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
@@ -1,144 +0,0 @@
1
- import { readdir, readFile, rename } from "node:fs/promises";
2
- import { join } from "node:path";
3
-
4
- export interface HarborVerifierOutput {
5
- readonly combined?: string;
6
- readonly stderr?: string;
7
- }
8
-
9
- export interface HarborJobResult {
10
- readonly job: unknown;
11
- readonly trial: unknown;
12
- readonly verifier?: HarborVerifierOutput;
13
- }
14
-
15
- const infrastructurePatterns = [
16
- /unknown flag: --project-name/i,
17
- /cannot connect to the docker daemon/i,
18
- /error during connect/i,
19
- /connection refused/i,
20
- /modal.*(?:unavailable|timed out|timeout)/i,
21
- /image build for im-[a-z0-9]+ failed/i,
22
- /all predefined address pools have been fully subnetted/i,
23
- /mounts denied/i,
24
- /network-policy[\s\S]*could not process rule/i,
25
- ];
26
-
27
- class IncompleteHarborJobError extends Error {}
28
-
29
- export function harborInfrastructureError(trial: unknown): string | undefined {
30
- if (!isRecord(trial) || !isRecord(trial.exception_info)) {
31
- return undefined;
32
- }
33
- const message = trial.exception_info.exception_message;
34
- const type = trial.exception_info.exception_type;
35
- if (
36
- typeof message !== "string" ||
37
- (type !== "AuthError" && !infrastructurePatterns.some((pattern) => pattern.test(message)))
38
- ) {
39
- return undefined;
40
- }
41
- return `${typeof type === "string" ? type : "HarborError"}: ${message}`;
42
- }
43
-
44
- export async function readHarborJobResult(
45
- jobsDirectory: string,
46
- jobName: string,
47
- ): Promise<HarborJobResult> {
48
- const jobDirectory = join(jobsDirectory, jobName);
49
- const job = JSON.parse(await readFile(join(jobDirectory, "result.json"), "utf8")) as unknown;
50
- const entries = await readdir(jobDirectory, { withFileTypes: true });
51
- const trials: Array<{ directory: string; result: unknown }> = [];
52
- for (const entry of entries) {
53
- if (!entry.isDirectory()) {
54
- continue;
55
- }
56
- const directory = join(jobDirectory, entry.name);
57
- const raw = await readFile(join(directory, "result.json"), "utf8").catch((error: unknown) =>
58
- isNotFound(error) ? undefined : Promise.reject(error),
59
- );
60
- if (raw) {
61
- trials.push({ directory, result: JSON.parse(raw) as unknown });
62
- }
63
- }
64
- const aggregateTrials =
65
- isRecord(job) && Array.isArray(job.trial_results) ? job.trial_results : [];
66
- const [onlyTrial] = trials;
67
- if (onlyTrial && trials.length === 1) {
68
- return {
69
- job,
70
- trial: onlyTrial.result,
71
- ...(await readVerifierOutput(onlyTrial.directory)),
72
- };
73
- }
74
- if (aggregateTrials.length === 1) {
75
- return { job, trial: aggregateTrials[0] };
76
- }
77
- if (trials.length === 0 && isRecord(job) && job.finished_at === null) {
78
- throw new IncompleteHarborJobError(`Harbor job ${jobName} has not finished`);
79
- }
80
- throw new Error(`expected one Harbor trial result in ${jobDirectory}, found ${trials.length}`);
81
- }
82
-
83
- export async function tryReadHarborJobResult(
84
- jobsDirectory: string,
85
- jobName: string,
86
- ): Promise<HarborJobResult | undefined> {
87
- try {
88
- return await readHarborJobResult(jobsDirectory, jobName);
89
- } catch (error) {
90
- if (isNotFound(error) || error instanceof IncompleteHarborJobError) {
91
- return undefined;
92
- }
93
- throw error;
94
- }
95
- }
96
-
97
- export async function archiveIncompleteHarborJob(
98
- jobsDirectory: string,
99
- jobName: string,
100
- ): Promise<string | undefined> {
101
- const source = join(jobsDirectory, jobName);
102
- const destination = `${source}.incomplete-${Date.now()}`;
103
- try {
104
- await rename(source, destination);
105
- return destination;
106
- } catch (error) {
107
- if (isNotFound(error)) {
108
- return undefined;
109
- }
110
- throw error;
111
- }
112
- }
113
-
114
- async function readVerifierOutput(
115
- trialDirectory: string,
116
- ): Promise<{ readonly verifier?: HarborVerifierOutput }> {
117
- const verifierDirectory = join(trialDirectory, "verifier");
118
- const [combined, stderr] = await Promise.all([
119
- readOptionalText(join(verifierDirectory, "test-stdout.txt")),
120
- readOptionalText(join(verifierDirectory, "test-stderr.txt")),
121
- ]);
122
- return combined || stderr
123
- ? { verifier: { ...(combined ? { combined } : {}), ...(stderr ? { stderr } : {}) } }
124
- : {};
125
- }
126
-
127
- async function readOptionalText(path: string): Promise<string | undefined> {
128
- return await readFile(path, "utf8").catch((error: unknown) =>
129
- isNotFound(error) ? undefined : Promise.reject(error),
130
- );
131
- }
132
-
133
- function isRecord(value: unknown): value is Record<string, unknown> {
134
- return typeof value === "object" && value !== null && !Array.isArray(value);
135
- }
136
-
137
- function isNotFound(error: unknown): boolean {
138
- return (
139
- typeof error === "object" &&
140
- error !== null &&
141
- "code" in error &&
142
- (error as { code?: unknown }).code === "ENOENT"
143
- );
144
- }
@@ -1,533 +0,0 @@
1
- import { chmod, cp, mkdir, readFile, rm, writeFile } from "node:fs/promises";
2
- import { join, posix, resolve, sep } from "node:path";
3
- import { type TaskDefinition, taskDefinitionSchema } from "./contracts.js";
4
- import { sha256 } from "./hash.js";
5
- import { runCommand } from "./process.js";
6
- import { patchPaths } from "./repair.js";
7
-
8
- const HARBOR_SCHEMA_VERSION = "1.4";
9
- const COMPILER_REVISION = 24;
10
-
11
- export interface AuthoredTaskFiles {
12
- readonly definition: TaskDefinition;
13
- readonly testPatch: string;
14
- readonly goldPatch: string;
15
- }
16
-
17
- export async function loadAuthoredTask(directory: string): Promise<AuthoredTaskFiles> {
18
- const definition = taskDefinitionSchema.parse(
19
- JSON.parse(await readFile(join(directory, "definition.json"), "utf8")),
20
- );
21
- assertSafeTaskPaths(definition);
22
- const [testPatch, goldPatch] = await Promise.all([
23
- readFile(join(directory, "test.patch"), "utf8"),
24
- readFile(join(directory, "gold.patch"), "utf8"),
25
- ]);
26
- if (!testPatch.startsWith("diff --git ")) {
27
- throw new Error("test.patch is not a Git patch");
28
- }
29
- assertSafePatchPaths(testPatch);
30
- if (!goldPatch.startsWith("diff --git ")) {
31
- throw new Error("gold.patch is not a Git patch");
32
- }
33
- return { definition, testPatch, goldPatch };
34
- }
35
-
36
- export async function compileHarborTask(
37
- authoredDirectory: string,
38
- repositoryDirectory: string,
39
- outputDirectory: string,
40
- ): Promise<void> {
41
- const task = await loadAuthoredTask(authoredDirectory);
42
- const dependencySetupPatch = dependencyManifestPatch(task.goldPatch);
43
- const preinstallGoldDependencies = dependencySetupPatch.length > 0;
44
- await runCommand("git", [
45
- "-C",
46
- repositoryDirectory,
47
- "cat-file",
48
- "-e",
49
- `${task.definition.baseCommit}^{commit}`,
50
- ]);
51
- await rm(outputDirectory, { recursive: true, force: true });
52
- const environment = join(outputDirectory, "environment");
53
- const solution = join(outputDirectory, "solution");
54
- const tests = join(outputDirectory, "tests");
55
- await Promise.all([
56
- mkdir(environment, { recursive: true }),
57
- mkdir(solution, { recursive: true }),
58
- mkdir(tests, { recursive: true }),
59
- ]);
60
-
61
- const snapshot = join(outputDirectory, ".repo.tar.gz");
62
- await runCommand("git", [
63
- "-C",
64
- repositoryDirectory,
65
- "archive",
66
- "--format=tar.gz",
67
- `--output=${snapshot}`,
68
- task.definition.baseCommit,
69
- ]);
70
- await Promise.all([
71
- cp(snapshot, join(environment, "repo.tar.gz")),
72
- cp(snapshot, join(tests, "repo.tar.gz")),
73
- writeFile(
74
- join(outputDirectory, "definition.json"),
75
- `${JSON.stringify(task.definition, null, 2)}\n`,
76
- ),
77
- writeFile(join(outputDirectory, "instruction.md"), `${task.definition.prompt.trim()}\n`),
78
- writeFile(join(solution, "gold.patch"), task.goldPatch),
79
- writeFile(join(solution, "solve.sh"), solutionScript()),
80
- writeFile(join(tests, "test.patch"), task.testPatch),
81
- writeFile(join(tests, "test.sh"), testScript(task.definition, task.testPatch)),
82
- writeFile(join(environment, "Dockerfile"), agentDockerfile(task.definition)),
83
- writeFile(
84
- join(tests, "Dockerfile"),
85
- verifierDockerfile(task.definition, preinstallGoldDependencies),
86
- ),
87
- writeFile(join(outputDirectory, "task.toml"), taskToml(task.definition)),
88
- ...(preinstallGoldDependencies
89
- ? [writeFile(join(tests, "dependency-setup.patch"), dependencySetupPatch)]
90
- : []),
91
- ]);
92
- await rm(snapshot);
93
- await Promise.all([
94
- chmod(join(solution, "solve.sh"), 0o755),
95
- chmod(join(tests, "test.sh"), 0o755),
96
- ]);
97
- await writeFile(
98
- join(outputDirectory, ".selfbench-manifest.json"),
99
- `${JSON.stringify(
100
- {
101
- generator: "selfbench",
102
- harborSchemaVersion: HARBOR_SCHEMA_VERSION,
103
- compilerRevision: COMPILER_REVISION,
104
- taskId: task.definition.taskId,
105
- difficulty: task.definition.difficulty,
106
- definitionSha256: sha256(JSON.stringify(task.definition)),
107
- testPatchSha256: sha256(task.testPatch),
108
- goldPatchSha256: sha256(task.goldPatch),
109
- },
110
- null,
111
- 2,
112
- )}\n`,
113
- );
114
- }
115
-
116
- export async function refreshHarborTask(
117
- outputDirectory: string,
118
- definition: TaskDefinition,
119
- ): Promise<void> {
120
- const manifestPath = join(outputDirectory, ".selfbench-manifest.json");
121
- const manifest = JSON.parse(await readFile(manifestPath, "utf8")) as Record<string, unknown>;
122
- if (manifest.taskId !== definition.taskId) {
123
- throw new Error(`bundle task ${String(manifest.taskId)} does not match ${definition.taskId}`);
124
- }
125
- const [goldPatch, testPatch] = await Promise.all([
126
- readFile(join(outputDirectory, "solution/gold.patch"), "utf8"),
127
- readFile(join(outputDirectory, "tests/test.patch"), "utf8"),
128
- ]);
129
- assertSafePatchPaths(testPatch);
130
- const dependencySetupPatch = dependencyManifestPatch(goldPatch);
131
- const preinstallGoldDependencies = dependencySetupPatch.length > 0;
132
- await writeFile(join(outputDirectory, "tests/test.sh"), testScript(definition, testPatch));
133
- await Promise.all([
134
- writeFile(join(outputDirectory, "definition.json"), `${JSON.stringify(definition, null, 2)}\n`),
135
- writeFile(join(outputDirectory, "task.toml"), taskToml(definition)),
136
- writeFile(join(outputDirectory, "environment/Dockerfile"), agentDockerfile(definition)),
137
- writeFile(
138
- join(outputDirectory, "tests/Dockerfile"),
139
- verifierDockerfile(definition, preinstallGoldDependencies),
140
- ),
141
- preinstallGoldDependencies
142
- ? writeFile(join(outputDirectory, "tests/dependency-setup.patch"), dependencySetupPatch)
143
- : rm(join(outputDirectory, "tests/dependency-setup.patch"), { force: true }),
144
- chmod(join(outputDirectory, "tests/test.sh"), 0o755),
145
- ]);
146
- await writeFile(
147
- manifestPath,
148
- `${JSON.stringify(
149
- {
150
- ...manifest,
151
- compilerRevision: COMPILER_REVISION,
152
- difficulty: definition.difficulty,
153
- definitionSha256: sha256(JSON.stringify(definition)),
154
- testPatchSha256: sha256(testPatch),
155
- goldPatchSha256: sha256(goldPatch),
156
- },
157
- null,
158
- 2,
159
- )}\n`,
160
- );
161
- }
162
-
163
- function taskToml(task: TaskDefinition): string {
164
- const metadata = {
165
- selfbench_task_id: task.taskId,
166
- difficulty: task.difficulty,
167
- repo: task.repo,
168
- base_commit: task.baseCommit,
169
- workdir: task.workdir,
170
- source_pr: task.sourcePr,
171
- compiler_revision: COMPILER_REVISION,
172
- };
173
- return `${[
174
- `schema_version = ${tomlString(HARBOR_SCHEMA_VERSION)}`,
175
- 'artifacts = ["/opt/selfbench/agent.patch"]',
176
- "",
177
- "[task]",
178
- `name = ${tomlString(`selfbench/${task.taskId}`)}`,
179
- 'version = "1.0.0"',
180
- `description = ${tomlString(`Reproduce ${task.taskId} from its authentic engineer request.`)}`,
181
- `keywords = ["software-engineering", "private-swe", "selfbench", ${tomlString(task.difficulty)}]`,
182
- "",
183
- "[metadata]",
184
- ...Object.entries(metadata).map(([key, value]) => `${key} = ${tomlValue(value)}`),
185
- "",
186
- "[agent]",
187
- `timeout_sec = ${task.timeouts.agentSeconds}.0`,
188
- 'user = "agent"',
189
- 'network_mode = "allowlist"',
190
- 'allowed_hosts = ["chatgpt.com", "*.chatgpt.com", "openai.com", "*.openai.com"]',
191
- "",
192
- "[verifier]",
193
- `timeout_sec = ${task.timeouts.setupSeconds + task.timeouts.testsSeconds}.0`,
194
- 'user = "root"',
195
- 'environment_mode = "separate"',
196
- 'network_mode = "public"',
197
- "",
198
- "[[verifier.collect]]",
199
- 'service = "main"',
200
- 'user = "root"',
201
- `timeout_sec = ${Math.min(task.timeouts.testsSeconds, 300)}.0`,
202
- 'command = "git --git-dir=/opt/selfbench/base.git --work-tree=/app add -A && git --git-dir=/opt/selfbench/base.git --work-tree=/app diff --cached --binary HEAD > /opt/selfbench/agent.patch"',
203
- "",
204
- "[environment]",
205
- 'network_mode = "public"',
206
- `build_timeout_sec = ${task.timeouts.setupSeconds + 600}.0`,
207
- `cpus = ${task.resources.cpus}`,
208
- `memory_mb = ${task.resources.memoryMb}`,
209
- `storage_mb = ${task.resources.storageMb}`,
210
- "",
211
- "[verifier.environment]",
212
- 'network_mode = "public"',
213
- `build_timeout_sec = ${task.timeouts.setupSeconds + 600}.0`,
214
- `cpus = ${task.resources.cpus}`,
215
- `memory_mb = ${task.resources.memoryMb}`,
216
- `storage_mb = ${task.resources.storageMb}`,
217
- ].join("\n")}\n`;
218
- }
219
-
220
- function agentDockerfile(task: TaskDefinition): string {
221
- return `${toolchainDockerfile(task.toolchains)}
222
- RUN useradd --create-home --shell /bin/bash agent
223
- ${repositoryDockerfile(task)}
224
- RUN git -C /app reset --hard -q HEAD \\
225
- && git -C /app clean -fdq \\
226
- && mkdir -p /opt/selfbench \\
227
- && cp -a /app/.git /opt/selfbench/base.git \\
228
- && chown -R agent:agent /app /home/agent /opt/uv-cache \\
229
- && chown -R root:root /opt/selfbench \\
230
- && chmod 700 /opt/selfbench \\
231
- && mkdir -p /home/agent/.cache/uv \\
232
- && chown -R agent:agent /home/agent/.cache
233
- ENV UV_CACHE_DIR=/home/agent/.cache/uv \\
234
- UV_NO_BUILD_ISOLATION=1
235
- USER agent
236
- WORKDIR /app
237
- `;
238
- }
239
-
240
- function verifierDockerfile(task: TaskDefinition, preinstallGoldDependencies: boolean): string {
241
- return `${toolchainDockerfile(task.toolchains)}
242
- ${repositoryDockerfile(task)}
243
- ${preinstallGoldDependencies ? goldDependencySetupLayer(task) : ""}
244
- RUN useradd --create-home --shell /bin/bash verifier \\
245
- && chown -R verifier:verifier /app /opt/uv-cache \\
246
- && mkdir -p /opt/selfbench \\
247
- && chmod 700 /opt/selfbench \\
248
- && mkdir -p /home/verifier/.cache/uv \\
249
- && chown -R verifier:verifier /home/verifier/.cache
250
- ENV UV_CACHE_DIR=/home/verifier/.cache/uv \\
251
- UV_NO_BUILD_ISOLATION=1
252
- COPY test.patch test.sh /tests/
253
- RUN chmod 700 /tests && chmod 600 /tests/test.patch && chmod +x /tests/test.sh
254
- WORKDIR /app
255
- `;
256
- }
257
-
258
- function goldDependencySetupLayer(task: TaskDefinition): string {
259
- return `COPY dependency-setup.patch /tmp/selfbench-dependency-setup.patch
260
- RUN git -C /app apply --binary --whitespace=nowarn /tmp/selfbench-dependency-setup.patch \\
261
- && cd ${shellQuote(`/app/${task.workdir}`)} \\
262
- && bash -lc ${shellQuote(task.setupCommand)} \\
263
- && git -C /app reset --hard -q HEAD \\
264
- && git -C /app clean -fdq \\
265
- && rm /tmp/selfbench-dependency-setup.patch
266
- `;
267
- }
268
-
269
- export function goldPatchChangesDependencyManifests(patch: string): boolean {
270
- return dependencyManifestPatch(patch).length > 0;
271
- }
272
-
273
- export function dependencyManifestPatch(patch: string): string {
274
- const sections = patch.split(/(?=^diff --git )/m);
275
- const selected = sections.filter((section) => {
276
- const header = section.split("\n", 1)[0] ?? "";
277
- const match = /^diff --git a\/(.+) b\/(.+)$/.exec(header);
278
- return match?.[2] ? isDependencyManifest(match[2]) : false;
279
- });
280
- return selected.length > 0 ? `${selected.join("").trimEnd()}\n` : "";
281
- }
282
-
283
- function isDependencyManifest(path: string): boolean {
284
- const name = posix.basename(path);
285
- return (
286
- /^(?:package(?:-lock)?\.json|npm-shrinkwrap\.json|yarn\.lock|pnpm-lock\.yaml|bun\.lockb?|deno\.lock)$/.test(
287
- name,
288
- ) ||
289
- /^(?:pyproject\.toml|uv\.lock|poetry\.lock|Pipfile(?:\.lock)?|requirements[^/]*\.txt)$/.test(
290
- name,
291
- ) ||
292
- /^(?:go\.(?:mod|sum)|Cargo\.(?:toml|lock))$/.test(name)
293
- );
294
- }
295
-
296
- function toolchainDockerfile(toolchains: readonly string[]): string {
297
- const layers: Record<string, string> = {
298
- uv: "RUN curl -LsSf https://astral.sh/uv/install.sh | env UV_INSTALL_DIR=/usr/local/bin UV_NO_MODIFY_PATH=1 sh",
299
- python:
300
- "RUN uv python install 3.11 3.12 3.13 && ln -sf /usr/local/bin/python3.12 /usr/local/bin/python3 && ln -sf /usr/local/bin/python3.12 /usr/local/bin/python",
301
- node: `ENV PLAYWRIGHT_BROWSERS_PATH=/opt/playwright
302
- RUN mkdir -p "$PLAYWRIGHT_BROWSERS_PATH" && chmod 755 "$PLAYWRIGHT_BROWSERS_PATH" \\
303
- && arch="$(dpkg --print-architecture)" && case "$arch" in arm64) node_arch=arm64 ;; amd64) node_arch=x64 ;; *) exit 1 ;; esac \\
304
- && curl -fsSL "https://nodejs.org/dist/v22.14.0/node-v22.14.0-linux-\${node_arch}.tar.xz" | tar -C /usr/local --strip-components=1 -xJ \\
305
- && mkdir -p /opt/corepack && chmod 755 /opt/corepack \\
306
- && corepack enable`,
307
- bun: "RUN npm install --global bun@1.3.14",
308
- // biome-ignore lint/suspicious/noTemplateCurlyInString: the output is a shell variable.
309
- go: `RUN arch="$(dpkg --print-architecture)" && curl -fsSL "https://go.dev/dl/go1.25.0.linux-${"${arch}"}.tar.gz" | tar -C /usr/local -xz`,
310
- rust: "RUN curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | env RUSTUP_HOME=/usr/local/rustup CARGO_HOME=/usr/local/cargo sh -s -- -y --no-modify-path --profile minimal --default-toolchain 1.90.0",
311
- };
312
- const selected = new Set(toolchains);
313
- if (selected.has("python")) {
314
- selected.add("uv");
315
- }
316
- if (selected.has("bun")) {
317
- selected.add("node");
318
- }
319
- const order = ["uv", "python", "node", "bun", "go", "rust"];
320
- return `FROM ubuntu:24.04
321
- ENV DEBIAN_FRONTEND=noninteractive \\
322
- UV_LINK_MODE=copy \\
323
- UV_CACHE_DIR=/opt/uv-cache \\
324
- UV_PYTHON_INSTALL_DIR=/usr/local/share/uv/python \\
325
- UV_PYTHON_BIN_DIR=/usr/local/bin \\
326
- RUSTUP_HOME=/usr/local/rustup \\
327
- CARGO_HOME=/usr/local/cargo \\
328
- COREPACK_HOME=/opt/corepack \\
329
- PATH=/usr/local/go/bin:/usr/local/cargo/bin:/usr/local/bin:/usr/local/sbin:/usr/bin:/usr/sbin:/bin:/sbin
330
- RUN apt-get update && apt-get install -y --no-install-recommends \\
331
- bash build-essential ca-certificates curl git jq passwd pkg-config procps unzip xz-utils \\
332
- && rm -rf /var/lib/apt/lists/*
333
- ${order
334
- .filter((name) => selected.has(name))
335
- .map((name) => layers[name])
336
- .filter(Boolean)
337
- .join("\n")}`;
338
- }
339
-
340
- function repositoryDockerfile(task: TaskDefinition): string {
341
- const pythonBuildDependencies = task.toolchains.includes("python")
342
- ? ` \\
343
- && find /app -path '*/.venv/bin/python' -exec uv pip install --python '{}' 'setuptools>=70' wheel ';'`
344
- : "";
345
- return `COPY repo.tar.gz /tmp/repo.tar.gz
346
- RUN mkdir -p /app && tar -xzf /tmp/repo.tar.gz -C /app && rm /tmp/repo.tar.gz \\
347
- && git -C /app init -q \\
348
- && git -C /app config user.email selfbench@local \\
349
- && git -C /app config user.name selfbench \\
350
- && git -C /app add -A \\
351
- && git -C /app commit -qm base
352
- RUN mkdir -p /opt/uv-cache && chmod 777 /opt/uv-cache \\
353
- && cd ${shellQuote(`/app/${task.workdir}`)} \\
354
- && bash -lc ${shellQuote(task.setupCommand)}${pythonBuildDependencies} \\
355
- && chmod -R a+rwX /opt/uv-cache`;
356
- }
357
-
358
- function solutionScript(): string {
359
- return `#!/bin/bash
360
- set -euo pipefail
361
- git -C /app apply --binary --whitespace=nowarn /solution/gold.patch
362
- `;
363
- }
364
-
365
- function testScript(task: TaskDefinition, testPatch: string): string {
366
- const repositoryTestPaths = [
367
- ...new Set([
368
- ...task.testPaths.map((path) => repositoryRelativePath(task, path)),
369
- ...patchPaths(testPatch),
370
- ]),
371
- ].sort();
372
- const exclusions = repositoryTestPaths
373
- .flatMap((path) => [
374
- `--exclude=${shellQuote(path.replace(/\/$/, ""))}`,
375
- `--exclude=${shellQuote(`${path.replace(/\/$/, "")}/*`)}`,
376
- ])
377
- .join(" ");
378
- const protectedPaths = repositoryTestPaths.map(shellQuote).join(" ");
379
- const protectedAbsolute = repositoryTestPaths.map((path) => shellQuote(`/app/${path}`)).join(" ");
380
- const f2p = taskCommand(task, task.failToPass);
381
- const p2p = task.passToPass.length > 0 ? taskCommand(task, task.passToPass) : "true";
382
- return `#!/bin/bash
383
- set -uo pipefail
384
- mkdir -p /logs/verifier
385
- patch_applied=1
386
- fail_to_pass=0
387
- pass_to_pass=0
388
- deterministic=0
389
- setup_completed=0
390
- fail_to_pass_exit_code=-1
391
- fail_to_pass_repeat_exit_code=-1
392
- pass_to_pass_exit_code=-1
393
- verifier_cache=""
394
-
395
- kill_verifier_processes() { pkill -KILL -u "$(id -u verifier)" 2>/dev/null || true; }
396
- # Some toolchains fetch dependencies at test runtime (e.g. Next.js e2e installs),
397
- # so a single registry connection reset must not be misread as a dead test. Retry
398
- # only infrastructure-style failures with backoff; real assertion failures fail fast.
399
- run_verifier_command() {
400
- local logfile
401
- logfile="$(mktemp /tmp/selfbench-verifier-command-XXXXXX.log)"
402
- local attempt=1
403
- local status=1
404
- while [ "$attempt" -le 3 ]; do
405
- : > "$logfile"
406
- runuser -u verifier -- env PATH="/usr/local/go/bin:/usr/local/cargo/bin:/usr/local/bin:/usr/local/sbin:/usr/bin:/usr/sbin:/bin:/sbin" UV_CACHE_DIR="$verifier_cache" UV_NO_BUILD_ISOLATION=1 bash -lc "$1" >"$logfile" 2>&1
407
- status=$?
408
- if [ "$status" -eq 0 ]; then
409
- break
410
- fi
411
- if [ "$attempt" -lt 3 ] && grep -qE 'ECONNRESET|ETIMEDOUT|ESOCKETTIMEDOUT|ENOTFOUND|EAI_AGAIN|META_FETCH_FAIL|FetchError|EPIPE|EPERM|registry\\.npmjs' "$logfile"; then
412
- sleep "$((10 * attempt))"
413
- attempt=$((attempt + 1))
414
- continue
415
- fi
416
- break
417
- done
418
- cat "$logfile"
419
- rm -f "$logfile"
420
- kill_verifier_processes
421
- return "$status"
422
- }
423
- protect_held_out_path() {
424
- local path="$1"
425
- chown -R root:root -- "$path"
426
- chmod -R a-w,go+rX -- "$path"
427
- }
428
-
429
- if [ ! -f /opt/selfbench/agent.patch ]; then
430
- patch_applied=0
431
- elif [ -s /opt/selfbench/agent.patch ]; then
432
- git -C /app apply --binary --whitespace=nowarn ${exclusions} /opt/selfbench/agent.patch || patch_applied=0
433
- fi
434
-
435
- if [ "$patch_applied" -eq 1 ]; then setup_completed=1; fi
436
-
437
- if [ "$patch_applied" -eq 1 ] && [ "$setup_completed" -eq 1 ]; then
438
- kill_verifier_processes
439
- for protected_path in ${protectedPaths}; do
440
- git -C /app restore --source=HEAD --staged --worktree -- "$protected_path" 2>/dev/null || true
441
- git -C /app clean -fd -- "$protected_path" >/dev/null 2>&1 || true
442
- done
443
- git -C /app apply --binary --whitespace=nowarn /tests/test.patch || patch_applied=0
444
- if [ "$patch_applied" -eq 1 ]; then
445
- for protected_path in ${protectedAbsolute}; do protect_held_out_path "$protected_path"; done
446
- fi
447
- rm -f /tests/test.patch
448
- fi
449
-
450
- if [ "$patch_applied" -eq 1 ] && [ "$setup_completed" -eq 1 ]; then
451
- cd ${shellQuote(`/app/${task.workdir}`)}
452
- verifier_cache="$(mktemp -d /tmp/selfbench-verifier-uv-XXXXXX)"
453
- cp -a /opt/uv-cache/. "$verifier_cache"/
454
- chown -R verifier:verifier "$verifier_cache"
455
- if run_verifier_command ${shellQuote(f2p)}; then
456
- fail_to_pass_exit_code=0
457
- fail_to_pass=1
458
- if run_verifier_command ${shellQuote(f2p)}; then
459
- fail_to_pass_repeat_exit_code=0
460
- deterministic=1
461
- else
462
- fail_to_pass_repeat_exit_code=$?
463
- fi
464
- else
465
- fail_to_pass_exit_code=$?
466
- fi
467
- if run_verifier_command ${shellQuote(p2p)}; then
468
- pass_to_pass_exit_code=0
469
- pass_to_pass=1
470
- else
471
- pass_to_pass_exit_code=$?
472
- fi
473
- rm -rf "$verifier_cache"
474
- fi
475
-
476
- reward=0
477
- if [ "$patch_applied" -eq 1 ] && [ "$fail_to_pass" -eq 1 ] && [ "$pass_to_pass" -eq 1 ] && [ "$deterministic" -eq 1 ]; then reward=1; fi
478
- cat > /logs/verifier/reward.json <<EOF
479
- {"reward": $reward, "patch_applied": $patch_applied, "fail_to_pass": $fail_to_pass, "pass_to_pass": $pass_to_pass, "deterministic": $deterministic, "setup_completed": $setup_completed, "fail_to_pass_exit_code": $fail_to_pass_exit_code, "fail_to_pass_repeat_exit_code": $fail_to_pass_repeat_exit_code, "pass_to_pass_exit_code": $pass_to_pass_exit_code}
480
- EOF
481
- exit 0
482
- `;
483
- }
484
-
485
- function taskCommand(task: TaskDefinition, tests: readonly string[]): string {
486
- return task.testCommand.replaceAll("{tests}", tests.map(shellQuote).join(" "));
487
- }
488
-
489
- function assertSafeTaskPaths(task: TaskDefinition): void {
490
- for (const path of [
491
- task.workdir,
492
- ...task.testPaths.map((value) => posix.join(task.workdir, value)),
493
- ]) {
494
- const resolved = resolve("/repo", path);
495
- if (resolved !== "/repo" && !resolved.startsWith(`/repo${sep}`)) {
496
- throw new Error(`task path escapes repository: ${path}`);
497
- }
498
- }
499
- }
500
-
501
- function assertSafePatchPaths(patch: string): void {
502
- const paths = patchPaths(patch);
503
- if (paths.length === 0) {
504
- throw new Error("test.patch changes no files");
505
- }
506
- for (const path of paths) {
507
- const resolved = resolve("/repo", path);
508
- if (
509
- resolved === "/repo" ||
510
- !resolved.startsWith(`/repo${sep}`) ||
511
- resolved.startsWith(`/repo${sep}.git${sep}`) ||
512
- resolved === `/repo${sep}.git`
513
- ) {
514
- throw new Error(`test patch path escapes repository: ${path}`);
515
- }
516
- }
517
- }
518
-
519
- function repositoryRelativePath(task: TaskDefinition, path: string): string {
520
- return posix.normalize(posix.join(task.workdir, path)).replace(/^\.\//, "");
521
- }
522
-
523
- function shellQuote(value: string): string {
524
- return `'${value.replaceAll("'", `'"'"'`)}'`;
525
- }
526
-
527
- function tomlString(value: string): string {
528
- return JSON.stringify(value);
529
- }
530
-
531
- function tomlValue(value: string | number): string {
532
- return typeof value === "string" ? tomlString(value) : String(value);
533
- }
package/src/hash.ts DELETED
@@ -1,5 +0,0 @@
1
- import { createHash } from "node:crypto";
2
-
3
- export function sha256(value: Uint8Array | string): string {
4
- return createHash("sha256").update(value).digest("hex");
5
- }
package/src/modal-auth.ts DELETED
@@ -1,11 +0,0 @@
1
- const MODAL_CREDENTIAL_KEYS = ["MODAL_TOKEN_ID", "MODAL_TOKEN_SECRET"] as const;
2
-
3
- export function removeEmptyModalCredentialOverrides(
4
- environment: NodeJS.ProcessEnv = process.env,
5
- ): void {
6
- for (const key of MODAL_CREDENTIAL_KEYS) {
7
- if (environment[key]?.trim() === "") {
8
- delete environment[key];
9
- }
10
- }
11
- }