref={fileInput}
124
- hidden
125
- type="file"
126
- accept=".gz,.tgz,application/gzip"
127
- onChange={(event) => {
128
- const file = event.target.files?.[0];
129
- if (file) void openFile(file);
130
- }}
131
- />
132
- <button type="button" className="button" onClick={() => fileInput.current?.click()}>
133
- Open gzip
134
- </button>
135
- <button type="button" className="button" onClick={() => void refreshRuns()}>
136
- Refresh runs
137
- </button>
138
- </div>
139
- </header>
140
- {error && <div className="error-banner">{error}</div>}
141
- <section className="workspace">
142
- <aside className="run-list surface">
143
- <div className="section-heading">
144
- <h2>Runs</h2>
145
- <span>{runs.length}</span>
146
- </div>
147
- {runs.length === 0 && <p className="muted">No runs found.</p>}
148
- {runs.map((run) => (
149
- <button
150
- type="button"
151
- className={`run-row ${run.runId === runId ? "selected" : ""}`}
152
- key={run.runId}
153
- onClick={() => void openRun(run.runId)}
154
- >
155
- <strong>{run.runId}</strong>
156
- <span>{run.status}</span>
157
- <small>{new Date(run.startedAt).toLocaleString()}</small>
158
- </button>
159
- ))}
160
- </aside>
161
- <section className="content">
162
- {!loaded && (
163
- <div className="empty surface">
164
- <h2>{busy ? "Loading export…" : "Select a completed run"}</h2>
165
- <p>Choose a run or open a local export gzip to inspect its accepted tasks.</p>
166
- </div>
167
- )}
168
- {loaded && status && (
169
- <>
170
- <div className="summary surface">
171
- <div>
172
- <p className="eyebrow">{loaded.manifest.repository.url}</p>
173
- <h2>{runId}</h2>
174
- <p className="muted">
175
- {status.phase} · {loaded.manifest.acceptedCount} accepted tasks · commit{" "}
176
- {loaded.manifest.repository.commit.slice(0, 12)}
177
- </p>
178
- </div>
179
- <button
180
- type="button"
181
- className="button primary"
182
- onClick={() => void downloadClean()}
183
- >
184
- {removed.size
185
- ? `Download cleaned export (${loaded.tasks.length - removed.size})`
186
- : "Download export copy"}
187
- </button>
188
- </div>
189
- <div className="review-grid">
190
- <div className="task-list surface">
191
- <div className="section-heading">
192
- <h2>Tasks</h2>
193
- <span>{removed.size} marked for removal</span>
194
- </div>
195
- {loaded.tasks.map((task) => (
196
- <button
197
- type="button"
198
- className={`task-row ${task.taskId === selectedTask?.taskId ? "selected" : ""} ${removed.has(task.taskId) ? "removed" : ""}`}
199
- key={task.taskId}
200
- onClick={() => setSelectedTaskId(task.taskId)}
201
- >
202
- <strong>{task.taskId}</strong>
203
- <span>{removed.has(task.taskId) ? "marked for removal" : "keep"}</span>
204
- </button>
205
- ))}
206
- </div>
207
- {selectedTask && (
208
- <TaskPanel
209
- task={selectedTask}
210
- removed={removed.has(selectedTask.taskId)}
211
- onToggle={() => toggleRemoved(selectedTask.taskId)}
212
- />
213
- )}
214
- </div>
215
- </>
216
- )}
217
- </section>
218
- </section>
219
- </main>
220
- );
221
- }
222
-
223
- function TaskPanel({
224
- task,
225
- removed,
226
- onToggle,
227
- }: {
228
- task: ExportTask;
229
- removed: boolean;
230
- onToggle: () => void;
231
- }) {
232
- const definition = parseJson(task.textFiles.get("definition.json"));
233
- return (
234
- <article className="task-detail surface">
235
- <div className="detail-header">
236
- <div>
237
- <p className="eyebrow">TASK</p>
238
- <h2>{task.taskId}</h2>
239
- <p className="muted">
240
- {String(definition?.difficulty ?? "unknown")} · {String(definition?.repo ?? "")}
241
- </p>
242
- </div>
243
- <button
244
- type="button"
245
- className={`button ${removed ? "undo" : "danger"}`}
246
- onClick={onToggle}
247
- >
248
- {removed ? "Keep task" : "Mark for removal"}
249
- </button>
250
- </div>
251
- <DetailBlock title="Prompt">
252
- <pre>
253
- {String(definition?.prompt ?? task.textFiles.get("instruction.md") ?? "No prompt")}
254
- </pre>
255
- </DetailBlock>
256
- <DetailBlock title="Task definition">
257
- <pre>{task.textFiles.get("definition.json") ?? "Missing definition.json"}</pre>
258
- </DetailBlock>
259
- <DetailBlock title="Gold patch">
260
- <PatchBlock patch={task.textFiles.get("solution/gold.patch")} />
261
- </DetailBlock>
262
- <DetailBlock title="Held-out test patch">
263
- <PatchBlock patch={task.textFiles.get("tests/test.patch")} />
264
- </DetailBlock>
265
- </article>
266
- );
267
- }
268
-
269
- function PatchBlock({ patch }: { patch: string | undefined }) {
270
- const files = React.useMemo(
271
- () => (patch ? parsePatchFiles(patch).flatMap((parsed) => parsed.files) : []),
272
- [patch],
273
- );
274
- if (!patch) return <pre>Missing patch</pre>;
275
- if (!files.length) return <pre>{patch}</pre>;
276
- const options = {
277
- themeType: window.matchMedia("(prefers-color-scheme: dark)").matches
278
- ? ("dark" as const)
279
- : ("light" as const),
280
- diffStyle: window.matchMedia("(max-width: 900px)").matches
281
- ? ("unified" as const)
282
- : ("split" as const),
283
- diffIndicators: "bars" as const,
284
- overflow: "scroll" as const,
285
- stickyHeader: true,
286
- };
287
- return (
288
- <DiffErrorBoundary fallback={patch}>
289
- <div className="patch-files">
290
- {files.map((file) => (
291
- <FileDiff
292
- key={`${file.prevName ?? ""}:${file.name}`}
293
- fileDiff={file}
294
- disableWorkerPool
295
- options={options}
296
- />
297
- ))}
298
- </div>
299
- </DiffErrorBoundary>
300
- );
301
- }
302
-
303
- class DiffErrorBoundary extends React.Component<
304
- React.PropsWithChildren<{ fallback: string }>,
305
- { failed: boolean }
306
- > {
307
- state = { failed: false };
308
-
309
- static getDerivedStateFromError() {
310
- return { failed: true };
311
- }
312
-
313
- componentDidCatch(error: unknown) {
314
- console.error("Pierre diff renderer failed", error);
315
- }
316
-
317
- render() {
318
- return this.state.failed ? <pre>{this.props.fallback}</pre> : this.props.children;
319
- }
320
- }
321
-
322
- function DetailBlock({ title, children }: { title: string; children: React.ReactNode }) {
323
- return (
324
- <section className="detail-block">
325
- <h3>{title}</h3>
326
- {children}
327
- </section>
328
- );
329
- }
330
-
331
- function parseJson(value: string | undefined): Record<string, unknown> | null {
332
- if (!value) return null;
333
- try {
334
- return JSON.parse(value) as Record<string, unknown>;
335
- } catch {
336
- return null;
337
- }
338
- }
@@ -1,57 +0,0 @@
1
- import { describe, expect, test } from "bun:test";
2
- import { buildCleanExport, loadExport } from "./export-loader";
3
- import type { LoadedExport } from "./types";
4
-
5
- describe("export review bundles", () => {
6
- test("round-trips nested task archives and removes marked tasks", async () => {
7
- const loaded: LoadedExport = {
8
- manifest: {
9
- schemaVersion: 1,
10
- runId: "run-123",
11
- candidateCounts: { easy: 2, medium: 0, hard: 0 },
12
- repository: { url: "https://github.com/example/repo", commit: "a".repeat(40) },
13
- version: { schema: 1 },
14
- acceptedCount: 2,
15
- tasks: [
16
- { taskId: "task-a", sha256: "a".repeat(64) },
17
- { taskId: "task-b", sha256: "b".repeat(64) },
18
- ],
19
- },
20
- tasks: [],
21
- taskArchives: new Map([
22
- ["task-a", await taskArchive("task-a")],
23
- ["task-b", await taskArchive("task-b")],
24
- ]),
25
- };
26
- loaded.tasks = [
27
- { taskId: "task-a", files: new Map(), textFiles: new Map() },
28
- { taskId: "task-b", files: new Map(), textFiles: new Map() },
29
- ];
30
-
31
- const cleaned = await buildCleanExport(loaded, new Set(["task-b"]));
32
- const result = await loadExport(cleaned);
33
-
34
- expect(result.manifest.acceptedCount).toBe(1);
35
- expect(result.manifest.tasks.map((task) => task.taskId)).toEqual(["task-a"]);
36
- expect(result.tasks[0]?.textFiles.get("definition.json")).toBe('{"taskId":"task-a"}');
37
- });
38
- });
39
-
40
- async function taskArchive(taskId: string): Promise<Uint8Array> {
41
- const data = new TextEncoder().encode(JSON.stringify({ taskId }));
42
- const header = new Uint8Array(512);
43
- write(header, 0, "harbor-task/definition.json");
44
- write(header, 124, data.length.toString(8).padStart(11, "0"));
45
- header[156] = 48;
46
- const tar = new Uint8Array(512 + Math.ceil(data.length / 512) * 512 + 1024);
47
- tar.set(header);
48
- tar.set(data, 512);
49
- const compressed = await new Response(
50
- new Blob([tar.buffer]).stream().pipeThrough(new CompressionStream("gzip")),
51
- ).arrayBuffer();
52
- return new Uint8Array(compressed);
53
- }
54
-
55
- function write(target: Uint8Array, offset: number, value: string): void {
56
- target.set(new TextEncoder().encode(value), offset);
57
- }