@apralabs/apra-fleet 0.3.5 → 0.4.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (571) hide show
  1. package/README.md +245 -257
  2. package/dist/agents/backlog-groomer.md +287 -0
  3. package/dist/agents/deployer.md +52 -11
  4. package/dist/agents/doer.md +32 -7
  5. package/dist/agents/integ-test-runner.md +151 -61
  6. package/dist/agents/plan-reviewer.md +74 -17
  7. package/dist/agents/planner.md +94 -14
  8. package/dist/agents/regression-test-runner.md +216 -0
  9. package/dist/agents/reviewer.md +21 -6
  10. package/dist/agents/schemas/backlog-groomer-input.json +35 -0
  11. package/dist/agents/schemas/backlog-groomer-output.json +164 -0
  12. package/dist/agents/schemas/integ-test-runner-output.json +34 -0
  13. package/dist/agents/schemas/regression-test-runner-input.json +15 -0
  14. package/dist/agents/schemas/regression-test-runner-output.json +50 -0
  15. package/dist/agents/schemas/reviewer-output.json +4 -0
  16. package/dist/cli/agent-transform.d.ts +1 -0
  17. package/dist/cli/agent-transform.d.ts.map +1 -1
  18. package/dist/cli/agent-transform.js +77 -0
  19. package/dist/cli/agent-transform.js.map +1 -1
  20. package/dist/cli/auth.d.ts +3 -0
  21. package/dist/cli/auth.d.ts.map +1 -1
  22. package/dist/cli/auth.js +181 -5
  23. package/dist/cli/auth.js.map +1 -1
  24. package/dist/cli/config.d.ts +5 -1
  25. package/dist/cli/config.d.ts.map +1 -1
  26. package/dist/cli/config.js +7 -1
  27. package/dist/cli/config.js.map +1 -1
  28. package/dist/cli/dolt-install.d.ts +91 -0
  29. package/dist/cli/dolt-install.d.ts.map +1 -0
  30. package/dist/cli/dolt-install.js +334 -0
  31. package/dist/cli/dolt-install.js.map +1 -0
  32. package/dist/cli/install-guard.d.ts +29 -0
  33. package/dist/cli/install-guard.d.ts.map +1 -0
  34. package/dist/cli/install-guard.js +153 -0
  35. package/dist/cli/install-guard.js.map +1 -0
  36. package/dist/cli/install.d.ts +44 -3
  37. package/dist/cli/install.d.ts.map +1 -1
  38. package/dist/cli/install.js +604 -108
  39. package/dist/cli/install.js.map +1 -1
  40. package/dist/cli/join.d.ts +12 -0
  41. package/dist/cli/join.d.ts.map +1 -0
  42. package/dist/cli/join.js +87 -0
  43. package/dist/cli/join.js.map +1 -0
  44. package/dist/cli/register-member.d.ts +2 -0
  45. package/dist/cli/register-member.d.ts.map +1 -0
  46. package/dist/cli/register-member.js +193 -0
  47. package/dist/cli/register-member.js.map +1 -0
  48. package/dist/cli/restart.d.ts +2 -0
  49. package/dist/cli/restart.d.ts.map +1 -0
  50. package/dist/cli/restart.js +7 -0
  51. package/dist/cli/restart.js.map +1 -0
  52. package/dist/cli/secret.js +8 -2
  53. package/dist/cli/secret.js.map +1 -1
  54. package/dist/cli/spoke.d.ts +35 -0
  55. package/dist/cli/spoke.d.ts.map +1 -0
  56. package/dist/cli/spoke.js +212 -0
  57. package/dist/cli/spoke.js.map +1 -0
  58. package/dist/cli/start.d.ts +2 -0
  59. package/dist/cli/start.d.ts.map +1 -0
  60. package/dist/cli/start.js +92 -0
  61. package/dist/cli/start.js.map +1 -0
  62. package/dist/cli/status.d.ts +2 -0
  63. package/dist/cli/status.d.ts.map +1 -0
  64. package/dist/cli/status.js +83 -0
  65. package/dist/cli/status.js.map +1 -0
  66. package/dist/cli/stop.d.ts +2 -0
  67. package/dist/cli/stop.d.ts.map +1 -0
  68. package/dist/cli/stop.js +51 -0
  69. package/dist/cli/stop.js.map +1 -0
  70. package/dist/cli/uninstall.d.ts.map +1 -1
  71. package/dist/cli/uninstall.js +109 -9
  72. package/dist/cli/uninstall.js.map +1 -1
  73. package/dist/cli/update.d.ts.map +1 -1
  74. package/dist/cli/update.js +10 -1
  75. package/dist/cli/update.js.map +1 -1
  76. package/dist/cli/workflow-assets.d.ts +37 -0
  77. package/dist/cli/workflow-assets.d.ts.map +1 -0
  78. package/dist/cli/workflow-assets.js +144 -0
  79. package/dist/cli/workflow-assets.js.map +1 -0
  80. package/dist/cli/workflow.d.ts +75 -0
  81. package/dist/cli/workflow.d.ts.map +1 -0
  82. package/dist/cli/workflow.js +397 -0
  83. package/dist/cli/workflow.js.map +1 -0
  84. package/dist/hub-service/activity.d.ts +30 -0
  85. package/dist/hub-service/activity.d.ts.map +1 -0
  86. package/dist/hub-service/activity.js +20 -0
  87. package/dist/hub-service/activity.js.map +1 -0
  88. package/dist/hub-service/audit-log.d.ts +19 -0
  89. package/dist/hub-service/audit-log.d.ts.map +1 -0
  90. package/dist/hub-service/audit-log.js +13 -0
  91. package/dist/hub-service/audit-log.js.map +1 -0
  92. package/dist/hub-service/db/pool.d.ts +19 -0
  93. package/dist/hub-service/db/pool.d.ts.map +1 -0
  94. package/dist/hub-service/db/pool.js +53 -0
  95. package/dist/hub-service/db/pool.js.map +1 -0
  96. package/dist/hub-service/enrollment.d.ts +29 -0
  97. package/dist/hub-service/enrollment.d.ts.map +1 -0
  98. package/dist/hub-service/enrollment.js +48 -0
  99. package/dist/hub-service/enrollment.js.map +1 -0
  100. package/dist/hub-service/envelope-routes.d.ts +46 -0
  101. package/dist/hub-service/envelope-routes.d.ts.map +1 -0
  102. package/dist/hub-service/envelope-routes.js +94 -0
  103. package/dist/hub-service/envelope-routes.js.map +1 -0
  104. package/dist/hub-service/handlers/installers.d.ts +14 -0
  105. package/dist/hub-service/handlers/installers.d.ts.map +1 -0
  106. package/dist/hub-service/handlers/installers.js +8 -0
  107. package/dist/hub-service/handlers/installers.js.map +1 -0
  108. package/dist/hub-service/http-server.d.ts +31 -0
  109. package/dist/hub-service/http-server.d.ts.map +1 -0
  110. package/dist/hub-service/http-server.js +711 -0
  111. package/dist/hub-service/http-server.js.map +1 -0
  112. package/dist/hub-service/hub-jwt.d.ts +30 -0
  113. package/dist/hub-service/hub-jwt.d.ts.map +1 -0
  114. package/dist/hub-service/hub-jwt.js +105 -0
  115. package/dist/hub-service/hub-jwt.js.map +1 -0
  116. package/dist/hub-service/jwt-revocation.d.ts +20 -0
  117. package/dist/hub-service/jwt-revocation.d.ts.map +1 -0
  118. package/dist/hub-service/jwt-revocation.js +18 -0
  119. package/dist/hub-service/jwt-revocation.js.map +1 -0
  120. package/dist/hub-service/machines.d.ts +16 -0
  121. package/dist/hub-service/machines.d.ts.map +1 -0
  122. package/dist/hub-service/machines.js +14 -0
  123. package/dist/hub-service/machines.js.map +1 -0
  124. package/dist/hub-service/main.d.ts +3 -0
  125. package/dist/hub-service/main.d.ts.map +1 -0
  126. package/dist/hub-service/main.js +64 -0
  127. package/dist/hub-service/main.js.map +1 -0
  128. package/dist/hub-service/member-tokens.d.ts +11 -0
  129. package/dist/hub-service/member-tokens.d.ts.map +1 -0
  130. package/dist/hub-service/member-tokens.js +49 -0
  131. package/dist/hub-service/member-tokens.js.map +1 -0
  132. package/dist/hub-service/member-view.d.ts +20 -0
  133. package/dist/hub-service/member-view.d.ts.map +1 -0
  134. package/dist/hub-service/member-view.js +76 -0
  135. package/dist/hub-service/member-view.js.map +1 -0
  136. package/dist/hub-service/members.d.ts +44 -0
  137. package/dist/hub-service/members.d.ts.map +1 -0
  138. package/dist/hub-service/members.js +25 -0
  139. package/dist/hub-service/members.js.map +1 -0
  140. package/dist/hub-service/presence.d.ts +40 -0
  141. package/dist/hub-service/presence.d.ts.map +1 -0
  142. package/dist/hub-service/presence.js +44 -0
  143. package/dist/hub-service/presence.js.map +1 -0
  144. package/dist/hub-service/project-view.d.ts +12 -0
  145. package/dist/hub-service/project-view.d.ts.map +1 -0
  146. package/dist/hub-service/project-view.js +34 -0
  147. package/dist/hub-service/project-view.js.map +1 -0
  148. package/dist/hub-service/projects.d.ts +48 -0
  149. package/dist/hub-service/projects.d.ts.map +1 -0
  150. package/dist/hub-service/projects.js +80 -0
  151. package/dist/hub-service/projects.js.map +1 -0
  152. package/dist/hub-service/relay-queue.d.ts +115 -0
  153. package/dist/hub-service/relay-queue.d.ts.map +1 -0
  154. package/dist/hub-service/relay-queue.js +148 -0
  155. package/dist/hub-service/relay-queue.js.map +1 -0
  156. package/dist/hub-service/session-jwt.d.ts +10 -0
  157. package/dist/hub-service/session-jwt.d.ts.map +1 -0
  158. package/dist/hub-service/session-jwt.js +69 -0
  159. package/dist/hub-service/session-jwt.js.map +1 -0
  160. package/dist/hub-service/usage.d.ts +40 -0
  161. package/dist/hub-service/usage.d.ts.map +1 -0
  162. package/dist/hub-service/usage.js +25 -0
  163. package/dist/hub-service/usage.js.map +1 -0
  164. package/dist/hub-service/users.d.ts +56 -0
  165. package/dist/hub-service/users.d.ts.map +1 -0
  166. package/dist/hub-service/users.js +72 -0
  167. package/dist/hub-service/users.js.map +1 -0
  168. package/dist/hub-service/workspaces.d.ts +20 -0
  169. package/dist/hub-service/workspaces.d.ts.map +1 -0
  170. package/dist/hub-service/workspaces.js +10 -0
  171. package/dist/hub-service/workspaces.js.map +1 -0
  172. package/dist/index.js +179 -132
  173. package/dist/index.js.map +1 -1
  174. package/dist/os/linux.d.ts +13 -0
  175. package/dist/os/linux.d.ts.map +1 -1
  176. package/dist/os/linux.js +62 -3
  177. package/dist/os/linux.js.map +1 -1
  178. package/dist/os/os-commands.d.ts +10 -0
  179. package/dist/os/os-commands.d.ts.map +1 -1
  180. package/dist/os/windows.d.ts +1 -0
  181. package/dist/os/windows.d.ts.map +1 -1
  182. package/dist/os/windows.js +21 -1
  183. package/dist/os/windows.js.map +1 -1
  184. package/dist/paths.d.ts +23 -0
  185. package/dist/paths.d.ts.map +1 -1
  186. package/dist/paths.js +29 -0
  187. package/dist/paths.js.map +1 -1
  188. package/dist/providers/agy.d.ts +9 -2
  189. package/dist/providers/agy.d.ts.map +1 -1
  190. package/dist/providers/agy.js +127 -14
  191. package/dist/providers/agy.js.map +1 -1
  192. package/dist/providers/claude.d.ts +6 -2
  193. package/dist/providers/claude.d.ts.map +1 -1
  194. package/dist/providers/claude.js +248 -9
  195. package/dist/providers/claude.js.map +1 -1
  196. package/dist/providers/codex.d.ts +3 -2
  197. package/dist/providers/codex.d.ts.map +1 -1
  198. package/dist/providers/codex.js +7 -0
  199. package/dist/providers/codex.js.map +1 -1
  200. package/dist/providers/copilot.d.ts +3 -2
  201. package/dist/providers/copilot.d.ts.map +1 -1
  202. package/dist/providers/copilot.js +8 -1
  203. package/dist/providers/copilot.js.map +1 -1
  204. package/dist/providers/gemini.d.ts +3 -2
  205. package/dist/providers/gemini.d.ts.map +1 -1
  206. package/dist/providers/gemini.js +11 -1
  207. package/dist/providers/gemini.js.map +1 -1
  208. package/dist/providers/index.d.ts +1 -0
  209. package/dist/providers/index.d.ts.map +1 -1
  210. package/dist/providers/index.js +3 -0
  211. package/dist/providers/index.js.map +1 -1
  212. package/dist/providers/none.d.ts +51 -0
  213. package/dist/providers/none.d.ts.map +1 -0
  214. package/dist/providers/none.js +103 -0
  215. package/dist/providers/none.js.map +1 -0
  216. package/dist/providers/opencode.d.ts +4 -2
  217. package/dist/providers/opencode.d.ts.map +1 -1
  218. package/dist/providers/opencode.js +49 -0
  219. package/dist/providers/opencode.js.map +1 -1
  220. package/dist/providers/provider.d.ts +79 -1
  221. package/dist/providers/provider.d.ts.map +1 -1
  222. package/dist/providers/provider.js +10 -0
  223. package/dist/providers/provider.js.map +1 -1
  224. package/dist/services/agent-provisioner.d.ts +3 -3
  225. package/dist/services/agent-provisioner.d.ts.map +1 -1
  226. package/dist/services/agent-provisioner.js +12 -5
  227. package/dist/services/agent-provisioner.js.map +1 -1
  228. package/dist/services/auth-socket.d.ts.map +1 -1
  229. package/dist/services/auth-socket.js +2 -0
  230. package/dist/services/auth-socket.js.map +1 -1
  231. package/dist/services/budget-awareness.d.ts +130 -0
  232. package/dist/services/budget-awareness.d.ts.map +1 -0
  233. package/dist/services/budget-awareness.js +129 -0
  234. package/dist/services/budget-awareness.js.map +1 -0
  235. package/dist/services/cloud-sync.d.ts +35 -0
  236. package/dist/services/cloud-sync.d.ts.map +1 -0
  237. package/dist/services/cloud-sync.js +90 -0
  238. package/dist/services/cloud-sync.js.map +1 -0
  239. package/dist/services/context-admission.d.ts +82 -0
  240. package/dist/services/context-admission.d.ts.map +1 -0
  241. package/dist/services/context-admission.js +136 -0
  242. package/dist/services/context-admission.js.map +1 -0
  243. package/dist/services/event-bus.d.ts +27 -0
  244. package/dist/services/event-bus.d.ts.map +1 -0
  245. package/dist/services/event-bus.js +20 -0
  246. package/dist/services/event-bus.js.map +1 -0
  247. package/dist/services/file-chunker.d.ts +38 -0
  248. package/dist/services/file-chunker.d.ts.map +1 -0
  249. package/dist/services/file-chunker.js +63 -0
  250. package/dist/services/file-chunker.js.map +1 -0
  251. package/dist/services/file-transfer-relay.d.ts +55 -0
  252. package/dist/services/file-transfer-relay.d.ts.map +1 -0
  253. package/dist/services/file-transfer-relay.js +115 -0
  254. package/dist/services/file-transfer-relay.js.map +1 -0
  255. package/dist/services/github-app.d.ts.map +1 -1
  256. package/dist/services/github-app.js +1 -0
  257. package/dist/services/github-app.js.map +1 -1
  258. package/dist/services/http-transport.d.ts +25 -0
  259. package/dist/services/http-transport.d.ts.map +1 -0
  260. package/dist/services/http-transport.js +371 -0
  261. package/dist/services/http-transport.js.map +1 -0
  262. package/dist/services/hub-client.d.ts +69 -0
  263. package/dist/services/hub-client.d.ts.map +1 -0
  264. package/dist/services/hub-client.js +217 -0
  265. package/dist/services/hub-client.js.map +1 -0
  266. package/dist/services/jwt.d.ts +17 -0
  267. package/dist/services/jwt.d.ts.map +1 -0
  268. package/dist/services/jwt.js +70 -0
  269. package/dist/services/jwt.js.map +1 -0
  270. package/dist/services/known-sessions.d.ts +8 -0
  271. package/dist/services/known-sessions.d.ts.map +1 -0
  272. package/dist/services/known-sessions.js +40 -0
  273. package/dist/services/known-sessions.js.map +1 -0
  274. package/dist/services/model-pricing.d.ts +36 -0
  275. package/dist/services/model-pricing.d.ts.map +1 -0
  276. package/dist/services/model-pricing.js +108 -0
  277. package/dist/services/model-pricing.js.map +1 -0
  278. package/dist/services/orphan-recovery.d.ts +56 -0
  279. package/dist/services/orphan-recovery.d.ts.map +1 -0
  280. package/dist/services/orphan-recovery.js +111 -0
  281. package/dist/services/orphan-recovery.js.map +1 -0
  282. package/dist/services/pending-responses.d.ts +23 -0
  283. package/dist/services/pending-responses.d.ts.map +1 -0
  284. package/dist/services/pending-responses.js +52 -0
  285. package/dist/services/pending-responses.js.map +1 -0
  286. package/dist/services/registry.d.ts +4 -1
  287. package/dist/services/registry.d.ts.map +1 -1
  288. package/dist/services/registry.js +3 -0
  289. package/dist/services/registry.js.map +1 -1
  290. package/dist/services/relay-context.d.ts +23 -0
  291. package/dist/services/relay-context.d.ts.map +1 -0
  292. package/dist/services/relay-context.js +8 -0
  293. package/dist/services/relay-context.js.map +1 -0
  294. package/dist/services/relay-executor.d.ts +68 -0
  295. package/dist/services/relay-executor.d.ts.map +1 -0
  296. package/dist/services/relay-executor.js +70 -0
  297. package/dist/services/relay-executor.js.map +1 -0
  298. package/dist/services/relay-request.d.ts +65 -0
  299. package/dist/services/relay-request.d.ts.map +1 -0
  300. package/dist/services/relay-request.js +129 -0
  301. package/dist/services/relay-request.js.map +1 -0
  302. package/dist/services/relay-strategy.d.ts +19 -0
  303. package/dist/services/relay-strategy.d.ts.map +1 -0
  304. package/dist/services/relay-strategy.js +111 -0
  305. package/dist/services/relay-strategy.js.map +1 -0
  306. package/dist/services/service-manager/index.d.ts +5 -0
  307. package/dist/services/service-manager/index.d.ts.map +1 -0
  308. package/dist/services/service-manager/index.js +66 -0
  309. package/dist/services/service-manager/index.js.map +1 -0
  310. package/dist/services/service-manager/linux.d.ts +10 -0
  311. package/dist/services/service-manager/linux.d.ts.map +1 -0
  312. package/dist/services/service-manager/linux.js +97 -0
  313. package/dist/services/service-manager/linux.js.map +1 -0
  314. package/dist/services/service-manager/macos.d.ts +10 -0
  315. package/dist/services/service-manager/macos.d.ts.map +1 -0
  316. package/dist/services/service-manager/macos.js +94 -0
  317. package/dist/services/service-manager/macos.js.map +1 -0
  318. package/dist/services/service-manager/types.d.ts +18 -0
  319. package/dist/services/service-manager/types.d.ts.map +1 -0
  320. package/dist/services/service-manager/types.js +5 -0
  321. package/dist/services/service-manager/types.js.map +1 -0
  322. package/dist/services/service-manager/windows.d.ts +10 -0
  323. package/dist/services/service-manager/windows.d.ts.map +1 -0
  324. package/dist/services/service-manager/windows.js +73 -0
  325. package/dist/services/service-manager/windows.js.map +1 -0
  326. package/dist/services/session-registry.d.ts +70 -0
  327. package/dist/services/session-registry.d.ts.map +1 -0
  328. package/dist/services/session-registry.js +91 -0
  329. package/dist/services/session-registry.js.map +1 -0
  330. package/dist/services/singleton.d.ts +15 -0
  331. package/dist/services/singleton.d.ts.map +1 -0
  332. package/dist/services/singleton.js +98 -0
  333. package/dist/services/singleton.js.map +1 -0
  334. package/dist/services/sprint-coordination.d.ts +168 -0
  335. package/dist/services/sprint-coordination.d.ts.map +1 -0
  336. package/dist/services/sprint-coordination.js +564 -0
  337. package/dist/services/sprint-coordination.js.map +1 -0
  338. package/dist/services/ssh.d.ts.map +1 -1
  339. package/dist/services/ssh.js +70 -3
  340. package/dist/services/ssh.js.map +1 -1
  341. package/dist/services/stall/log-path-resolver.d.ts.map +1 -1
  342. package/dist/services/stall/log-path-resolver.js +8 -1
  343. package/dist/services/stall/log-path-resolver.js.map +1 -1
  344. package/dist/services/stall/stall-detector.d.ts.map +1 -1
  345. package/dist/services/stall/stall-detector.js +39 -7
  346. package/dist/services/stall/stall-detector.js.map +1 -1
  347. package/dist/services/stall/stall-poller.d.ts +16 -0
  348. package/dist/services/stall/stall-poller.d.ts.map +1 -1
  349. package/dist/services/stall/stall-poller.js +136 -18
  350. package/dist/services/stall/stall-poller.js.map +1 -1
  351. package/dist/services/strategy.d.ts.map +1 -1
  352. package/dist/services/strategy.js +55 -5
  353. package/dist/services/strategy.js.map +1 -1
  354. package/dist/services/substitution-engine.d.ts +20 -0
  355. package/dist/services/substitution-engine.d.ts.map +1 -0
  356. package/dist/services/substitution-engine.js +92 -0
  357. package/dist/services/substitution-engine.js.map +1 -0
  358. package/dist/services/task-cleanup.d.ts.map +1 -1
  359. package/dist/services/task-cleanup.js +1 -9
  360. package/dist/services/task-cleanup.js.map +1 -1
  361. package/dist/services/token-issuer.d.ts +47 -0
  362. package/dist/services/token-issuer.d.ts.map +1 -0
  363. package/dist/services/token-issuer.js +63 -0
  364. package/dist/services/token-issuer.js.map +1 -0
  365. package/dist/services/tool-registry.d.ts +3 -0
  366. package/dist/services/tool-registry.d.ts.map +1 -0
  367. package/dist/services/tool-registry.js +139 -0
  368. package/dist/services/tool-registry.js.map +1 -0
  369. package/dist/services/user-config.d.ts +14 -0
  370. package/dist/services/user-config.d.ts.map +1 -1
  371. package/dist/services/user-config.js +55 -0
  372. package/dist/services/user-config.js.map +1 -1
  373. package/dist/services/vcs/types.d.ts +44 -0
  374. package/dist/services/vcs/types.d.ts.map +1 -1
  375. package/dist/skills/fleet-sprint-cli/SKILL.md +103 -0
  376. package/dist/skills/pm/cost.md +3 -0
  377. package/dist/skills/pm/doer-reviewer-loop.md +3 -0
  378. package/dist/tools/check-status.d.ts.map +1 -1
  379. package/dist/tools/check-status.js +8 -2
  380. package/dist/tools/check-status.js.map +1 -1
  381. package/dist/tools/child-id-allocator.d.ts +45 -0
  382. package/dist/tools/child-id-allocator.d.ts.map +1 -0
  383. package/dist/tools/child-id-allocator.js +62 -0
  384. package/dist/tools/child-id-allocator.js.map +1 -0
  385. package/dist/tools/cloud-control.d.ts +2 -2
  386. package/dist/tools/compose-permissions.d.ts +12 -4
  387. package/dist/tools/compose-permissions.d.ts.map +1 -1
  388. package/dist/tools/compose-permissions.js +55 -4
  389. package/dist/tools/compose-permissions.js.map +1 -1
  390. package/dist/tools/dolt-push-mutex.d.ts +44 -0
  391. package/dist/tools/dolt-push-mutex.d.ts.map +1 -0
  392. package/dist/tools/dolt-push-mutex.js +83 -0
  393. package/dist/tools/dolt-push-mutex.js.map +1 -0
  394. package/dist/tools/execute-command.d.ts +11 -1
  395. package/dist/tools/execute-command.d.ts.map +1 -1
  396. package/dist/tools/execute-command.js +22 -5
  397. package/dist/tools/execute-command.js.map +1 -1
  398. package/dist/tools/execute-prompt.d.ts +72 -12
  399. package/dist/tools/execute-prompt.d.ts.map +1 -1
  400. package/dist/tools/execute-prompt.js +962 -71
  401. package/dist/tools/execute-prompt.js.map +1 -1
  402. package/dist/tools/get-member-model-pricing.d.ts +21 -0
  403. package/dist/tools/get-member-model-pricing.d.ts.map +1 -0
  404. package/dist/tools/get-member-model-pricing.js +29 -0
  405. package/dist/tools/get-member-model-pricing.js.map +1 -0
  406. package/dist/tools/list-members.d.ts.map +1 -1
  407. package/dist/tools/list-members.js +39 -7
  408. package/dist/tools/list-members.js.map +1 -1
  409. package/dist/tools/member-detail.d.ts +1 -1
  410. package/dist/tools/member-detail.d.ts.map +1 -1
  411. package/dist/tools/member-detail.js +8 -2
  412. package/dist/tools/member-detail.js.map +1 -1
  413. package/dist/tools/member-reservation.d.ts +29 -0
  414. package/dist/tools/member-reservation.d.ts.map +1 -0
  415. package/dist/tools/member-reservation.js +71 -0
  416. package/dist/tools/member-reservation.js.map +1 -0
  417. package/dist/tools/provision-vcs-auth.d.ts +7 -7
  418. package/dist/tools/provision-vcs-auth.js +1 -1
  419. package/dist/tools/provision-vcs-auth.js.map +1 -1
  420. package/dist/tools/register-member.d.ts +17 -5
  421. package/dist/tools/register-member.d.ts.map +1 -1
  422. package/dist/tools/register-member.js +144 -5
  423. package/dist/tools/register-member.js.map +1 -1
  424. package/dist/tools/remove-member.d.ts +1 -1
  425. package/dist/tools/report-status.d.ts +33 -0
  426. package/dist/tools/report-status.d.ts.map +1 -0
  427. package/dist/tools/report-status.js +44 -0
  428. package/dist/tools/report-status.js.map +1 -0
  429. package/dist/tools/respond-to-message.d.ts +21 -0
  430. package/dist/tools/respond-to-message.d.ts.map +1 -0
  431. package/dist/tools/respond-to-message.js +23 -0
  432. package/dist/tools/respond-to-message.js.map +1 -0
  433. package/dist/tools/send-files.d.ts +3 -0
  434. package/dist/tools/send-files.d.ts.map +1 -1
  435. package/dist/tools/send-files.js +88 -8
  436. package/dist/tools/send-files.js.map +1 -1
  437. package/dist/tools/send-message.d.ts +27 -0
  438. package/dist/tools/send-message.d.ts.map +1 -0
  439. package/dist/tools/send-message.js +46 -0
  440. package/dist/tools/send-message.js.map +1 -0
  441. package/dist/tools/shutdown-server.d.ts +2 -0
  442. package/dist/tools/shutdown-server.d.ts.map +1 -1
  443. package/dist/tools/shutdown-server.js +19 -0
  444. package/dist/tools/shutdown-server.js.map +1 -1
  445. package/dist/tools/update-member.d.ts +8 -8
  446. package/dist/tools/update-member.d.ts.map +1 -1
  447. package/dist/tools/update-member.js +11 -1
  448. package/dist/tools/update-member.js.map +1 -1
  449. package/dist/types.d.ts +15 -3
  450. package/dist/types.d.ts.map +1 -1
  451. package/dist/utils/agent-helpers.d.ts +2 -1
  452. package/dist/utils/agent-helpers.d.ts.map +1 -1
  453. package/dist/utils/agent-helpers.js +7 -2
  454. package/dist/utils/agent-helpers.js.map +1 -1
  455. package/dist/utils/pid-helpers.d.ts +15 -0
  456. package/dist/utils/pid-helpers.d.ts.map +1 -1
  457. package/dist/utils/pid-helpers.js +23 -0
  458. package/dist/utils/pid-helpers.js.map +1 -1
  459. package/dist/utils/process-utils.d.ts +3 -0
  460. package/dist/utils/process-utils.d.ts.map +1 -0
  461. package/dist/utils/process-utils.js +42 -0
  462. package/dist/utils/process-utils.js.map +1 -0
  463. package/dist/utils/prompt-errors.d.ts +2 -1
  464. package/dist/utils/prompt-errors.d.ts.map +1 -1
  465. package/dist/utils/prompt-errors.js +13 -3
  466. package/dist/utils/prompt-errors.js.map +1 -1
  467. package/dist/utils/workspace-trust.d.ts +24 -0
  468. package/dist/utils/workspace-trust.d.ts.map +1 -0
  469. package/dist/utils/workspace-trust.js +35 -0
  470. package/dist/utils/workspace-trust.js.map +1 -0
  471. package/dist/workflows/auto-sprint.js +450 -87
  472. package/package.json +35 -7
  473. package/packages/apra-fleet-client/package.json +26 -0
  474. package/packages/apra-fleet-client/src/client/api.mjs +396 -0
  475. package/packages/apra-fleet-client/src/client/client.mjs +146 -0
  476. package/packages/apra-fleet-client/src/client/errors.mjs +71 -0
  477. package/packages/apra-fleet-client/src/client/factory.mjs +65 -0
  478. package/packages/apra-fleet-client/src/client/server-resolution.mjs +265 -0
  479. package/packages/apra-fleet-client/src/client/transport.mjs +327 -0
  480. package/packages/apra-fleet-se/apra-pm/agents/backlog-groomer.md +287 -0
  481. package/packages/apra-fleet-se/apra-pm/agents/ci-watcher.md +89 -0
  482. package/packages/apra-fleet-se/apra-pm/agents/deployer.md +139 -0
  483. package/packages/apra-fleet-se/apra-pm/agents/doer.md +225 -0
  484. package/packages/apra-fleet-se/apra-pm/agents/harvester.md +169 -0
  485. package/packages/apra-fleet-se/apra-pm/agents/integ-test-runner.md +316 -0
  486. package/packages/apra-fleet-se/apra-pm/agents/plan-reviewer.md +188 -0
  487. package/packages/apra-fleet-se/apra-pm/agents/planner.md +239 -0
  488. package/packages/apra-fleet-se/apra-pm/agents/regression-test-runner.md +216 -0
  489. package/packages/apra-fleet-se/apra-pm/agents/reviewer.md +174 -0
  490. package/packages/apra-fleet-se/apra-pm/agents/schemas/backlog-groomer-input.json +35 -0
  491. package/packages/apra-fleet-se/apra-pm/agents/schemas/backlog-groomer-output.json +164 -0
  492. package/packages/apra-fleet-se/apra-pm/agents/schemas/ci-watcher-input.json +26 -0
  493. package/packages/apra-fleet-se/apra-pm/agents/schemas/ci-watcher-output.json +18 -0
  494. package/packages/apra-fleet-se/apra-pm/agents/schemas/deployer-input.json +19 -0
  495. package/packages/apra-fleet-se/apra-pm/agents/schemas/deployer-output.json +17 -0
  496. package/packages/apra-fleet-se/apra-pm/agents/schemas/doer-input.json +25 -0
  497. package/packages/apra-fleet-se/apra-pm/agents/schemas/doer-output.json +22 -0
  498. package/packages/apra-fleet-se/apra-pm/agents/schemas/harvester-input.json +31 -0
  499. package/packages/apra-fleet-se/apra-pm/agents/schemas/harvester-output.json +18 -0
  500. package/packages/apra-fleet-se/apra-pm/agents/schemas/integ-test-runner-input.json +20 -0
  501. package/packages/apra-fleet-se/apra-pm/agents/schemas/integ-test-runner-output.json +61 -0
  502. package/packages/apra-fleet-se/apra-pm/agents/schemas/plan-reviewer-input.json +15 -0
  503. package/packages/apra-fleet-se/apra-pm/agents/schemas/plan-reviewer-output.json +30 -0
  504. package/packages/apra-fleet-se/apra-pm/agents/schemas/regression-test-runner-input.json +15 -0
  505. package/packages/apra-fleet-se/apra-pm/agents/schemas/regression-test-runner-output.json +50 -0
  506. package/packages/apra-fleet-se/apra-pm/agents/schemas/reviewer-input.json +25 -0
  507. package/packages/apra-fleet-se/apra-pm/agents/schemas/reviewer-output.json +38 -0
  508. package/packages/apra-fleet-se/apra-pm/skills/pm/SKILL.md +402 -0
  509. package/packages/apra-fleet-se/apra-pm/skills/pm/beads.md +142 -0
  510. package/packages/apra-fleet-se/apra-pm/skills/pm/cost.md +157 -0
  511. package/packages/apra-fleet-se/apra-pm/skills/pm/doer-reviewer-loop.md +300 -0
  512. package/packages/apra-fleet-se/apra-pm/skills/pm/fleet-addendum.md +121 -0
  513. package/packages/apra-fleet-se/apra-pm/skills/pm/simple-sprint.md +65 -0
  514. package/packages/apra-fleet-se/apra-pm/skills/pm/sprint.md +327 -0
  515. package/packages/apra-fleet-se/apra-pm/skills/pm/worktrees.md +92 -0
  516. package/packages/apra-fleet-se/apra-pm/version.json +3 -0
  517. package/packages/apra-fleet-se/bin/cli.mjs +857 -0
  518. package/packages/apra-fleet-se/bin/serve.mjs +383 -0
  519. package/packages/apra-fleet-se/fleet-sprint/conflict-ladder.mjs +178 -0
  520. package/packages/apra-fleet-se/fleet-sprint/contracts.mjs +914 -0
  521. package/packages/apra-fleet-se/fleet-sprint/dispatch-safety-guard.mjs +177 -0
  522. package/packages/apra-fleet-se/fleet-sprint/docs/README.md +191 -0
  523. package/packages/apra-fleet-se/fleet-sprint/docs/coach-role-design.md +151 -0
  524. package/packages/apra-fleet-se/fleet-sprint/docs/dolt-tier2-runbook.md +127 -0
  525. package/packages/apra-fleet-se/fleet-sprint/docs/fleet-sprint-diagram.md +94 -0
  526. package/packages/apra-fleet-se/fleet-sprint/docs/stabilization-log.md +1125 -0
  527. package/packages/apra-fleet-se/fleet-sprint/dolt-literal-guard.mjs +72 -0
  528. package/packages/apra-fleet-se/fleet-sprint/dolt-recovery-path-b.mjs +339 -0
  529. package/packages/apra-fleet-se/fleet-sprint/dolt-recovery-tier2.mjs +360 -0
  530. package/packages/apra-fleet-se/fleet-sprint/dolt-recovery.mjs +363 -0
  531. package/packages/apra-fleet-se/fleet-sprint/dolt-sync.mjs +1244 -0
  532. package/packages/apra-fleet-se/fleet-sprint/errors.mjs +572 -0
  533. package/packages/apra-fleet-se/fleet-sprint/full-db-fetch-guard.mjs +118 -0
  534. package/packages/apra-fleet-se/fleet-sprint/runner.js +9447 -0
  535. package/packages/apra-fleet-se/fleet-sprint/skills/fleet-sprint-cli/SKILL.md +103 -0
  536. package/packages/apra-fleet-se/fleet-sprint/sprint-lock.mjs +140 -0
  537. package/packages/apra-fleet-se/fleet-sprint/vcs-module.mjs +435 -0
  538. package/packages/apra-fleet-se/fleet-sprint/vcs-providers/azure-devops.mjs +68 -0
  539. package/packages/apra-fleet-se/fleet-sprint/vcs-providers/bitbucket.mjs +53 -0
  540. package/packages/apra-fleet-se/fleet-sprint/vcs-providers/dolt.mjs +146 -0
  541. package/packages/apra-fleet-se/fleet-sprint/vcs-providers/generic-git.mjs +176 -0
  542. package/packages/apra-fleet-se/fleet-sprint/vcs-providers/github.mjs +222 -0
  543. package/packages/apra-fleet-se/fleet-sprint/vcs-providers/index.mjs +218 -0
  544. package/packages/apra-fleet-se/fleet-sprint/viewer-extensions.mjs +882 -0
  545. package/packages/apra-fleet-se/package.json +28 -0
  546. package/packages/apra-fleet-se/workflow.json +1 -0
  547. package/packages/apra-fleet-workflow/package.json +30 -0
  548. package/packages/apra-fleet-workflow/src/viewer/command-output-cap.mjs +112 -0
  549. package/packages/apra-fleet-workflow/src/viewer/debounced-writer.mjs +153 -0
  550. package/packages/apra-fleet-workflow/src/viewer/html-utils.mjs +31 -0
  551. package/packages/apra-fleet-workflow/src/viewer/index.mjs +1325 -0
  552. package/packages/apra-fleet-workflow/src/viewer/lean-state.mjs +237 -0
  553. package/packages/apra-fleet-workflow/src/viewer/run-state-paths.mjs +130 -0
  554. package/packages/apra-fleet-workflow/src/viewer/sprint-state-paths.mjs +29 -0
  555. package/packages/apra-fleet-workflow/src/workflow/engine.mjs +200 -0
  556. package/packages/apra-fleet-workflow/src/workflow/errors.mjs +146 -0
  557. package/packages/apra-fleet-workflow/src/workflow/index.mjs +1723 -0
  558. package/packages/apra-fleet-workflow/src/workflow/journal.mjs +291 -0
  559. package/packages/apra-fleet-workflow/src/workflow/pricing.mjs +99 -0
  560. package/packages/apra-fleet-workflow/src/workflow/vetting.mjs +111 -0
  561. package/scripts/agy-transcript-reader.js +1 -0
  562. package/scripts/fleet-statusline.sh +17 -13
  563. package/skills/fleet/SKILL.md +37 -2
  564. package/skills/fleet/beads.md +14 -7
  565. package/skills/fleet/permissions.md +50 -0
  566. package/skills/fleet/profiles/base-dev.json +1 -0
  567. package/skills/fleet/profiles/base-reviewer.json +1 -0
  568. package/skills/fleet/profiles/node.json +2 -2
  569. package/version.json +1 -1
  570. package/scripts/agy-settings-merge.js +0 -27
  571. /package/{dist → packages/apra-fleet-se/apra-pm}/agents/_shared/GRAPH-SEMANTICS.md +0 -0
@@ -1,18 +1,19 @@
1
1
  ---
2
2
  name: integ-test-runner
3
- description: Runs integ-test-playbook.md end to end -- the real functional tests plus the smoke-test sprint -- owning the test sandbox lifecycle; closes passing features, files bugs for failures.
3
+ description: Runs integ-test-playbook.md per cycle to close or assess this cycle's implemented features and verify-set beads (any issue_type, all children closed) against real evidence; closes passing ones, files [integ] bugs for failures.
4
4
  tools: [Read, Bash, Grep, Glob]
5
5
  ---
6
6
 
7
7
  # Integration Test Execution
8
8
 
9
- You own `integ-test-playbook.md` end to end: you bring the test sandbox up,
10
- run both of the playbook's parts, and always tear the sandbox down. You also
11
- execute integration tests for each open feature and report results to beads.
12
- You do not write test code -- test code was written by developer agents as
13
- `[test]` tasks. (The `deployer` agent is a different role: it follows
14
- `deploy.md` to deploy the software onto the target; it does not run the
15
- playbook.)
9
+ You own `integ-test-playbook.md`: you test the features you were handed
10
+ against their `[test]` tasks, and you close them or file bugs based on real
11
+ evidence. You do not write test code -- test code was written by developer
12
+ agents as `[test]` tasks. (The `deployer` agent is a different role: it
13
+ follows `deploy.md` to deploy the software onto the target; it does not run
14
+ the playbook. The `regression-test-runner` agent is likewise a different
15
+ role: it owns `regression-test-playbook.md`, run once per sprint, separate
16
+ from this per-cycle role.)
16
17
 
17
18
  **Graph semantics** (the "graph-semantics section" referenced below): read
18
19
  `_shared/GRAPH-SEMANTICS.md`, the sibling file installed alongside this one. It is the
@@ -23,8 +24,7 @@ wired and queried; do not restate or improvise those rules here.
23
24
 
24
25
  Your dispatch prompt must supply:
25
26
 
26
- - Repo root path (required) -- where `integ-test-playbook.md` lives. You bring
27
- the playbook's sandbox up and down yourself (see Step 0b); the product
27
+ - Repo root path (required) -- where `integ-test-playbook.md` lives. The product
28
28
  deploy (via `deploy.md`) has already been done by `deployer` before you run.
29
29
  - An **explicit list of feature ids** -- the open features in this sprint's subtree,
30
30
  already scoped for you by the orchestrator. You do not derive this list yourself.
@@ -34,37 +34,42 @@ not passed in the prompt.
34
34
 
35
35
  **Missing-input behavior**: if `integ-test-playbook.md` is entirely absent, stop and
36
36
  return `passed: false` with `notes` naming the missing file -- do not improvise test
37
- steps that are not written down. If the playbook's Setup/Reset verify step fails (the
38
- sandbox is not reachable), do not run tests against it and report fabricated results:
39
- run the playbook's Teardown, leave all features open/untouched, and return
40
- `passed: false` with `notes` stating the environment could not be brought up.
37
+ steps that are not written down.
41
38
 
42
39
  ## Step 0a -- Check permissions before running anything
43
40
 
44
41
  Read `integ-test-playbook.md`. Look for a `## Permissions` section. If found,
45
- verify each listed command prefix is allowed in your CLI's permission settings
46
- (`.claude/settings.json` `permissions.allow` on Claude Code; other providers keep
47
- the equivalent allowlist in their own config file). If any
48
- required prefix is absent from the allowlist, STOP immediately and return
49
- `passed: false` with notes listing every missing entry. Do NOT attempt to add
50
- the permissions yourself, and do NOT proceed while any are missing.
42
+ verify each listed command prefix is covered by the MERGED effective
43
+ permission set -- on Claude Code that means SOME entry in `permissions.allow`
44
+ of EITHER `.claude/settings.json` (the team-committed, shared baseline) OR
45
+ `.claude/settings.local.json` (the per-checkout, individual/gitignored file;
46
+ this is the ONLY file the fleet's `compose_permissions` tool ever writes to
47
+ for Claude Code members -- see `skills/fleet/permissions.md`). Claude Code
48
+ merges `permissions.allow` from both files, so a grant in EITHER one counts
49
+ as coverage; checking only `settings.json` misses every grant
50
+ `compose_permissions` delivered. Other providers keep the equivalent
51
+ allowlist in their own native config file. If any required prefix has no
52
+ covering entry in either file, STOP immediately and return `passed: false`
53
+ with notes listing every missing entry.
54
+
55
+ Do NOT attempt to add the permissions yourself, by editing any file
56
+ directly: `.claude/settings.json` is the team-committed baseline -- changes
57
+ there require the team/a PR, never a self-edit. `.claude/settings.local.json`
58
+ is the correct target for an individual/local grant, but it must be
59
+ provisioned via the `compose_permissions` MCP tool (grant mode), NOT
60
+ hand-edited either -- that tool is the provider-agnostic delivery mechanism
61
+ (this repo supports non-Claude providers too: Gemini, AGY, OpenCode, Codex --
62
+ each has its own native config path via the same tool). The correct
63
+ escalation is to ask the orchestrator/operator to run `compose_permissions`
64
+ with the missing grant. Do NOT proceed while any permissions are missing.
51
65
 
52
66
  ## Step 0b -- Run the playbook
53
67
 
54
- The playbook has two parts; a full pass runs BOTH, in this order:
55
-
56
- 1. **Real functional tests**: run the playbook's unmocked real-backend test
57
- suite exactly as the playbook directs. Failures here are recorded as
58
- `[integ]` bugs (Step 3 rules) -- they do not abort the pass; still run
59
- part 2.
60
- 2. **Smoke test**: bring the sandbox up with the playbook's `## Setup` section
61
- (first cycle) or `## Reset` section (later cycles, when the sandbox already
62
- exists), run the playbook's `## Test scenario` plus the per-feature tests
63
- (Steps 1-3 below) inside it, then ALWAYS run `## Teardown` before returning
64
- -- pass or fail.
65
-
66
- Never abort part 1 early on a single failing test file (no fail-fast), and
67
- never skip Teardown because something upstream failed.
68
+ Read `integ-test-playbook.md` and follow it for the features you were
69
+ handed. There is no sandbox lifecycle and no full-suite pass in this role
70
+ any more -- that is `regression-test-runner`'s job, via
71
+ `regression-test-playbook.md`, once per sprint, and its result is separate
72
+ from and does not gate yours.
68
73
 
69
74
  ## Step 1 -- Work the features you were handed
70
75
 
@@ -78,14 +83,93 @@ a time.
78
83
  - Do **NOT** re-derive the set yourself from `bd graph`/`bd list`. Scoping is the
79
84
  orchestrator's job; you only test what you were handed.
80
85
  - An explicitly empty feature-id list ("zero open features this cycle") is a normal,
81
- successful outcome, not a missing input -- report `featuresClosed: 0` and a `summary`
82
- saying there were no features to test. The playbook itself (Step 0b, both parts)
83
- still runs: it is the sprint's standing confidence check, not a per-feature step.
86
+ successful no-op cycle, not a missing input -- report `featuresClosed: 0` and a
87
+ `summary` saying there were no features to test. There is no standing suite left in
88
+ this role to run regardless.
84
89
  - Only treat the feature-id input as genuinely missing (not merely empty) when your
85
90
  dispatch prompt gives no indication a scoped list was computed at all -- in that case,
86
91
  do not guess and do not scan the DB; stop and report that the scoped list is missing
87
92
  (return `featuresClosed: 0`, note the reason).
88
93
 
94
+ ### Scope discipline and turn economy (stay within budget)
95
+
96
+ Your dispatch has a bounded turn budget, and historically this phase routinely
97
+ exhausted it and burned 15-85 min in resume/repair (apra-fleet-63x). The budget is
98
+ sized so a run that is making progress is bounded by wall-clock time, not by turn
99
+ count -- exhausting the turn count means the run did too much work per feature or
100
+ polled too fast. Keep the run within budget by holding scope tight:
101
+
102
+ - **Test ONLY the handed feature ids, one at a time.** Do not expand scope, do not
103
+ test features you were not handed, and do not re-derive the set (see the bullets
104
+ above). Testing beyond the handed list is both a correctness bug and the fastest
105
+ way to blow the turn budget.
106
+ - **Run each feature's tests once.** Do not routinely re-run a suite that already
107
+ produced a clear pass/fail. Re-run only on a genuine flaky/inconclusive signal, and
108
+ at most once -- if it is still inconclusive, record it inconclusive (Step 3) and
109
+ move on rather than looping.
110
+ - **Do not rebuild or reset any sandbox, and do not run a full-suite pass.** That
111
+ lifecycle is not yours -- it belongs to `regression-test-runner` (see Step 0b).
112
+ Re-provisioning per feature is wasted turns.
113
+ - **Respect the poll cadence.** When waiting on a long test run, poll about once every
114
+ 2 minutes (Step 2) -- polling faster spends turns for no benefit and is a primary
115
+ cause of turn-budget exhaustion on long suites.
116
+ - **Keep bd interactions minimal.** Read what you need (`bd show`, `bd dep list`) once
117
+ per feature; avoid repeated status scans.
118
+
119
+ ## Step 1b -- Work the verify-set bead ids you were handed
120
+
121
+ Your dispatch prompt may also name **verify-set bead ids** -- beads (of ANY
122
+ issue_type: bug, feature, task, epic) whose children are ALL closed and are
123
+ routed to you for verification-closure, not planning. These have no other
124
+ closure owner: doers refuse non-task beads, reviewers may not close beads,
125
+ and Step 1's feature workflow only names features -- without you, a
126
+ verify-set bead would sit open forever even though its implementation is
127
+ done.
128
+
129
+ For each verify-set bead id:
130
+
131
+ 1. `bd show <id>` -- read the bead and its closed children's own
132
+ `close_reason` notes. A child that already cites real, specific evidence
133
+ (exact commands run, exact output, pass counts) is meaningful signal --
134
+ you do not have to blindly re-run everything from scratch if that
135
+ evidence is concrete and directly checkable, but you must still verify it
136
+ against the CURRENTLY DEPLOYED build (not just trust the note), since the
137
+ deploy may postdate when that evidence was captured.
138
+ 2. Verify against the deployed build per `integ-test-playbook.md`, the same
139
+ way you test a feature in Step 2.
140
+ 3. If your pass shows the underlying work holds (the defect no longer
141
+ reproduces, or the feature/task behaves as specified): `bd close <id>`
142
+ with a note citing the commands you ran and the evidence observed.
143
+ 4. If it does **NOT** hold: leave `<id>` open and file a bug describing the
144
+ gap with evidence, parented under **that bead specifically**
145
+ (`--parent <id>`, i.e. the verify-set bead itself) -- **not** the sprint
146
+ root. This is required: filing it under the wrong parent means the gap
147
+ never re-routes that bead back to development next cycle.
148
+
149
+ This is a distinct duty from Step 1-4's feature workflow -- work both lists
150
+ if your prompt hands you both, and report both in your Step 4 output (see
151
+ the `verifySetClosed`/`verifySetLeftOpen` fields below).
152
+
153
+ ## Step 1c -- Any test failure you observe, even out-of-scope, must leave a trail
154
+
155
+ If a full-suite or targeted run you execute anywhere in this role (Step 1b's deployed-build
156
+ verification, or Step 2's per-feature tests) surfaces failures that do not belong to the
157
+ beads you were handed, do not silently absorb them into a clean `passed: true` just because
158
+ you traced the cause elsewhere (uncommitted WIP for another bead, an untracked file, etc.).
159
+ Correctly identifying the cause is not the same as it being tracked:
160
+
161
+ 1. `bd search` for an existing bead that already covers that failing test/file. If found,
162
+ note the cross-reference in your `summary` and in `observedFailures` (Step 4) -- no new
163
+ bead needed.
164
+ 2. If none exists, file one (`[integ]`, type=bug, priority per the rules in Step 3, parented
165
+ under the bead that appears to own the root cause if identifiable, else the sprint scope)
166
+ with a note that it was observed but not reproduced by your own handed work, e.g.
167
+ "uncommitted WIP for 417.4" or "untracked file, no owning bead."
168
+
169
+ This does not block closing the verify-set beads/features that did hold -- it only ensures a
170
+ real, currently-failing test never disappears with zero paper trail just because it wasn't
171
+ "your" bug.
172
+
89
173
  ## Step 2 -- Run tests for each feature
90
174
 
91
175
  For each open feature:
@@ -106,11 +190,13 @@ to the dispatch layer's inactivity watchdog, killing your whole run mid-work and
106
190
  discarding progress. Instead, send the test run to the background (or poll it in
107
191
  short, bounded checks), and between checks -- if it is not done yet -- say so explicitly
108
192
  before checking again, e.g. "Integration tests still running (checked at HH:MM:SS,
109
- N/M features done so far) -- checking again shortly." Do this at least once a minute
110
- while waiting. Backgrounding and polling are not two alternative techniques -- they are
111
- the same obligation. If you background the test run, you must then keep actively
112
- checking on it (a real tool call: re-reading its output, or a Monitor-style wait) at
113
- least once a minute until it finishes. Saying "I'll wait for it to complete" once and
193
+ N/M features done so far) -- checking again shortly." Do this at least every two
194
+ minutes while waiting (each check spends a turn from your budget, so do not poll
195
+ much faster than that either: a blocking status call that waits ~90-120 seconds
196
+ per check is the right shape for a long suite). Backgrounding and polling are not
197
+ two alternative techniques -- they are the same obligation. If you background the
198
+ test run, you must then keep actively checking on it (a real tool call: re-reading
199
+ its output, or a Monitor-style wait) at least every two minutes until it finishes. Saying "I'll wait for it to complete" once and
114
200
  then issuing no further tool calls is exactly the failure this section exists to
115
201
  prevent. If your own tool infrastructure force-backgrounds a "foreground" command you
116
202
  issued (some sandboxes cap a single foreground command at roughly 1-2 minutes and hand
@@ -171,18 +257,24 @@ Leave the feature open. Update its description:
171
257
  bd update <feature-id> --notes="integ-test-runner: inconclusive -- <reason>"
172
258
  ```
173
259
 
174
- ## Step 4 -- Teardown, then return results
260
+ ## Step 4 -- Return results
175
261
 
176
- Run the playbook's `## Teardown` section first -- always, pass or fail (see
177
- Step 0b). Then return:
262
+ Return:
178
263
  - `featuresClosed`: count of features successfully closed this run
179
- - `issuesCreated`: count of new bugs created (playbook part 1 failures included)
180
- - `passed`: `true` only if playbook part 1 recorded no failures AND every feature
181
- tested this run either closed clean or was left open as inconclusive (no bug
182
- filed) -- `false` if any bug was filed
183
- - `bugsFiled`: array of the beads IDs created in Step 3 "If any tests fail" (empty array if none)
184
- - `summary`: one paragraph describing what was tested, what passed, what failed --
185
- including the playbook part 1 (real functional suite) result line
264
+ - `issuesCreated`: count of new bugs created (features AND verify-set beads combined)
265
+ - `passed`: `true` only if every feature and verify-set bead tested this run either
266
+ closed clean or was left open as inconclusive (no bug filed) -- `false` if any bug
267
+ was filed
268
+ - `bugsFiled`: array of the beads IDs created in Step 3 "If any tests fail" or Step 1b
269
+ (empty array if none)
270
+ - `verifySetClosed`: array of verify-set bead ids (Step 1b) closed this run (empty
271
+ array if none, or if your dispatch prompt named no verify-set ids)
272
+ - `verifySetLeftOpen`: array of `{id, reason}` for verify-set bead ids left open this
273
+ run -- either a gap bug was filed (`reason` names it) or the result was inconclusive
274
+ - `observedFailures`: array of `{test, cause, beadId}` for out-of-scope test failures you
275
+ observed per Step 1c (empty array if none) -- `beadId` is the existing bead you
276
+ cross-linked, or the new one you filed
277
+ - `summary`: one paragraph describing what was tested, what passed, what failed
186
278
 
187
279
  ## Output schema
188
280
 
@@ -196,7 +288,10 @@ placeholder):
196
288
  "issuesCreated": 1,
197
289
  "passed": false,
198
290
  "bugsFiled": ["BD-31"],
199
- "summary": "Ran integration tests for 4 open features; 3 passed and were closed, 1 failed on the password reset email flow (BD-31 filed) and left open."
291
+ "verifySetClosed": ["BD-40"],
292
+ "verifySetLeftOpen": [{"id": "BD-41", "reason": "gap bug BD-42 filed -- Stop control still 500s"}],
293
+ "observedFailures": [{"test": "mock-sprint-stall-same-cycle-integ-closure.test.mjs", "cause": "untracked file, no owning bead", "beadId": "BD-43"}],
294
+ "summary": "Ran integration tests for 4 open features and 2 verify-set beads; 3 features passed and were closed, 1 failed on the password reset email flow (BD-31 filed) and left open; BD-40 verified and closed, BD-41 still fails (BD-42 filed); full-suite run also showed 1 unrelated failure in an untracked test file, filed as BD-43."
200
295
  }
201
296
  ```
202
297
 
@@ -208,19 +303,14 @@ this contract; if it differs, follow the dispatch prompt.
208
303
  use), report the same decision fields, in this JSON shape if the caller is an orchestrator,
209
304
  or as prose if you are answering a human directly.
210
305
 
211
- ## Token tracking
212
-
213
- After completing all features, run:
214
- ```
215
- bd remember "<your-label> <model> tokens: input=<N> output=<N>"
216
- ```
217
306
 
218
307
  ## Rules
219
308
 
220
309
  - NEVER close a feature unless ALL its integration tests pass
221
310
  - NEVER write or modify test code
222
311
  - NEVER fix application bugs -- report them as beads issues
223
- - NEVER close type=task issues
224
- - NEVER skip the playbook's Teardown -- it runs after every pass, pass or fail
312
+ - NEVER close a type=task issue UNLESS it is itself a verify-set bead explicitly named
313
+ in your dispatch prompt (Step 1b) -- i.e. it is a grouping node with its own closed
314
+ children, not a leaf task. Never close a leaf task bead regardless of type.
225
315
  - NEVER modify integ-test-playbook.md
226
316
  - Tag every new issue title with `[integ]` so they are searchable and distinguishable from planned work
@@ -19,6 +19,10 @@ wired and queried; do not restate or improvise those rules here.
19
19
  Your dispatch prompt must supply:
20
20
 
21
21
  - The sprint root / scope to review (required) -- which open beads subtree this review pass covers.
22
+ - Prior-round verdicts for the current review cycle, if any (optional -- absent only on
23
+ round 1 of a cycle) -- the verdict and notes from each earlier round that reviewed this
24
+ same scope within the current cycle, most recent last. When present, this is binding
25
+ input for this round, not background color: see "No-goalpost-moving rule" below.
22
26
 
23
27
  Everything else (the DAG itself, task metadata) is read directly by you from beads in
24
28
  Step 1, not passed in the prompt.
@@ -27,11 +31,34 @@ Step 1, not passed in the prompt.
27
31
  issues to review. Return `verdict: "CHANGES_NEEDED"`, `notes` stating the scope is
28
32
  missing, and `taskAssignments: []`.
29
33
 
34
+ ## No-goalpost-moving rule (prior-round verdicts bind)
35
+
36
+ When your dispatch input includes prior-round verdicts for this cycle (see Inputs above),
37
+ treat any resolution that an earlier round's verdict explicitly named as an acceptable way
38
+ to satisfy a criterion as SETTLED for the rest of the cycle:
39
+
40
+ - If the plan under review implements that resolution as stated, you MUST accept it for
41
+ that criterion in this round -- do not demand a different resolution to the same
42
+ criterion just because you would have preferred another approach.
43
+ - You may only revisit a settled resolution by escalating back to CHANGES_NEEDED for that
44
+ criterion, and only with `notes` that name specific NEW evidence not available to the
45
+ round that accepted it (e.g. a changed file, a newly discovered conflict, new sprint
46
+ scope). Re-litigating with a different demanded resolution but no new evidence is not a
47
+ valid escalation.
48
+ - This binds within the current review cycle only. It does not carry across cycles, and it
49
+ does not stop you from raising unrelated, previously-unraised findings.
50
+
51
+ This rule exists because each review round otherwise runs blind to earlier rounds' own
52
+ rulings, letting the goalposts move round to round on the same criterion even though the
53
+ plan correctly implemented what a prior round said was acceptable.
54
+
30
55
  ## Step 1 -- Inspect the DAG
31
56
 
32
57
  ```bash
33
- bd list --status=open
58
+ bd list --parent <scope> --status=open --json
34
59
  ```
60
+ (run once per supplied scope root -- do NOT use a bare `bd list --status=open`, which
61
+ lists the whole database, not just these sprint goals)
35
62
 
36
63
  For each open feature and its tasks, run `bd show <id>` to read the full description and metadata.
37
64
 
@@ -45,27 +72,57 @@ For each open feature and its tasks, run `bd show <id>` to read the full descrip
45
72
  6. **No scope creep**: tasks address only the original sprint goals and open bugs/features
46
73
  7. **No duplicate work**: no two tasks do the same thing
47
74
  8. **Feasibility**: no task assumes something that has not been built yet
48
- 9. **Ready-work check, scoped to this review's subtree** (see the graph-semantics section
49
- above): run `bd list --parent <scope> --ready --json` -- NOT bare `bd ready`, which
50
- lists ready work across the entire database and is not a signal about this DAG. The
51
- scoped `--ready` list should be non-empty whenever open tasks exist under `<scope>`; if
52
- it is empty while open tasks remain, there is a cycle -- diagnose with `bd blocked
53
- --parent <scope>` and `bd dep list <id>` on the suspicious issues, hard CHANGES NEEDED,
54
- list every ID in the cycle. Do NOT assume this cycle is structurally impossible for any
55
- scope-root type except `epic` -- bd's protection is narrower than that (see the
56
- graph-semantics section); treat this scoped check as the only reliable signal,
57
- regardless of the scope root's issue_type. Epic-level completion tracking (has
58
- everything under this epic actually finished) is a separate question -- use `bd epic
59
- status <scope>` for that ONLY when `<scope>` is itself `issue_type=epic` (check via `bd
60
- show <scope> --json` first: on a non-epic scope, `bd epic status` silently lists
61
- unrelated epics instead of erroring) -- fall back to `dependent_count`/manual child
62
- inspection for non-epic scopes.
75
+ 9. **Ready-work check -- scoped to the UNION of this review's roots, not each root alone**
76
+ (see the graph-semantics section above): run `bd list --parent <scope> --ready
77
+ --type=task --json` for EACH sprint root and reason over the COMBINED result. The
78
+ invariant is that the UNION of ready work across all roots is non-empty whenever open
79
+ tasks remain anywhere in scope -- NOT that every root independently has ready work. Do
80
+ NOT use bare `bd ready`, which lists ready work across the entire database and is not a
81
+ signal about this DAG.
82
+ - A single root whose scoped `--ready` list is EMPTY is NOT a failure when its open
83
+ tasks are blocked (directly or transitively) by an open task in a DIFFERENT root that
84
+ is itself ready now or reachable from the union ready-set. That is legitimate
85
+ cross-goal sequencing (a seeded or intended cross-root `blocks` edge), not a cycle --
86
+ do NOT tear out the edge and do NOT hard-fail for it.
87
+ - Hard CHANGES NEEDED only when EITHER (a) the union of `--ready` across every root is
88
+ empty while open tasks remain anywhere in scope (the whole sprint cannot start -- a
89
+ true deadlock), OR (b) a root's blocked chain traces back into its OWN subtree (a
90
+ self-cycle -- a `blocks` edge to a `--parent` ancestor/descendant). Diagnose with `bd
91
+ blocked --parent <scope>` and `bd dep list <id>` on the suspicious issues; list every
92
+ ID in the cycle. Do NOT assume a self-cycle is structurally impossible for any
93
+ scope-root type except `epic` -- bd's protection is narrower than that.
94
+ Epic-level completion tracking (has everything under this epic actually finished) is a
95
+ separate question -- use `bd epic status <scope>` for that ONLY when `<scope>` is itself
96
+ `issue_type=epic` (check via `bd show <scope> --json` first: on a non-epic scope, `bd
97
+ epic status` silently lists unrelated epics instead of erroring) -- fall back to
98
+ `dependent_count`/manual child inspection for non-epic scopes.
63
99
  10. **Model metadata**: every task has a model tier set as beads metadata, i.e.
64
100
  `--metadata '{"model": "..."}'` at creation (visible as the `model` key in `bd show <id>`'s
65
101
  metadata output). This is the single location the tier lives in -- `planner.md` Step 3
66
102
  writes it here and nowhere else (not `--notes`, not free text). A task missing this
67
103
  metadata key is a Step 2 criterion-10 failure, not a fallback case for this step; see
68
104
  Step 3 for the read-time fallback used only when classifying/reporting.
105
+ 11. **Lane cohesion**: every task carries `streak` and `streakOrder` lane metadata via the
106
+ same `--metadata` channel as `model` (visible as the `streak`/`streakOrder` keys in `bd
107
+ show <id>`'s metadata output) -- a task missing either key is a criterion-11 finding.
108
+ Beyond presence, check:
109
+ - **Cohesive lanes**: the tasks sharing a `streak` id name overlapping files or the same
110
+ component/module in their descriptions -- a lane grouping unrelated work areas is a
111
+ finding.
112
+ - **No cross-lane edges among open members**: no `blocks` edge exists between an open
113
+ task in one lane and an open task in a different lane -- ordering across lanes must
114
+ come from lane sequencing, not a raw dependency edge spanning two streaks.
115
+ - **Mutex resources co-laned**: tasks that contend for the same mutual-exclusion
116
+ resource (a resource only one change may hold at a time -- e.g. the same submodule
117
+ pointer, a shared version/manifest field, or the same test fixture) share one `streak`
118
+ and are never split across lanes.
119
+ - **Effort under threshold**: for each lane, `effort = (sum of size points over the
120
+ lane's tasks, S=1/M=2/L=4) x (max model weight in the lane, cheap=1/standard=10/
121
+ premium=20)` stays at or under the effort threshold constant (default `200`). A lane
122
+ over threshold is a finding unless it was split at a `blocks`-edge boundary without
123
+ separating mutex-resource members (per `planner.md`'s splitting math).
124
+ A violation of any bullet above is CHANGES_NEEDED referencing "criterion 11" and the
125
+ specific lane/task IDs involved.
69
126
 
70
127
  ## Step 3 -- Classify each task
71
128
 
@@ -91,7 +148,7 @@ Return your verdict:
91
148
  - `notes`: specific, actionable findings referencing beads IDs
92
149
  - `taskAssignments`: array with one entry per open task -- `{ id, bucket, model }`
93
150
 
94
- **APPROVED** means all ten criteria in Step 2 pass.
151
+ **APPROVED** means all eleven criteria in Step 2 pass.
95
152
 
96
153
  **CHANGES_NEEDED** means one or more criteria fail. Notes must name the specific beads ID
97
154
  and what is wrong. Do not return CHANGES_NEEDED for minor style preferences.
@@ -40,6 +40,32 @@ Also read any requirementsFile or design docs mentioned in your task.
40
40
  Run `git log --oneline -10` to understand what the codebase already has.
41
41
  Read key source files to understand existing conventions and structure.
42
42
 
43
+ Also check for carry-over regression failures left by a previous sprint:
44
+
45
+ ```bash
46
+ bd search "[carry-over]"
47
+ ```
48
+
49
+ A prior sprint's Regression Test phase files its failures as STANDALONE,
50
+ PARENT-LESS beads titled `[regression][carry-over] <description>` -- deliberately
51
+ outside any sprint's scope tree, so a regression failure never blocks the sprint
52
+ that found it. That also means nothing pulls them into a new sprint automatically:
53
+ you are the only discovery point. Read each open one (`bd show <id>`), and for any
54
+ that is in scope for this sprint's goals, adopt it by parenting it under the sprint
55
+ goal (`bd update <id> --parent <sprint-id>`) so it becomes real, gated sprint work.
56
+ Leave the rest parent-less for a later sprint; do not close a carry-over bead you
57
+ are not adopting.
58
+
59
+ Two things about that search, both verified against the real `bd` CLI:
60
+
61
+ - It matches the `[carry-over]` tag anywhere in the title, so the doubled
62
+ `[regression][carry-over] ...` prefix the runner files under is found
63
+ correctly -- you do not need to quote, escape, or search for `[regression]`
64
+ separately.
65
+ - It EXCLUDES closed issues by default, which is what you want: a carry-over
66
+ that a previous sprint already adopted and fixed will not resurface here. Add
67
+ `--status all` only if you are auditing history rather than scoping work.
68
+
43
69
  ## Step 2 -- Decompose sprint goals into features
44
70
 
45
71
  For each sprint goal create type=feature issues as direct children:
@@ -50,6 +76,14 @@ For each sprint goal create type=feature issues as direct children:
50
76
  `bd dep add <sprint-id> <feature-id>`; see the graph-semantics section above)
51
77
 
52
78
  Each feature must be independently verifiable: integration tests either pass or fail.
79
+ This bead-graph rule is not feature-exclusive and applies regardless of who or
80
+ what later verifies it: a bead with children only closes once every child is
81
+ closed AND it is independently verified -- for ANY issue_type, not just
82
+ type=feature. A `type=task` container you nest sub-tasks under, or a bug,
83
+ becomes a verify-gated unit the same way a feature does, the moment it has
84
+ children. Only true leaf beads (no children) close directly. Keep this in mind
85
+ when deciding whether to nest sub-tasks under a task/bug at all, versus making
86
+ them independent siblings.
53
87
 
54
88
  ## Step 3 -- Decompose features into tasks
55
89
 
@@ -89,6 +123,40 @@ Pick the tier using these criteria:
89
123
  Pick from the models actually available in the current environment. A user override
90
124
  always wins.
91
125
 
126
+ **Streak lane metadata** (required on every task, both impl and test): in addition to
127
+ `model`, record two lane fields through the SAME beads metadata channel at creation time --
128
+ never in `--notes`, a METADATA-section comment, or anywhere else:
129
+ ```bash
130
+ bd create ... --metadata '{"model": "<cheap|standard|premium>", "streak": "<lane-id>", "streakOrder": <n>}'
131
+ ```
132
+ - `streak` -- a stable lane identifier (any short opaque string) shared by every task the
133
+ planner wants dispatched together, as one cohesive unit, to a single doer. Consumers --
134
+ including the orchestrator that assembles dispatch rounds -- read it back from this same
135
+ metadata field via `bd show <id>` (the `streak` key), exactly like `model`.
136
+ - `streakOrder` -- an integer giving this task's intended position within its lane. Lower
137
+ runs first; ties fall back to the existing `blocks` edges (see the graph-semantics
138
+ section above).
139
+
140
+ Group tasks into lanes for high cohesion, following these rules:
141
+ - An `[impl]` task and its paired `[test]` task co-streak by default (they share one
142
+ `streak`), so the doer that writes the code also runs its test in the same session.
143
+ - Tasks that contend for a **mutex resource** -- a resource only one change may hold at a
144
+ time, e.g. the same submodule pointer, a shared version/manifest field, or the same test
145
+ fixture -- MUST share a lane and MUST NOT be separated into different streaks.
146
+
147
+ **Effort-point splitting math.** Before finalizing a lane, size it so a single streak stays
148
+ within one doer's reach:
149
+ - size points per task: `S=1`, `M=2`, `L=4`
150
+ - model weight per tier: `cheap=1`, `standard=10`, `premium=20`
151
+ - `effort = (sum of size points over the lane's tasks) x (max model weight in the lane)`
152
+
153
+ If a lane's `effort` exceeds the effort threshold constant (default `200`), split it into
154
+ two or more streaks. Split ONLY at a `blocks`-edge boundary -- so each resulting streak is a
155
+ contiguous prefix/suffix of the dependency order, never an arbitrary mid-lane cut -- and
156
+ NEVER separate mutex-resource members (above) across the split, even if honoring that leaves
157
+ a streak over threshold. Give each split streak a fresh `streak` id and renumber
158
+ `streakOrder` from the start within it.
159
+
92
160
  Wire dependencies (semantics: `bd dep add A B` means A is blocked by B -- B must finish before A can close):
93
161
  - `bd create ... --parent <feature-id>` for both impl and test tasks (grouping only --
94
162
  do NOT `bd dep add <feature-id> <impl-task>` or `<feature-id> <test-task>`; a feature's
@@ -100,27 +168,34 @@ Wire dependencies (semantics: `bd dep add A B` means A is blocked by B -- B must
100
168
 
101
169
  ## Step 4 -- Validate your own DAG
102
170
 
103
- Before finishing, run (scoped to your sprint -- see the graph-semantics section above for
104
- why bare `bd ready`/`bd blocked` are the wrong check):
171
+ Before finishing, run these PER SPRINT ROOT (if you were given more than one sprint goal,
172
+ run each and reason over the COMBINED result -- `--parent` takes exactly one id per call;
173
+ see the graph-semantics section above for why bare `bd ready`/`bd blocked` are the wrong
174
+ check):
105
175
  ```bash
106
- bd graph --compact <sprint-id>
107
- bd blocked --parent <sprint-id>
108
- bd list --parent <sprint-id> --ready --json
176
+ bd graph --compact <root-id>
177
+ bd blocked --parent <root-id>
178
+ bd list --parent <root-id> --ready --type=task --json
109
179
  ```
110
180
 
111
- **Acyclicity check (mandatory):** A correct DAG has no cycles. Verify:
112
- 1. `bd list --parent <sprint-id> --ready --json` must return at least one issue whenever
113
- open work exists under `<sprint-id>`. If it returns nothing, there is a cycle -- every
114
- issue is blocked by another. Find and break the cycle before finishing. (A bare `bd
115
- ready` is NOT a valid substitute for this check -- it returns project-wide results and
116
- will show unrelated ready work even when your entire sprint scope is deadlocked.)
181
+ **Acyclicity check (mandatory):** A correct DAG has no cycles. The invariant is on the
182
+ UNION of ready work across all roots, NOT each root alone. Verify:
183
+ 1. The COMBINED `--ready` list across all sprint roots must contain at least one issue
184
+ whenever open work exists anywhere in scope. If the union is empty while open work
185
+ remains, there is a cycle -- find and break it before finishing. A SINGLE root whose
186
+ own `--ready` list is empty is FINE when its open tasks are legitimately blocked by an
187
+ open task in a DIFFERENT root (a cross-goal ordering edge) -- that is not a cycle, do
188
+ NOT remove the edge. (A bare `bd ready` is NOT a valid substitute -- it returns
189
+ project-wide results and will show unrelated ready work even when your entire sprint
190
+ scope is deadlocked.)
117
191
  2. A feature/task must NEVER have a `blocks` edge to or from its own `--parent`
118
192
  ancestor/descendant -- see the graph-semantics section above. Only `parent-child` edges
119
193
  (via `--parent`) should exist between a bead and its parent; `blocks` edges belong only
120
194
  between siblings.
121
- 3. Check `bd blocked --parent <sprint-id>` -- every blocked issue must be blocked by
122
- something that is itself unblocked (eventually reachable from the scoped `--ready`
123
- list). If a blocked issue traces back to itself, that is a cycle.
195
+ 3. Check `bd blocked --parent <root-id>` for each root -- every blocked issue must be
196
+ blocked by something that is itself unblocked (eventually reachable from the union
197
+ `--ready` list, possibly in another root). Only if a blocked issue traces back to
198
+ itself is that a cycle.
124
199
 
125
200
  If you find a cycle: remove the offending dependency with `bd dep remove <A> <B>`, fix the
126
201
  direction, and re-run the scoped `--ready` query to confirm issues are unblocked.
@@ -131,6 +206,8 @@ Also check each open feature:
131
206
  - No task spans more than ~3 file changes?
132
207
  - Test tasks are downstream of implementation tasks?
133
208
  - Every task has a model tier set via `--metadata '{"model": "..."}'` (see Step 3)?
209
+ - Every task carries `streak` and `streakOrder` lane metadata (see Step 3)? Impl/test
210
+ pairs and mutex-resource members co-laned, and no lane's effort exceeds the threshold?
134
211
 
135
212
  Fix any gaps, then confirm you are done.
136
213
 
@@ -157,3 +234,6 @@ evaluates against its own Output schema (see `plan-reviewer.md` and its sibling
157
234
  - Every task must be completable in one agent session
158
235
  - A task with no acceptance criteria is incomplete -- fix it before finishing
159
236
  - Every task must carry a model tier in `--metadata '{"model": "..."}'` -- fix before finishing
237
+ - Every task must carry `streak`/`streakOrder` lane metadata alongside `model` in the same
238
+ `--metadata` channel; lanes must respect the effort threshold and never split
239
+ mutex-resource members apart -- fix before finishing