@wildo-ai/framework-knowledge 1.1.8 → 1.1.10

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 (480) hide show
  1. package/dist/claude-marketplace/.claude-plugin/marketplace.json +1 -1
  2. package/dist/claude-marketplace/plugins/wildo/.claude-plugin/plugin.json +1 -1
  3. package/dist/claude-marketplace/plugins/wildo/references/acceptance.md +11 -0
  4. package/dist/claude-marketplace/plugins/wildo/references/composites-and-the-loop.md +9 -2
  5. package/dist/claude-marketplace/plugins/wildo/references/creation-state.md +21 -0
  6. package/dist/claude-marketplace/plugins/wildo/references/derived-artifacts.md +121 -0
  7. package/dist/claude-marketplace/plugins/wildo/references/expert-personas-and-deliberations.md +26 -7
  8. package/dist/claude-marketplace/plugins/wildo/references/runs-judges-and-questions.md +31 -5
  9. package/dist/claude-marketplace/plugins/wildo/skills/accept/SKILL.md +4 -2
  10. package/dist/claude-marketplace/plugins/wildo/skills/answer/SKILL.md +29 -2
  11. package/dist/claude-marketplace/plugins/wildo/skills/build/SKILL.md +69 -24
  12. package/dist/claude-marketplace/plugins/wildo/skills/doctor/SKILL.md +10 -0
  13. package/dist/claude-marketplace/plugins/wildo/skills/run/SKILL.md +21 -5
  14. package/dist/claude-marketplace/plugins/wildo/skills/start/SKILL.md +31 -5
  15. package/dist/claude-marketplace/plugins/wildo/skills/status/SKILL.md +2 -0
  16. package/dist/claude-marketplace/plugins/wildo/skills/why/SKILL.md +20 -4
  17. package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
  18. package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
  19. package/dist/esm/framework-knowledge.definitions.js +95 -5
  20. package/dist/esm/framework-knowledge.definitions.js.map +1 -1
  21. package/dist/esm/framework-knowledge.loader.d.ts.map +1 -1
  22. package/dist/esm/index.d.ts.map +1 -1
  23. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +2 -2
  24. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts.map +1 -1
  25. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +2 -2
  26. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -1
  27. package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts +11 -11
  28. package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts.map +1 -1
  29. package/dist/esm/playbooks/bottom_up.build/playbook.definition.js +29 -22
  30. package/dist/esm/playbooks/bottom_up.build/playbook.definition.js.map +1 -1
  31. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +41 -3
  32. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts.map +1 -1
  33. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +175 -14
  34. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
  35. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +1 -1
  36. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts.map +1 -1
  37. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +3 -3
  38. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
  39. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +1 -1
  40. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +1 -1
  41. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
  42. package/dist/esm/playbooks/bottom_up.conception/playbook.definition.d.ts +8 -4
  43. package/dist/esm/playbooks/bottom_up.conception/playbook.definition.d.ts.map +1 -1
  44. package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js +13 -6
  45. package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js.map +1 -1
  46. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +4 -2
  47. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
  48. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +90 -13
  49. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
  50. package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.d.ts +4 -3
  51. package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.d.ts.map +1 -1
  52. package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.js +4 -3
  53. package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.js.map +1 -1
  54. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +8 -0
  55. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
  56. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +12 -4
  57. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
  58. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts +12 -3
  59. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts.map +1 -1
  60. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js +8 -4
  61. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js.map +1 -1
  62. package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.d.ts +4 -1
  63. package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.d.ts.map +1 -1
  64. package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.js +2 -1
  65. package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.js.map +1 -1
  66. package/dist/esm/playbooks/cross_cutting.application-creation/playbook.definition.d.ts.map +1 -1
  67. package/dist/esm/playbooks/cross_cutting.compliance/playbook.definition.d.ts.map +1 -1
  68. package/dist/esm/playbooks/cross_cutting.feature-development/playbook.definition.d.ts.map +1 -1
  69. package/dist/esm/playbooks/cross_cutting.refinement/playbook.definition.d.ts.map +1 -1
  70. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts.map +1 -1
  71. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts +1 -1
  72. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts.map +1 -1
  73. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js +13 -1
  74. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js.map +1 -1
  75. package/dist/esm/playbooks/refinement.feature-contribution/playbook.definition.d.ts.map +1 -1
  76. package/dist/esm/playbooks/refinement.governance-document-candidate/playbook.definition.d.ts.map +1 -1
  77. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +25 -27
  78. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
  79. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +91 -43
  80. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
  81. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts +41 -0
  82. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts.map +1 -0
  83. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js +43 -0
  84. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js.map +1 -0
  85. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts +200 -0
  86. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts.map +1 -0
  87. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js +203 -0
  88. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js.map +1 -0
  89. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts +81 -0
  90. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts.map +1 -0
  91. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js +93 -0
  92. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js.map +1 -0
  93. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +3 -1
  94. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
  95. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +27 -18
  96. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
  97. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts.map +1 -1
  98. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +11 -1
  99. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -1
  100. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +11 -11
  101. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -1
  102. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +2 -0
  103. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -1
  104. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +3 -1
  105. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
  106. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts.map +1 -1
  107. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +2 -0
  108. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
  109. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +3 -1
  110. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
  111. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts.map +1 -1
  112. package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts +5 -2
  113. package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts.map +1 -1
  114. package/dist/esm/playbooks/top_down.definition/playbook.definition.js +16 -4
  115. package/dist/esm/playbooks/top_down.definition/playbook.definition.js.map +1 -1
  116. package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.d.ts +27 -6
  117. package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.d.ts.map +1 -1
  118. package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.js +32 -12
  119. package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.js.map +1 -1
  120. package/dist/esm/playbooks/top_down.feature-drafts/playbook.definition.d.ts.map +1 -1
  121. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts.map +1 -1
  122. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.d.ts.map +1 -1
  123. package/dist/esm/playbooks/top_down.market-research/playbook.definition.d.ts.map +1 -1
  124. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts +2 -1
  125. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts.map +1 -1
  126. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js +13 -5
  127. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js.map +1 -1
  128. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +7 -3
  129. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
  130. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +71 -2
  131. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
  132. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts +2 -1
  133. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts.map +1 -1
  134. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js +23 -8
  135. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js.map +1 -1
  136. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts +7 -1
  137. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts.map +1 -1
  138. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js +4 -2
  139. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js.map +1 -1
  140. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +9 -3
  141. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
  142. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +3 -3
  143. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
  144. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts.map +1 -1
  145. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +35 -2
  146. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
  147. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +41 -17
  148. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
  149. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
  150. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +1 -1
  151. package/dist/knowledge/manifest.json +8 -8
  152. package/dist/knowledge/playbooks/bottom_up.assemble-verify/method.md +22 -7
  153. package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +3 -3
  154. package/dist/knowledge/playbooks/bottom_up.build/method.md +17 -15
  155. package/dist/knowledge/playbooks/bottom_up.build/playbook.json +4 -3
  156. package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-protocol.json +1 -1
  157. package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-treatment.json +1 -1
  158. package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +261 -34
  159. package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +42 -4
  160. package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +188 -59
  161. package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +2 -2
  162. package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +169 -276
  163. package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +2 -2
  164. package/dist/knowledge/playbooks/bottom_up.capability-composition/method.md +8 -1
  165. package/dist/knowledge/playbooks/bottom_up.capability-composition/playbook.json +1 -1
  166. package/dist/knowledge/playbooks/bottom_up.conception/method.md +3 -2
  167. package/dist/knowledge/playbooks/bottom_up.conception/playbook.json +11 -3
  168. package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-protocol.json +1 -1
  169. package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-treatment.json +1 -1
  170. package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +129 -17
  171. package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +7 -4
  172. package/dist/knowledge/playbooks/bottom_up.experience-plan/method.md +28 -6
  173. package/dist/knowledge/playbooks/bottom_up.experience-plan/playbook.json +5 -4
  174. package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +13 -5
  175. package/dist/knowledge/playbooks/bottom_up.placement-plan/method.md +50 -0
  176. package/dist/knowledge/playbooks/bottom_up.placement-plan/playbook.json +16 -4
  177. package/dist/knowledge/playbooks/bottom_up.website-plan/method.md +19 -0
  178. package/dist/knowledge/playbooks/bottom_up.website-plan/playbook.json +5 -2
  179. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +7 -3
  180. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +1 -1
  181. package/dist/knowledge/playbooks/refinement.document-facts/method.md +8 -0
  182. package/dist/knowledge/playbooks/refinement.document-facts/playbook.json +3 -2
  183. package/dist/knowledge/playbooks/refinement.feature-contribution/method.md +5 -2
  184. package/dist/knowledge/playbooks/refinement.feature-contribution/playbook.json +1 -1
  185. package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-protocol.json +1 -1
  186. package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-treatment.json +1 -1
  187. package/dist/knowledge/playbooks/top_down.brand-identity/method.md +75 -37
  188. package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +35 -38
  189. package/dist/knowledge/playbooks/top_down.brand-name-research/method.md +145 -0
  190. package/dist/knowledge/playbooks/top_down.brand-name-research/playbook.json +57 -0
  191. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-protocol.json +1 -0
  192. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-treatment.json +1 -0
  193. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/method.md +99 -0
  194. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/playbook.json +65 -0
  195. package/dist/knowledge/playbooks/top_down.brand-naming/method.md +56 -0
  196. package/dist/knowledge/playbooks/top_down.brand-naming/playbook.json +76 -0
  197. package/dist/knowledge/playbooks/top_down.business-model/evaluation-protocol.json +1 -1
  198. package/dist/knowledge/playbooks/top_down.business-model/evaluation-treatment.json +1 -1
  199. package/dist/knowledge/playbooks/top_down.business-model/method.md +60 -6
  200. package/dist/knowledge/playbooks/top_down.business-model/playbook.json +15 -10
  201. package/dist/knowledge/playbooks/top_down.capability-map/method.md +10 -9
  202. package/dist/knowledge/playbooks/top_down.capability-map/playbook.json +1 -1
  203. package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +30 -10
  204. package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +3 -1
  205. package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +4 -1
  206. package/dist/knowledge/playbooks/top_down.definition/method.md +8 -3
  207. package/dist/knowledge/playbooks/top_down.definition/playbook.json +6 -4
  208. package/dist/knowledge/playbooks/top_down.expert-personas/playbook.json +16 -2
  209. package/dist/knowledge/playbooks/top_down.feature-drafts/method.md +5 -2
  210. package/dist/knowledge/playbooks/top_down.feature-drafts/playbook.json +1 -1
  211. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/evaluation-protocol.json +1 -1
  212. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/evaluation-treatment.json +1 -1
  213. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/method.md +26 -0
  214. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/playbook.json +4 -2
  215. package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-protocol.json +1 -1
  216. package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-treatment.json +1 -1
  217. package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +11 -1
  218. package/dist/knowledge/playbooks/top_down.requirements-definition/evaluation-protocol.json +1 -1
  219. package/dist/knowledge/playbooks/top_down.requirements-definition/evaluation-treatment.json +1 -1
  220. package/dist/knowledge/playbooks/top_down.requirements-definition/method.md +84 -9
  221. package/dist/knowledge/playbooks/top_down.requirements-definition/playbook.json +6 -3
  222. package/dist/knowledge/playbooks/top_down.risk-register/method.md +21 -0
  223. package/dist/knowledge/playbooks/top_down.risk-register/playbook.json +8 -2
  224. package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +4 -2
  225. package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +29 -0
  226. package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +58 -17
  227. package/dist/knowledge/references/brand.name-choice.config.md +144 -0
  228. package/dist/knowledge/references/brand.name-screening.config.md +308 -0
  229. package/dist/knowledge/references/build-plan.task-graph.config.md +119 -11
  230. package/dist/knowledge/references/business-model.pricing-plan.config.md +16 -0
  231. package/dist/knowledge/references/business-model.snapshot.config.md +64 -0
  232. package/dist/knowledge/references/business-model.snapshot.validation.md +68 -4
  233. package/dist/knowledge/references/capability-composition.config.md +67 -4
  234. package/dist/knowledge/references/companion.market.prompt-renderer.md +11 -6
  235. package/dist/knowledge/references/example.authorization.application-roles.office-and-field.md +44 -0
  236. package/dist/knowledge/references/example.backend.custom-operation.audit-event.md +81 -0
  237. package/dist/knowledge/references/example.backend.custom-operation.child-line-total.md +258 -0
  238. package/dist/knowledge/references/example.backend.custom-operation.computed-total.md +153 -0
  239. package/dist/knowledge/references/example.backend.custom-operation.create-related-resource.md +107 -0
  240. package/dist/knowledge/references/example.data-seeding.minimal.md +39 -10
  241. package/dist/knowledge/references/example.data-seeding.row-reference.md +80 -0
  242. package/dist/knowledge/references/example.email.template.minimal.md +1 -1
  243. package/dist/knowledge/references/example.resource.config-wiring.retention-policy-operations.md +74 -0
  244. package/dist/knowledge/references/example.resource.personal-data.free-text-field.md +19 -0
  245. package/dist/knowledge/references/example.resource.personal-data.person-without-account.md +27 -0
  246. package/dist/knowledge/references/example.resource.status-lifecycle.quote.md +152 -0
  247. package/dist/knowledge/references/example.resource.ui-behavior.filter-presets.md +15 -0
  248. package/dist/knowledge/references/example.resource.ui-behavior.operation-icon.md +8 -0
  249. package/dist/knowledge/references/example.views.app-level.home-definition.md +13 -0
  250. package/dist/knowledge/references/example.views.chart-definition.shared.md +83 -0
  251. package/dist/knowledge/references/experience-plan.config.md +60 -7
  252. package/dist/knowledge/references/market.context-block.builder.md +1 -1
  253. package/dist/knowledge/references/market.snapshot.validation.md +1 -1
  254. package/dist/knowledge/references/placement-plan.config.md +43 -0
  255. package/dist/knowledge/references/requirements.functional-requirement.config.md +8 -2
  256. package/dist/knowledge/references/requirements.non-functional-requirement.config.md +2 -0
  257. package/dist/knowledge/references/requirements.references.conventions.md +1 -1
  258. package/dist/knowledge/references/requirements.snapshot.config.md +57 -1
  259. package/dist/knowledge/references/requirements.snapshot.validation.md +35 -1
  260. package/dist/knowledge/references/saas.backend.audit-logs.log-event.md +63 -0
  261. package/dist/knowledge/references/saas.backend.document-sequence.issue-in-operation.md +60 -0
  262. package/dist/knowledge/references/saas.backend.document-sequence.raise-floor.md +156 -0
  263. package/dist/knowledge/references/saas.backend.email.send.md +77 -0
  264. package/dist/knowledge/references/saas.backend.notifications.operation-email-template-ref.md +60 -0
  265. package/dist/knowledge/references/saas.data-seeding.bootstrap-wiring.md +7 -1
  266. package/dist/knowledge/references/saas.data-seeding.computed-entry.md +43 -0
  267. package/dist/knowledge/references/saas.data-seeding.definition-input.md +14 -2
  268. package/dist/knowledge/references/saas.data-seeding.row-reference.md +93 -0
  269. package/dist/knowledge/references/saas.frontend.collection-filter-presets.md +124 -0
  270. package/dist/knowledge/references/saas.frontend.launcher.item-refs.md +316 -0
  271. package/dist/knowledge/references/saas.frontend.launcher.merge-rules.md +106 -0
  272. package/dist/knowledge/references/saas.frontend.launcher.runtime-availability.md +60 -0
  273. package/dist/knowledge/references/saas.frontend.resource-label-params.md +52 -0
  274. package/dist/knowledge/references/saas.frontend.resource-operation-frontend-config.md +47 -18
  275. package/dist/knowledge/references/saas.frontend.resource-ui-behavior-config.md +4 -1
  276. package/dist/knowledge/references/saas.frontend.settings-hub.engine-destination-roles.md +25 -0
  277. package/dist/knowledge/references/saas.frontend.settings-hub.placement.md +2 -2
  278. package/dist/knowledge/references/saas.models.audit.trail-config.md +45 -0
  279. package/dist/knowledge/references/saas.models.notifications.user-notification-definition.md +5 -3
  280. package/dist/knowledge/references/saas.models.queue.scheduled-recovery.md +81 -2
  281. package/dist/knowledge/references/saas.models.resource-config.builder-parameters.md +26 -0
  282. package/dist/knowledge/references/saas.models.roles.definition.md +61 -0
  283. package/dist/knowledge/references/saas.models.roles.organization-defaults.md +97 -0
  284. package/dist/knowledge/references/saas.public-runtime.contract.md +26 -0
  285. package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +10 -0
  286. package/dist/knowledge/references/saas.website.astro.bridge.md +10 -0
  287. package/dist/knowledge/references/saas.website.astro.label-loader.md +12 -0
  288. package/dist/knowledge/references/saas.website.astro.llms-txt-server.md +14 -1
  289. package/dist/knowledge/references/saas.website.astro.site-context.md +13 -0
  290. package/dist/knowledge/references/saas.website.blog.bridge.md +4 -0
  291. package/dist/knowledge/references/saas.website.config.site-context-loader.md +3 -0
  292. package/dist/knowledge/references/saas.website.factories.define-section.md +4 -0
  293. package/dist/knowledge/references/saas.website.legal.public-document-links.md +76 -0
  294. package/dist/knowledge/references/saas.website.page-manifest.schema.md +12 -3
  295. package/dist/knowledge/references/saas.website.page-sections.component.md +72 -0
  296. package/dist/knowledge/references/saas.website.root-config.seo.md +2 -1
  297. package/dist/knowledge/references/saas.website.runtime.context.md +7 -0
  298. package/dist/knowledge/references/saas.website.sections.definition-schema.md +11 -0
  299. package/dist/knowledge/references/saas.website.seo.llms-txt-config.md +2 -0
  300. package/dist/knowledge/references/website-plan.config.md +26 -0
  301. package/dist/knowledge/references/zod.decorators.chainable-runtime.md +13 -0
  302. package/dist/knowledge/references/zod.decorators.decorator-vocabulary.md +7 -0
  303. package/dist/knowledge/references/zod.decorators.document-sequence.md +65 -0
  304. package/dist/knowledge/references/zod.decorators.schema-metadata.md +1 -0
  305. package/dist/knowledge/references/zod.decorators.shared-structural-methods.md +21 -0
  306. package/dist/knowledge/references/zod.factories.bigdecimal.md +1 -0
  307. package/dist/knowledge/references/zod.factories.code.md +1 -0
  308. package/dist/knowledge/references/zod.factories.duration.md +1 -0
  309. package/dist/knowledge/references/zod.factories.money.md +1 -0
  310. package/dist/knowledge/registries/assurance-authority-bases.json +1 -1
  311. package/dist/knowledge/registries/framework-topics.json +374 -1
  312. package/dist/knowledge/registries/playbooks.json +76 -28
  313. package/dist/knowledge/registries/source-tags.json +1513 -898
  314. package/dist/knowledge/rules/live-context-door.md +5 -2
  315. package/dist/knowledge/skills/INDEX.md +5 -2
  316. package/dist/knowledge/skills/application-consumer-documentation-authoring/SKILL.md +16 -3
  317. package/dist/knowledge/skills/application-database-migrations/SKILL.md +14 -3
  318. package/dist/knowledge/skills/application-roles-authoring/SKILL.md +158 -0
  319. package/dist/knowledge/skills/application-roles-authoring/references/framework-application-roles-api.md +169 -0
  320. package/dist/knowledge/skills/application-roles-authoring/references/office-and-field-worked-example.md +63 -0
  321. package/dist/knowledge/skills/authorization-unit-narrowing/SKILL.md +6 -1
  322. package/dist/knowledge/skills/backend-custom-operation/SKILL.md +256 -9
  323. package/dist/knowledge/skills/backend-custom-operation/references/after-the-operation.md +42 -0
  324. package/dist/knowledge/skills/backend-custom-operation/references/framework-audit-log-event-api.md +220 -0
  325. package/dist/knowledge/skills/brand-logo-authoring/SKILL.md +5 -0
  326. package/dist/knowledge/skills/brand-name-screening/SKILL.md +178 -0
  327. package/dist/knowledge/skills/brand-name-screening/references/framework-brand-name-screening-api.md +466 -0
  328. package/dist/knowledge/skills/brand-name-screening/references/screening-procedure.md +87 -0
  329. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +7 -3
  330. package/dist/knowledge/skills/config-app-shell/SKILL.md +58 -5
  331. package/dist/knowledge/skills/config-app-shell/references/framework-launcher-items-api.md +461 -0
  332. package/dist/knowledge/skills/config-app-shell/references/framework-launcher-visibility-api.md +80 -0
  333. package/dist/knowledge/skills/config-design-system/SKILL.md +28 -6
  334. package/dist/knowledge/skills/config-navigation/SKILL.md +14 -3
  335. package/dist/knowledge/skills/config-saas/SKILL.md +56 -15
  336. package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +65 -2
  337. package/dist/knowledge/skills/config-saas/references/framework-audit-trail-config-api.md +62 -2
  338. package/dist/knowledge/skills/config-saas/references/framework-background-work-api.md +81 -2
  339. package/dist/knowledge/skills/config-saas-backend/SKILL.md +6 -1
  340. package/dist/knowledge/skills/configure-billing/SKILL.md +18 -4
  341. package/dist/knowledge/skills/email-add-template/SKILL.md +28 -6
  342. package/dist/knowledge/skills/email-add-template/references/email-artifact-paths.md +1 -1
  343. package/dist/knowledge/skills/email-add-template/references/framework-email-send-api.md +128 -0
  344. package/dist/knowledge/skills/email-add-template/references/framework-operation-email-template-ref-api.md +99 -0
  345. package/dist/knowledge/skills/engine-component-registration/SKILL.md +6 -1
  346. package/dist/knowledge/skills/engine-product-definitions/SKILL.md +21 -8
  347. package/dist/knowledge/skills/flows-actors-chat-assistant/SKILL.md +10 -2
  348. package/dist/knowledge/skills/flows-actors-llm-agent-invocation/SKILL.md +18 -4
  349. package/dist/knowledge/skills/frontend-component-catalog/SKILL.md +11 -3
  350. package/dist/knowledge/skills/frontend-component-catalog/references/framework-component-catalog.md +2 -1
  351. package/dist/knowledge/skills/frontend-component-catalog/references/framework-component-usage.md +8 -0
  352. package/dist/knowledge/skills/i18n-rerun-pipeline/SKILL.md +19 -5
  353. package/dist/knowledge/skills/i18n-translation-rerun/SKILL.md +10 -2
  354. package/dist/knowledge/skills/inbound-channels/SKILL.md +2 -2
  355. package/dist/knowledge/skills/infra-environment-config/SKILL.md +6 -1
  356. package/dist/knowledge/skills/local-environment-bootstrap/SKILL.md +17 -2
  357. package/dist/knowledge/skills/local-environment-bootstrap/references/derived-artifact-currency.md +122 -0
  358. package/dist/knowledge/skills/local-environment-bootstrap/references/framework-upgrade-and-dependency-alignment.md +11 -0
  359. package/dist/knowledge/skills/local-environment-bootstrap/references/wildo-cli-bootstrap-commands.md +9 -2
  360. package/dist/knowledge/skills/market-add-feature-benefit/SKILL.md +10 -2
  361. package/dist/knowledge/skills/market-alternatives/SKILL.md +10 -2
  362. package/dist/knowledge/skills/market-authoring-overview/SKILL.md +10 -2
  363. package/dist/knowledge/skills/market-category/SKILL.md +21 -7
  364. package/dist/knowledge/skills/market-channels/SKILL.md +6 -1
  365. package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +22 -4
  366. package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +12 -2
  367. package/dist/knowledge/skills/market-generation-cli/SKILL.md +21 -11
  368. package/dist/knowledge/skills/market-generation-cli/references/framework-market-generation-cli.md +11 -6
  369. package/dist/knowledge/skills/market-icp/SKILL.md +10 -2
  370. package/dist/knowledge/skills/market-jobs-pains-gains/SKILL.md +6 -1
  371. package/dist/knowledge/skills/market-message-templates-authoring/SKILL.md +6 -1
  372. package/dist/knowledge/skills/market-message-templates-authoring/references/framework-message-template-api.md +1 -1
  373. package/dist/knowledge/skills/market-persona/SKILL.md +14 -3
  374. package/dist/knowledge/skills/market-positioning-authoring/SKILL.md +6 -1
  375. package/dist/knowledge/skills/market-proof-and-objection/SKILL.md +10 -2
  376. package/dist/knowledge/skills/market-scoring-interpretation/SKILL.md +6 -1
  377. package/dist/knowledge/skills/market-snapshot-validation/SKILL.md +15 -4
  378. package/dist/knowledge/skills/market-snapshot-validation/references/framework-snapshot-validation-api.md +1 -1
  379. package/dist/knowledge/skills/market-tone-of-voice/SKILL.md +6 -1
  380. package/dist/knowledge/skills/model-cost-attribution/references/framework-work-unit-api.md +26 -0
  381. package/dist/knowledge/skills/module-companion-exports/SKILL.md +7 -1
  382. package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +10 -0
  383. package/dist/knowledge/skills/module-relationships/SKILL.md +37 -8
  384. package/dist/knowledge/skills/pdf-template-authoring/SKILL.md +4 -2
  385. package/dist/knowledge/skills/provider-address-lookup/SKILL.md +14 -3
  386. package/dist/knowledge/skills/provider-frontend-file-picker/SKILL.md +6 -1
  387. package/dist/knowledge/skills/provider-operation-calls/SKILL.md +14 -3
  388. package/dist/knowledge/skills/rate-limit-authoring/SKILL.md +10 -2
  389. package/dist/knowledge/skills/resource-add-field/SKILL.md +10 -2
  390. package/dist/knowledge/skills/resource-add-field/references/framework-field-cross-layer-api.md +46 -17
  391. package/dist/knowledge/skills/resource-add-resource/SKILL.md +14 -2
  392. package/dist/knowledge/skills/resource-add-resource/references/framework-new-resource-core-config-api.md +26 -0
  393. package/dist/knowledge/skills/resource-config-wiring/SKILL.md +29 -3
  394. package/dist/knowledge/skills/resource-config-wiring/references/framework-collection-operation-declarations.md +19 -4
  395. package/dist/knowledge/skills/resource-config-wiring/references/framework-operation-audit-api.md +5 -2
  396. package/dist/knowledge/skills/resource-config-wiring/references/framework-personal-data-declaration-api.md +103 -0
  397. package/dist/knowledge/skills/resource-config-wiring/references/framework-retention-policy-operations.md +135 -0
  398. package/dist/knowledge/skills/resource-config-wiring/references/framework-saas-models-resource-config-api.md +26 -0
  399. package/dist/knowledge/skills/resource-config-wiring/references/framework-user-notifications-api.md +26 -7
  400. package/dist/knowledge/skills/resource-custom-view/SKILL.md +10 -2
  401. package/dist/knowledge/skills/resource-custom-view/references/custom-view-contracts.md +46 -17
  402. package/dist/knowledge/skills/resource-external-data/references/erasure-suppression.md +2 -2
  403. package/dist/knowledge/skills/resource-retention-binding/SKILL.md +5 -1
  404. package/dist/knowledge/skills/resource-schema-authoring/SKILL.md +15 -1
  405. package/dist/knowledge/skills/resource-schema-authoring/references/computed-totals.md +569 -0
  406. package/dist/knowledge/skills/resource-schema-authoring/references/document-numbers.md +358 -0
  407. package/dist/knowledge/skills/resource-schema-authoring/references/framework-decorator-vocabulary-api.md +8 -0
  408. package/dist/knowledge/skills/resource-schema-authoring/references/framework-shared-decorator-methods-api.md +21 -0
  409. package/dist/knowledge/skills/resource-schema-authoring/references/framework-special-factories-api.md +7 -2
  410. package/dist/knowledge/skills/resource-schema-authoring/references/framework-zod-lifecycle-and-chainable-api.md +13 -0
  411. package/dist/knowledge/skills/resource-status-lifecycle/SKILL.md +153 -0
  412. package/dist/knowledge/skills/resource-status-lifecycle/references/commercial-documents.md +46 -0
  413. package/dist/knowledge/skills/resource-status-lifecycle/references/quote-lifecycle-worked-example.md +198 -0
  414. package/dist/knowledge/skills/resource-ui-behavior/SKILL.md +30 -4
  415. package/dist/knowledge/skills/resource-ui-behavior/references/framework-collection-filter-presets-api.md +157 -0
  416. package/dist/knowledge/skills/resource-ui-behavior/references/framework-frontend-resource-ui-contracts-api.md +101 -19
  417. package/dist/knowledge/skills/seeding-authoring/SKILL.md +202 -39
  418. package/dist/knowledge/skills/seeding-authoring/references/cross-seed-row-references.md +67 -0
  419. package/dist/knowledge/skills/seeding-authoring/references/framework-data-seeding-api.md +154 -4
  420. package/dist/knowledge/skills/seeding-authoring/references/seed-row-overlay.md +22 -0
  421. package/dist/knowledge/skills/seeding-operations/references/framework-data-seeding-operations-api.md +7 -1
  422. package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-destinations-catalog.md +43 -0
  423. package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-placement-api.md +2 -2
  424. package/dist/knowledge/skills/spec-companion-exports/SKILL.md +6 -1
  425. package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +10 -0
  426. package/dist/knowledge/skills/spec-component-update/SKILL.md +10 -2
  427. package/dist/knowledge/skills/spec-composite-view-update/SKILL.md +2 -2
  428. package/dist/knowledge/skills/spec-family-update/SKILL.md +71 -66
  429. package/dist/knowledge/skills/spec-family-update/references/family-spec-routing.md +1 -1
  430. package/dist/knowledge/skills/spec-resource-update/SKILL.md +30 -10
  431. package/dist/knowledge/skills/spec-resource-update/references/resource-spec-field-routing.md +28 -0
  432. package/dist/knowledge/skills/spec-update-after-change/SKILL.md +22 -5
  433. package/dist/knowledge/skills/views-add-composite-view/SKILL.md +6 -1
  434. package/dist/knowledge/skills/views-add-custom-view/SKILL.md +10 -2
  435. package/dist/knowledge/skills/views-app-level/SKILL.md +13 -3
  436. package/dist/knowledge/skills/views-app-level/references/application-home.md +56 -0
  437. package/dist/knowledge/skills/views-chart-authoring/SKILL.md +221 -37
  438. package/dist/knowledge/skills/views-composite-authoring/SKILL.md +22 -5
  439. package/dist/knowledge/skills/views-execution-authoring/SKILL.md +1 -1
  440. package/dist/knowledge/skills/website-anonymous-session/SKILL.md +32 -2
  441. package/dist/knowledge/skills/website-blog-authoring/SKILL.md +16 -3
  442. package/dist/knowledge/skills/website-blog-authoring/references/blog-adapter-api.md +4 -0
  443. package/dist/knowledge/skills/website-bundle-discipline/SKILL.md +7 -1
  444. package/dist/knowledge/skills/website-consent-gate-overrides/SKILL.md +13 -1
  445. package/dist/knowledge/skills/website-factory-advanced/SKILL.md +14 -2
  446. package/dist/knowledge/skills/website-inbound-contact-forms/SKILL.md +13 -1
  447. package/dist/knowledge/skills/website-layout-overrides/SKILL.md +6 -1
  448. package/dist/knowledge/skills/website-marketing-metadata-extension/SKILL.md +19 -1
  449. package/dist/knowledge/skills/website-navigation-authoring/SKILL.md +55 -18
  450. package/dist/knowledge/skills/website-navigation-authoring/references/framework-public-document-links-api.md +98 -0
  451. package/dist/knowledge/skills/website-navigation-authoring/references/worked-examples-header-footer.md +8 -11
  452. package/dist/knowledge/skills/website-page-authoring/SKILL.md +100 -8
  453. package/dist/knowledge/skills/website-page-authoring/references/framework-site-context-loader-api.md +3 -0
  454. package/dist/knowledge/skills/website-primitive-overrides/SKILL.md +6 -1
  455. package/dist/knowledge/skills/website-section-contact/SKILL.md +15 -0
  456. package/dist/knowledge/skills/website-section-contact/references/define-website-section-api.md +15 -0
  457. package/dist/knowledge/skills/website-section-cta/SKILL.md +15 -0
  458. package/dist/knowledge/skills/website-section-cta/references/define-website-section-api.md +15 -0
  459. package/dist/knowledge/skills/website-section-faq/SKILL.md +21 -1
  460. package/dist/knowledge/skills/website-section-faq/references/define-website-section-api.md +15 -0
  461. package/dist/knowledge/skills/website-section-feature-benefit-summary/SKILL.md +21 -1
  462. package/dist/knowledge/skills/website-section-feature-benefit-summary/references/define-website-section-api.md +15 -0
  463. package/dist/knowledge/skills/website-section-feature-detail/SKILL.md +25 -2
  464. package/dist/knowledge/skills/website-section-feature-detail/references/define-website-section-api.md +15 -0
  465. package/dist/knowledge/skills/website-section-footer-cta/SKILL.md +15 -0
  466. package/dist/knowledge/skills/website-section-footer-cta/references/define-website-section-api.md +15 -0
  467. package/dist/knowledge/skills/website-section-hero/SKILL.md +33 -10
  468. package/dist/knowledge/skills/website-section-hero/references/define-website-section-api.md +15 -0
  469. package/dist/knowledge/skills/website-section-pricing/SKILL.md +21 -1
  470. package/dist/knowledge/skills/website-section-pricing/references/define-website-section-api.md +15 -0
  471. package/dist/knowledge/skills/website-section-social-proof/SKILL.md +27 -2
  472. package/dist/knowledge/skills/website-section-social-proof/references/define-website-section-api.md +15 -0
  473. package/dist/knowledge/skills/website-seo-aeo-geo/SKILL.md +16 -4
  474. package/dist/knowledge/skills/website-seo-aeo-geo/references/aeo-api.md +11 -0
  475. package/dist/knowledge/skills/website-seo-aeo-geo/references/geo-api.md +16 -1
  476. package/dist/knowledge/skills/website-seo-aeo-geo/references/seo-api.md +2 -1
  477. package/dist/knowledge/topic-index.json +1590 -292
  478. package/dist/tsconfig.build.tsbuildinfo +1 -1
  479. package/dist/tsconfig.tsbuildinfo +1 -1
  480. package/package.json +4 -4
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-decompose/playbook.definition.ts"],"names":[],"mappings":"AACA,OAAO,EACL,oCAAoC,EACpC,kCAAkC,EAClC,wCAAwC,EACxC,+BAA+B,EAC/B,gCAAgC,EAChC,sCAAsC,EACtC,0CAA0C,EAC1C,6CAA6C,EAC7C,8BAA8B,EAC9B,oCAAoC,EACpC,6BAA6B,GAC9B,MAAM,sCAAsC,CAAC;AAE9C;;;;;;;;;;;;;;;GAeG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,2BAA2B;IAClC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,46DAA46D;IACt7D,eAAe,EAAE;QACf,EAAE,MAAM,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,aAAa,EAAE,EAAE;QACtE;YACE,MAAM,EAAE,mBAAmB;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,gBAAgB,EAAE;YAC1C,IAAI,EAAE,g1BAAg1B;SACv1B;KACF;IACD,QAAQ,EAAE;QACR,EAAE,QAAQ,EAAE,aAAa,EAAE;QAC3B,EAAE,QAAQ,EAAE,SAAS,EAAE;QACvB,EAAE,QAAQ,EAAE,cAAc,EAAE;QAC5B,EAAE,QAAQ,EAAE,gBAAgB,EAAE;QAC9B,EAAE,QAAQ,EAAE,gBAAgB,EAAE;QAC9B,EAAE,QAAQ,EAAE,cAAc,EAAE,IAAI,EAAE,8SAA8S,EAAE;QAClV,EAAE,QAAQ,EAAE,aAAa,EAAE,QAAQ,EAAE,KAAK,EAAE,IAAI,EAAE,2PAA2P,EAAE;QAC/S,EAAE,QAAQ,EAAE,iBAAiB,EAAE,IAAI,EAAE,gYAAgY,EAAE;QACva,EAAE,QAAQ,EAAE,oBAAoB,EAAE,IAAI,EAAE,gPAAgP,EAAE;QAC1R,EAAE,QAAQ,EAAE,kBAAkB,EAAE,IAAI,EAAE,yfAAyf,EAAE;QACjiB,EAAE,QAAQ,EAAE,gBAAgB,EAAE,IAAI,EAAE,qfAAqf,EAAE;QAC3hB,EAAE,QAAQ,EAAE,cAAc,EAAE,IAAI,EAAE,qVAAqV,EAAE;QACzX,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,kMAAkM,EAAE;KACrO;IACD,SAAS,EAAE;QACT;YACE,QAAQ,EAAE,YAAY;YACtB,WAAW,EAAE,wCAAwC;YACrD,aAAa,EAAE,whJAAwhJ;SACxiJ;KACF;IACD,QAAQ,EAAE;QACR,kBAAkB,EAAE,ywBAAywB;QAC7xB,gBAAgB,EAAE,CAAC,iBAAiB,EAAE,eAAe,EAAE,kBAAkB,CAAC;QAC1E,WAAW,EAAE;YACX,qBAAqB;YACrB,uBAAuB;YACvB,2BAA2B;YAC3B,wBAAwB;YACxB,sBAAsB;YACtB,4BAA4B;YAC5B,sBAAsB;YACtB,sBAAsB;YACtB,qBAAqB;YACrB,iCAAiC;SAClC;KACF;IACD,UAAU,EAAE,iBAAiB;IAC7B,UAAU,EAAE,gBAAgB;IAC5B,QAAQ,EAAE;QACR,SAAS,EAAE,CAAC;KACb;IACD,WAAW,EAAE,eAAe;CACpB,CAAC;AAEX,MAAM,CAAC,MAAM,yBAAyB,GAAG;IACvC,aAAa,EAAE,CAAC;IAChB,aAAa,EAAE,+DAA+D;IAC9E,6GAA6G;IAC7G,sGAAsG;IACtG,iBAAiB,EAAE,CAAC;IACpB,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,WAAW,EAAE,8DAA8D;QAC3E,eAAe,EAAE,CAAC;QAClB,sBAAsB,EAAE,6CAA6C,CAAC,8BAA8B;QACpG,mBAAmB,EAAE,0CAA0C,CAAC,2BAA2B;QAC3F,iBAAiB,EAAE,CAAC,8BAA8B,CAAC,GAAG,EAAE,8BAA8B,CAAC,aAAa,EAAE,8BAA8B,CAAC,OAAO,EAAE,8BAA8B,CAAC,IAAI,CAAC;QAClL,oBAAoB,EAAE,oEAAoE;QAC1F;;;;;;;WAOG;QACH,QAAQ,EAAE;YACV;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,wEAAwE;gBACtF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,oxBAAoxB;gBACtxB,eAAe,EAAE,CAAC,iBAAiB,EAAE,oBAAoB,EAAE,sBAAsB,CAAC;gBAClF,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,mFAAmF;wBACnG,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,+FAA+F;oBACtI,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,oMAAoM;oBAC9O,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,wJAAwJ;oBAC9L,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,0GAA0G;iBAC3J;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,6EAA6E;gBAC3F,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,6iCAA6iC;gBAC/iC,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,wFAAwF;wBACxG,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,wIAAwI;oBAC/K,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,mHAAmH;oBAC7J,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,+UAA+U;oBACrX,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,uFAAuF;iBACxI;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,oEAAoE;gBAClF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,wXAAwX;gBAC1X,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,+EAA+E;wBAC/F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,4JAA4J;oBACnM,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,kKAAkK;oBAC5M,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sJAAsJ;oBAC5L,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,6FAA6F;iBAC9I;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,kEAAkE;gBAChF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,qlBAAqlB;gBACvlB,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,6EAA6E;wBAC7F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,sIAAsI;oBAC7K,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,kJAAkJ;oBAC5L,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,6OAA6O;oBACnR,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,6FAA6F;iBAC9I;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,iEAAiE;gBAC/E;;;;;;mBAMG;gBACH,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,ohBAAohB;gBACthB,eAAe,EAAE,CAAC,iBAAiB,EAAE,0BAA0B,CAAC;gBAChE,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,4EAA4E;wBAC5F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,2FAA2F;oBAClI,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,8JAA8J;oBACxM,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,oMAAoM;oBAC1O,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,4DAA4D;iBAC7G;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,2EAA2E;gBACzF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,ylBAAylB;gBAC3lB,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,sFAAsF;wBACtG,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,mJAAmJ;oBAC1L,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,sMAAsM;oBAChP,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,6IAA6I;oBACnL,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,kIAAkI;iBACnL;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,kEAAkE;gBAChF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,+bAA+b;gBACjc,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,6EAA6E;wBAC7F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,yEAAyE;oBAChH,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,2HAA2H;oBACrK,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sGAAsG;oBAC5I,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,kCAAkC;iBACnF;aACF;YACD;;;;;;;eAOG;YACH;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,qDAAqD;gBACnE,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,qzBAAqzB;gBACvzB,eAAe,EAAE,CAAC,iBAAiB,EAAE,oBAAoB,EAAE,sBAAsB,EAAE,0BAA0B,CAAC;gBAC9G,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,gEAAgE;wBAChF,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,qIAAqI;oBAC5K,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,2IAA2I;oBACrL,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sNAAsN;oBAC5P,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,gHAAgH;iBACjK;aACF;SACA;KACF;IACD,sBAAsB,EAAE;QACtB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,mEAAmE;QAC9E,aAAa,EAAE,CAAC;QAChB,4BAA4B,EAAE,CAAC,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE,CAAC;QAC9H,wBAAwB,EAAE,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE;QACxH,sBAAsB,EAAE,EAAE,iBAAiB,EAAE,wEAAwE,EAAE,qBAAqB,EAAE,CAAC,EAAE;QACjJ,iBAAiB,EAAE,mDAAmD;QACtE,mBAAmB,EAAE,+DAA+D;QACpF,eAAe,EAAE,CAAC;QAClB,gBAAgB,EAAE,mEAAmE;QACrF,eAAe,EAAE,iEAAiE;QAClF,kBAAkB,EAAE,gEAAgE;KACrF;IACD,uBAAuB,EAAE;QACvB,aAAa,EAAE,CAAC;QAChB,gBAAgB,EAAE,gEAAgE;QAClF,oBAAoB,EAAE,CAAC;QACvB,WAAW,EAAE,CAAC,qEAAqE,CAAC;QACpF,aAAa,EAAE,CAAC,6DAA6D,CAAC;QAC9E,aAAa,EAAE,2EAA2E;QAC1F,qBAAqB,EAAE,4DAA4D;KACpF;IACD,YAAY,EAAE;QACZ,aAAa,EAAE,CAAC;QAChB,OAAO,EAAE,+DAA+D;QACxE,WAAW,EAAE,CAAC;QACd,aAAa,EAAE,sCAAsC,CAAC,sBAAsB;QAC5E,sBAAsB,EAAE,oEAAoE;QAC5F,cAAc,EAAE;YACd,EAAE,OAAO,EAAE,8BAA8B,CAAC,IAAI,EAAE,WAAW,EAAE,gCAAgC,CAAC,iBAAiB,EAAE;YACjH,EAAE,OAAO,EAAE,8BAA8B,CAAC,OAAO,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACzG,EAAE,OAAO,EAAE,8BAA8B,CAAC,GAAG,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACrG,EAAE,OAAO,EAAE,8BAA8B,CAAC,aAAa,EAAE,WAAW,EAAE,gCAAgC,CAAC,gBAAgB,EAAE;SAC1H;QACD,iBAAiB,EAAE,CAAC;gBAClB,YAAY,EAAE,6DAA6D;gBAC3E,uBAAuB,EAAE,CAAC,wFAAwF,CAAC;aACpH,CAAC;QACF,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;QACnE,wBAAwB,EAAE,KAAK;QAC/B,qBAAqB,EAAE,gCAAgC,CAAC,gBAAgB;QACxE,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;KACpE;IACD,oBAAoB,EAAE;QACpB,aAAa,EAAE,CAAC;QAChB,cAAc,EAAE,uEAAuE;QACvF,kBAAkB,EAAE,CAAC;QACrB,mBAAmB,EAAE,yEAAyE;QAC9F,YAAY,EAAE,+DAA+D;QAC7E,qBAAqB,EAAE,sEAAsE;QAC7F,kBAAkB,EAAE,6DAA6D;QACjF,gBAAgB,EAAE,uDAAuD;QACzE,kBAAkB,EAAE,IAAI;QACxB,oBAAoB,EAAE,kCAAkC,CAAC,8BAA8B;QACvF,gBAAgB,EAAE,oCAAoC,CAAC,gBAAgB;QACvE,gBAAgB,EAAE,CAAC,wCAAwC,CAAC,eAAe,CAAC;QAC5E,+BAA+B,EAAE,CAAC,mFAAmF,CAAC;QACtH,eAAe,EAAE,iEAAiE;QAClF,cAAc,EAAE,yDAAyD;QACzE,gBAAgB,EAAE,6BAA6B,CAAC,YAAY;QAC5D,wBAAwB,EAAE,KAAK;KAChC;IACD,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,8DAA8D;QACzE,aAAa,EAAE,CAAC;QAChB,QAAQ,EAAE;YACR,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,QAAQ,EAAE,MAAM,EAAE,+BAA+B,CAAC,QAAQ,EAAE;YACpH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,MAAM,EAAE,MAAM,EAAE,+BAA+B,CAAC,MAAM,EAAE;YAChH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,gBAAgB,EAAE,MAAM,EAAE,+BAA+B,CAAC,gBAAgB,EAAE;YACpI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,iBAAiB,EAAE,MAAM,EAAE,+BAA+B,CAAC,iBAAiB,EAAE;YACtI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,KAAK,EAAE,MAAM,EAAE,+BAA+B,CAAC,KAAK,EAAE;SAC/G;QACD,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,cAAc,EAAE,+BAA+B,CAAC,KAAK;KACtD;CAC8C,CAAC","sourcesContent":["import type { MetaWorkflowEvaluationTreatmentSource } from '@wildo-ai/saas-backend-lib/meta-workflow-runtime';\nimport {\n MetaWorkflow_AuthorityAssuranceClass,\n MetaWorkflow_AuthorityDecisionMode,\n MetaWorkflow_AuthorityInteractionChannel,\n MetaWorkflow_ContinuationAction,\n MetaWorkflow_DecisionConsequence,\n MetaWorkflow_DecisionRuleBoundaryClass,\n MetaWorkflow_EvaluationAggregationStrategy,\n MetaWorkflow_EvaluationPromptAssemblyStrategy,\n MetaWorkflow_EvaluationVerdict,\n MetaWorkflow_EvidenceRequirementKind,\n MetaWorkflow_HardFloorPosture,\n} from '@wildo-ai/saas-models/meta-workflows';\n\n/**\n * Canonical native declaration for this reusable application-creation method.\n *\n * The structured method remains intentionally rich: its intent, inputs, output\n * contracts, elicitation, deterministic verification and skill routing are the\n * application knowledge a later generic assessment loop composes.\n *\n * The `evaluationTreatmentSource` below is the `build-plan-coherent` reviewer checklist the\n * method carried as prose from the flexible-intelligence hard cut until 2026-09-22 (#1487) —\n * eight invariants that its own closing sentence said \"nothing executes\". Compiled here, the\n * ADVISORY judge reads them against the landed build plan and the domain plan it decomposes,\n * so a resource with no task, a relationship wired before its endpoints, or a product naming\n * only a scaffolded file is reported BEFORE a coding dispatch pays for it. Advisory as\n * everywhere in this lane: the plan is landed when the judge speaks, and a verdict is a note\n * for the creator's `approve_result` review, never a refusal.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-decompose\",\n \"version\": \"0.4.0\",\n \"phase\": \"bottom_up\",\n \"intent\": \"Bottom-up build decomposition — the FIRST build-execution playbook, the pivot from planning the domain (the domain-plan) to decomposing the BUILD. Reads the approved domain-plan (the ModuleBusinessSemantics module drafts + per-module resource inventory), the relationship drafts inside it (the inter-resource relationship intents), and the definition set (roadmap for phasing, requirements + feature-drafts for task-brief context), and the PLACEMENT PLAN (where each settings destination, resource operation and view sits in the shell, decided upstream), and DECOMPOSES the build work into an ordered set of coding-agent tasks. Each task is bound onto (a) the 7-topic functional taxonomy (configure_application_foundation -> model_domain_graph -> define_interaction_semantics -> shape_user_experience -> extend_application -> connect_runtime_and_external_capabilities -> assemble_verify_and_iterate) and (b) the app-knowledge skill catalog (each task names the skill(s) that carry its technical HOW). The tasks follow the per-resource inner order (schema -> config -> ui-behavior -> spec, then operations / interaction semantics, then UX, then extensions, then integrations), with companion-owned generation steps (i18n-labels, email-templates, logo, and database-migrations for applications with an accepted PostgreSQL schema plan) interleaved at the points their inputs exist. This playbook PRODUCES the ordered task graph (a build-plan artifact); it does NOT dispatch tasks to coding agents (that is the dispatch-orchestration playbook downstream), does NOT capture change-sets / single-flight-lock / verify, and does NOT solve multi-agent scale or interleaving. It authors no schemas and generates no code. The typed BuildPlanTaskGraph contract and deterministic validator already exist. Declare prerequisiteTaskRefs explicitly: the host derives readiness from those edges; functionalTopic provides context and skill routing, not an implicit execution order.\",\n \"preconditions\": [\n { \"kind\": \"artifact_exists\", \"selector\": { \"family\": \"domain-plan\" } },\n {\n \"kind\": \"artifact_expected\",\n \"selector\": { \"family\": \"placement-plan\" },\n \"//\": \"SEQUENCING, not readiness — and the distinction is the whole point. `bottom_up.placement-plan` gates on the SAME `domain-plan` this does, so both become eligible at the same instant and decomposing first is legal. This method then says, at its placement section, 'No placement plan? Emit nothing here and say so' — which is honest per task and catastrophic per plan: the build proceeds with ZERO SHELL_PLACEMENT tasks and nothing refuses, so the finished application has no navigation and the cause is three playbooks upstream. `artifact_expected` is the kind written for exactly this (its own doc: use it whenever running early DEGRADES the output rather than invalidating it): the board reports `blocked only by sequencing`, a human may still run it deliberately, and `unmet` finally explains WHY the order matters instead of losing the signal.\"\n }\n ],\n \"inputs\": [\n { \"family\": \"domain-plan\" },\n { \"family\": \"roadmap\" },\n { \"family\": \"requirements\" },\n { \"family\": \"feature-drafts\" },\n { \"family\": \"placement-plan\" },\n { \"family\": \"vision-brief\", \"//\": \"Carries the landed COMPLIANCE POSTURE and constraints. Measured 2026-09-04 (#309): without this input the decomposer, given a landed GDPR/ePrivacy posture, produced ZERO posture-derived tasks — the obligations lived in a family the brief never carried. No intent slice: the posture must arrive whole.\" },\n { \"family\": \"brand-brief\", \"render\": \"map\", \"//\": \"Whether the application HAS a brand decides whether the `logo` generation step is authored (method: companion generation steps; checklist invariant 6). The method only needs to know it exists, so it reads the brand as a map, not its content (#1424).\" },\n { \"family\": \"experience-plan\", \"//\": \"The application's own surfaces and its shell composition (#1493). Each view becomes a task over the product kind its KIND names, each configuration an APPLICATION_FRONTEND_CONFIG task, each planned milestone an APPLICATION_MILESTONE task and each planned piece of guidance an APPLICATION_GUIDANCE task — with the skill taken from the experience plan's total maps, never chosen here.\" },\n { \"family\": \"documentation-plan\", \"//\": \"Which chapters the documentation portal carries (#1494). Each becomes a DOCUMENTATION_CHAPTER task under the TECHNICAL_DOCUMENTATION target, whose scope prohibits the portal's generated tree. A NOT_APPLICABLE plan, or none, emits nothing.\" },\n { \"family\": \"integration-plan\", \"//\": \"What runs beside the backend and what the application reaches out to (#1495). Each worker, minion and provider binding becomes a task over its own target kind, with the skill taken from the three total maps rather than chosen here — which is what makes the worker, minion and provider skills reachable. Each declared inbound channel becomes an INBOUND_CHANNEL_HANDLER task in the module its messages concern (#1832), routed to `inbound-channels` by the dispatch. No plan, or an empty one, emits nothing.\" },\n { \"family\": \"business-model\", \"//\": \"The pricing plans the application sells (#1835). Each becomes a product of the billing catalogue — one BILLING_CATALOG task producing an APPLICATION_BILLING_PRODUCT per plan — so the backend has something to sell and the website's pricing page reads the catalogue instead of re-typing the plans' prices. Measured on the first journey-built application: with no such task its catalogue stayed EMPTY and the website agent hand-copied the prices. No business model, or one with no plans, emits nothing.\" },\n { \"family\": \"website-plan\", \"//\": \"What the marketing site says, page by page (#1492). The decomposer turns each page into a WEBSITE_PAGE task and each section into a WEBSITE_SECTION task bound to the skill its KIND names — so the website skills are reached by construction rather than by a model recalling folder names. A NOT_APPLICABLE plan, or none at all, emits nothing.\" },\n { \"family\": \"build-plan\", \"//\": \"Its own family: its method refines its own prior output and keeps its refs, so it must be GIVEN that output (#1430). Input, not precondition: a first run, with no prior output, stays eligible.\" }\n ],\n \"outputs\": [\n {\n \"family\": \"build-plan\",\n \"schemaRef\": \"saas-specifications:BuildPlanTaskGraph\",\n \"description\": \"The build decomposition — an ORDERED set of coding-agent build tasks (a task graph) that turns the approved domain plan into a sequence of buildable units. Each task carries: a stable task ref, the target it builds (a module, a resource + one of its build stages, a relationship, a companion-generation step, a shell-surface placement config), WHAT IT PRODUCES (`produces` — the artifacts whose presence in the finished application proves the task landed; distinct from the target, which is a write scope several tasks may share), the ONE functional topic it belongs to (a real MetaWorkflow_FunctionalTopic value), the skill(s) that carry its technical HOW (real folders from the app-knowledge skill catalog, resolved via the skills router), and its ordering intent (which tasks must precede it — expressed as typed prerequisiteTaskRefs, which the host resolves for readiness). Author prerequisiteTaskRefs to express the actual dependencies, using these planning considerations: (a) the cross-app topic dependency edges (model_domain_graph before define_interaction_semantics before app-level shape_user_experience before extend_application before connect_runtime_and_external_capabilities; foundation and assemble/verify are owned by sibling playbooks) and (b) the per-resource stage sequence schema -> config -> ui-behavior -> spec — which deliberately CROSSES topics (ui-behavior is shape_user_experience; the spec is a model_domain_graph documentation capstone ordered last) and so is not monotonic on axis (a); a roadmap-driven MVP-first preference breaks ties within a band. TYPED since the flexible-intelligence Block 3: the `_core` build-task-graph contract (`BuildPlanTaskGraph` — `tasks[]` with a stable `taskRef`, a closed `BuildPlanTaskTargetKind` target (MODULE / RESOURCE_STAGE / RELATIONSHIP / COMPANION_GENERATION_STEP / SHELL_PLACEMENT / MODULE_FRONTEND / MODULE_BACKEND / APPLICATION_FRONTEND_CONFIG / WEBSITE / TECHNICAL_DOCUMENTATION / WORKER / MINION / PROVIDER_BINDING / BILLING_CATALOG), a `produces` list over the closed `BuildPlanTaskProductKind` vocabulary (the resource products — schema fields, registration, ui-behavior, specification, relationship, operation, composite / custom / chart view, PDF template; the application products — view, document, module, frontend configuration, custom component, milestone, guidance; and the runtime products — worker jobs, minion behaviours, provider binding, website page and section, documentation chapter, inbound channel handler; and the billing product the catalogue sells), exactly one `functionalTopic`, `skillRefs`, DECLARED `prerequisiteTaskRefs` the host resolves for readiness, and traceability `servesRefs`) is the family schema; the provider answers the strict `BuildPlanTaskGraphGeneration` shape and the trusted runtime stamps refs and version. The task never carries paths, commands, prompts or runtime controls — the dispatch host derives mutation scope and verification from the target kind. `validateBuildPlanTaskGraph` is the deterministic validator. A task's products must name something COMPOSITION DOES NOT ALREADY WRITE (the fields a schema gains, not its scaffolded file) and no two tasks may claim the same artifact — that is what makes landing decidable; a coding task declaring none is reported as `TASK_DECLARES_NO_PRODUCT`. If such a task has a COMPLETED durable run, the host advances past it but reports its ref in `unverifiableLandedTaskRefs`: it ran, but its output is not proven. Without that completed run it remains unlanded. Companion-generation tasks use their own landed conditions; migrations require the schema plan to be in sync. Product probes inspect committed files and named declarations, not runtime correctness. Two things are HARD FLOORS: a prerequisite cycle, and a resource stage that declares its predecessor stage in the SAME graph without depending on it — dispatch order comes solely from `prerequisiteTaskRefs`, so an undeclared stage edge lets the host author a resources-config for a schema that has not landed. A predecessor stage that is ABSENT from the plan is an authoring WARNING instead, because a plan may legitimately author one stage of a resource the tree already carries; the coherence reviewer checklist (`build-plan-coherent`, in the method) remains the semantic check and the creator's approve_result review the trust floor. Consumed by the bottom-up DISPATCH-ORCHESTRATION playbook (which single-flight-dispatches each task through the coding-agent contract) and the SCALE playbook (which parallelises + interleaves the companion generation steps) — both downstream of this decomposition.\"\n }\n ],\n \"method\": {\n \"//contextSources\": \"WORKSPACE_TRUTH — this playbook plans against CODE, not against definition artifacts: it needs real module ids and per-resource present schema fields, or it invents ids that do not resolve and every task it emits fails at dispatch. SKILL_CATALOG — its method routes THROUGH the skills router and binds every emitted task to a skill folder, so it must choose from the real set; measured 2026-08-27 it was choosing from recall, and a dangling skill ref is a task the dispatch playbook cannot run. COHERENCE_REPORT — the computed cross-family findings over the conception it builds on (dangling edges into the domain plan, a composition surface no plan realises), so its judge can tell a conception fault from its own (#1638): the build lane routes the first back to conception.\",\n \"contextSources\": [\"workspace_truth\", \"skill_catalog\", \"coherence_report\"],\n \"skillRefs\": [\n \"resource-add-module\",\n \"resource-add-resource\",\n \"resource-schema-authoring\",\n \"resource-config-wiring\",\n \"resource-ui-behavior\",\n \"frontend-component-catalog\",\n \"spec-resource-update\",\n \"module-relationships\",\n \"module-registration\",\n \"application-database-migrations\"\n ]\n },\n \"executor\": \"companion_agent\",\n \"approval\": \"approve_result\",\n \"budget\": {\n \"maxRuns\": 3\n },\n \"onFailure\": \"keep_and_flag\"\n} as const;\n\nexport const evaluationTreatmentSource = {\n schemaVersion: 1,\n definitionRef: 'application-creation:evaluation-treatment/build-plan-coherent',\n // 2 since #1638: `conception-buildable` faults the CONCEPTION, not the plan, which changes what a GAP means.\n // 3: relationship coverage leaves a relationship to an undeclared resource to `conception-buildable`.\n definitionVersion: 3,\n evaluationProtocol: {\n schemaVersion: 1,\n protocolRef: 'application-creation:evaluation-protocol/build-plan-coherent',\n protocolVersion: 1,\n promptAssemblyStrategy: MetaWorkflow_EvaluationPromptAssemblyStrategy.CANONICAL_PROTOCOL_EVIDENCE_V1,\n aggregationStrategy: MetaWorkflow_EvaluationAggregationStrategy.WORST_VERDICT_PRECEDENCE_V1,\n verdictPrecedence: [MetaWorkflow_EvaluationVerdict.GAP, MetaWorkflow_EvaluationVerdict.INDETERMINATE, MetaWorkflow_EvaluationVerdict.CONCERN, MetaWorkflow_EvaluationVerdict.PASS],\n aggregationPolicyRef: 'application-creation:aggregation/worst-build-plan-coherent-verdict',\n /*\n * One criterion per invariant of the method's `build-plan-coherent` checklist (its invariants 2 and 2b\n * share one criterion, because well-formedness and product declaration are read off the same task).\n * `assessesAspects` scopes a criterion to the families it actually reads (#1423): coverage reads the\n * domain plan's modules and resources beside the tasks; relationship coverage reads its relationship\n * drafts; the interleave criterion names no aspects because it needs the brand MAP and the store\n * selection, which are not aspects of a family, and so reads the whole evidence.\n */\n criteria: [\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-module-and-resource-coverage',\n criterionVersion: 1,\n instruction:\n \"Determine whether every resource in every module's inventory (mainResources and supportingResources) of the domain plan has build tasks, and whether every task's moduleRef names a module the domain plan declares. A module whose resources have tasks but which carries no redundant scaffold task is NOT a finding: module slices are scaffolded by the foundation step. A module added after foundation with neither a foundation slice nor an ensure-module task IS a gap. The billing catalogue is covered the same way: every pricing plan the business model declares must be an APPLICATION_BILLING_PRODUCT of a BILLING_CATALOG task whose servesRefs name the plan; a declared plan with no billing product is a gap (the backend would have nothing to sell and the website would re-type its price).\",\n assessesAspects: ['build-plan.task', 'domain-plan.module', 'domain-plan.resource'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-module-and-resource-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every domain-plan resource has build tasks and every moduleRef resolves to a declared module.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"Coverage is complete, but a task's objective CREATES a resource the domain plan shows as already existing instead of enriching it (a no-op dispatch), or a supporting resource's coverage is thin.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A resource with no task (the build would not produce it), or a task naming a module the domain plan does not declare (the dispatcher cannot route it).',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The domain plan or the build plan is absent, truncated or unreadable, so coverage cannot be established.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-task-well-formedness-and-products',\n criterionVersion: 1,\n instruction:\n \"Determine whether every task names exactly one real functional topic and at least one skill from the app-knowledge skill catalog, and whether every task except a COMPANION_GENERATION_STEP declares at least one product that names something composition does not already write (the fields a schema gains, the verbs a config gains, both endpoints of a relationship, the declarations a config file gains, the jobs a worker gains — not a scaffolded file or a composed package). Every product must be of the kind that names its surface: a view is a RESOURCE_COMPOSITE_VIEW / RESOURCE_CUSTOM_VIEW / RESOURCE_CHART_VIEW / APPLICATION_VIEW, a page a WEBSITE_PAGE, a worker an APPLICATION_WORKER, a provider a PROVIDER_BINDING — a non-resource surface declared under a MODULE target with a resource-shaped product, or with no product at all, is a gap. No two tasks may claim the same artifact; two tasks enriching one resource with DIFFERENT fields is correct. A cross-resource foreign key declared on a schema task's products is a gap: the relationship task is its single home.\",\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-task-well-formedness-and-products',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every task is bound to a real topic and skill, declares products composition does not already write, and no artifact is claimed twice.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"A task's products are meaningful but thinly described, or a generation step's landed condition is stated loosely.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: 'An invented topic or dangling skill; a coding task with empty products; a product naming only a scaffolded artifact or a composed package; a non-resource surface (a view, a page, a worker, a provider, a config file) declared under a resource-shaped kind; two tasks claiming one artifact; or a foreign key attributed to a schema task.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The skill catalog or the task list is not in evidence, so bindings cannot be checked.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-per-resource-stage-order',\n criterionVersion: 1,\n instruction:\n 'For each resource, determine whether its tasks respect the inner order schema -> config -> ui-behavior -> spec through their declared prerequisiteTaskRefs. A supporting resource may legitimately omit stages it does not need (a junction with schema and config and no ui-behavior is fine); only an out-of-order stage, or a main resource missing schema or config, is a finding.',\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-per-resource-stage-order',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: \"Every resource's stages are ordered schema -> config -> ui-behavior -> spec through declared prerequisites, and every main resource has schema and config.\",\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'Stages are ordered but a prerequisite edge is carried by prose rather than by prerequisiteTaskRefs, or an omitted stage on a supporting resource is unexplained.',\n [MetaWorkflow_EvaluationVerdict.GAP]: \"A config task ordered before its resource's schema task, a spec task before its ui-behavior task, or a main resource with no schema or config stage.\",\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Tasks do not carry enough target and prerequisite detail to reconstruct per-resource order.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-topic-dependency-order',\n criterionVersion: 1,\n instruction:\n \"Determine whether tasks respect the topic dependency edges: model_domain_graph before define_interaction_semantics; an app-level shape_user_experience task (views or navigation composing several resources or operations) after the interaction semantics and resources it composes; extend_application after the UX it extends; connect_runtime_and_external_capabilities after the resources it connects; and a resource's spec task after the stages it documents. A resource's OWN ui-behavior depends only on its own schema and config and MAY precede cross-resource operations — that is not a violation.\",\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-topic-dependency-order',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every cross-topic dependency is honoured by declared prerequisites, and the per-resource ui-behavior exception is applied correctly.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"The order is right but relies on band position rather than a declared prerequisite, or an MVP-first tie-break contradicts the roadmap's phasing.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: \"An app-level view composing resources or operations placed before they exist, an integration task before the resources it connects, a user-experience task before that resource's schema task, or a spec task before its ui-behavior stage.\",\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Topics or prerequisites are missing from the evidence, so ordering cannot be reconstructed.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-relationship-coverage',\n /*\n * Version 2 (2026-09-25): a relationship whose endpoint no module declares is excluded. Measured on\n * scratch-journey with a planted relationship to an undeclared resource: `conception-buildable` gave\n * GAP and version 1 of this criterion ALSO gave GAP (\"no wiring task\"). This one's GAP re-opens the\n * decomposer inside the build lane, so the lane re-ran decomposition on a relationship no task can\n * wire, up to its iteration cap, before the conception verdict reached the root.\n */\n criterionVersion: 2,\n instruction:\n \"Determine whether every relationship draft in the domain plan has a wiring task bound to the module-relationships skill, ordered after BOTH endpoint resources' schema tasks, and whether the wiring task is the single home of the relationship's foreign-key product. A relationship whose source or target resource is declared by no module of the domain plan is NOT this criterion's finding: no task can wire it, so it is the conception's fault and `conception-buildable` judges it. Judge the relationships whose endpoints both exist.\",\n assessesAspects: ['build-plan.task', 'domain-plan.relationship'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-relationship-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: \"Every relationship draft has one wiring task, ordered after both endpoints' schema tasks.\",\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"Every relationship is wired, but a wiring task's ordering relies on prose rather than declared prerequisites, or its cardinality intent is restated loosely.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: \"A relationship draft whose endpoints both exist with no wiring task, a wiring task ordered before an endpoint's schema task, or a relationship whose foreign key is also claimed by a schema task.\",\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: \"The domain plan's relationship drafts are not in evidence.\",\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-companion-generation-interleave',\n criterionVersion: 1,\n instruction:\n 'Determine whether the executable companion-owned generation steps are present and placed after the surfaces whose output they consume: i18n-labels after the resources it labels; email-templates after the surfaces it serves; database-migrations after the schema stages whose drift it migrates, and only for a PostgreSQL-backed application; logo present whenever the application has a brand brief, and unordered with respect to resource work because it consumes the brand and no code surface. Do NOT flag the absence of a seeds step: seed generation has no companion pipeline and must not be authored.',\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-companion-generation-interleave',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every executable generation step the application needs is present and placed after the surfaces it consumes; logo is present when a brand exists.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'A labels or email step is ordered before some surface it consumes, a migration step is missing on a PostgreSQL-backed application, or the logo step is missing on an application with a brand brief.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A generation step the pipeline cannot execute is authored (an unknown generationStepRef, or seeds), or a generation step declares products.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Whether the application has a brand brief or which store it uses is not in evidence, so the required step set cannot be decided.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-decomposition-boundary',\n criterionVersion: 1,\n instruction:\n 'Determine whether the plan stays at DECOMPOSITION depth: tasks name what they build, their topic, their skills, their target, their products and their ordering intent, and do not specify how a task is dispatched (single-flight locking, change-set capture, git baseline, verify mechanics), do not solve multi-agent scale or interleaving concurrency, and do not author a schema, resolve a cardinality into a concrete foreign key, or generate code.',\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-decomposition-boundary',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every task describes WHAT it builds and none describes how it executes.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'A task brief drifts toward execution detail or names a concrete field type or foreign key the coding agent should decide.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A task that specifies dispatch mechanics, concurrency, or authors schema or code in the plan itself.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Task briefs are not in evidence.',\n },\n },\n /*\n * The one criterion that faults the CONCEPTION rather than the plan (#1638). Every other criterion\n * here is the decomposer's own, and its GAP re-opens the decomposer. This one says the plan could not\n * be right however it was decomposed, because what it rests on is wrong — and the root routes that\n * GAP back to the conception lane through the build lane's exported verdict. Keeping it separate from\n * module-and-resource coverage is the point: a resource the plan merely FORGOT is not a conception\n * fault, and re-running the conception for it would be the most expensive way to fix an omission.\n */\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/conception-buildable',\n criterionVersion: 1,\n instruction:\n \"Determine whether the CONCEPTION this plan rests on can be built as declared. This criterion faults the domain plan, the capability composition or the surface plans — never the build plan. It is a GAP when (a) the domain plan declares a module, resource or relationship that no build task target can express, however it is decomposed, or (b) the computed coherence report shows a dangling reference or an unrealised decision in the conception (a domain-plan resource another family names that does not exist, a composition surface no plan realises) that the build would have to invent to proceed. A domain-plan element declared in an expressible shape that the build plan simply omits is NOT this criterion: that is module-and-resource coverage, the decomposer's own fault. Name the conception element in the rationale.\",\n assessesAspects: ['build-plan.task', 'domain-plan.module', 'domain-plan.resource', 'domain-plan.relationship'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/conception-buildable',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Everything the conception declares has a build target, and the coherence report shows nothing in it the build would have to invent.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'A conception element is expressible only awkwardly, or the coherence report shows an unrealised item that reads as a deliberate deferral.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'The domain plan declares something no build target can express, or the coherence report shows a dangling reference or unrealised decision in the conception that the build cannot proceed past without inventing it.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The domain plan or the coherence report is not in evidence, so the conception cannot be read against the plan.',\n },\n },\n ],\n },\n evaluatorBindingPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:evaluator-binding-policy/build-plan-coherent',\n policyVersion: 1,\n admissibleEvaluatorSelectors: [{ evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 }],\n defaultEvaluatorSelector: { evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 },\n outputContractSelector: { outputContractRef: 'meta-workflow:output-contract/structured-semantic-evaluation-candidate', outputContractVersion: 1 },\n fallbackPolicyRef: 'application-creation:evaluator-policy/fail-closed',\n escalationPolicyRef: 'application-creation:evaluator-policy/request-explicit-review',\n maximumAttempts: 2,\n timeoutPolicyRef: 'application-creation:evaluator-policy/bounded-semantic-evaluation',\n budgetPolicyRef: 'application-creation:evaluator-policy/current-work-cycle-budget',\n selectionPolicyRef: 'application-creation:evaluator-policy/scoped-risk-and-evidence',\n },\n decisionPointDefinition: {\n schemaVersion: 1,\n decisionPointRef: 'application-creation:decision-point/build-plan-coherent-result',\n decisionPointVersion: 1,\n triggerRefs: ['application-creation:trigger/build-plan-task-graph-staged-and-valid'],\n hardFloorRefs: ['application-creation:hard-floor/build-plan-task-graph-valid'],\n riskPolicyRef: 'application-creation:risk-policy/scoped-application-and-execution-context',\n significancePolicyRef: 'application-creation:significance-policy/build-plan-change',\n },\n decisionRule: {\n schemaVersion: 1,\n ruleRef: 'application-creation:decision-rule/build-plan-coherent-result',\n ruleVersion: 1,\n boundaryClass: MetaWorkflow_DecisionRuleBoundaryClass.QUALITY_INTERPRETATION,\n evidenceAggregationRef: 'application-creation:aggregation/worst-build-plan-coherent-verdict',\n resultMappings: [\n { verdict: MetaWorkflow_EvaluationVerdict.PASS, consequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY },\n { verdict: MetaWorkflow_EvaluationVerdict.CONCERN, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.GAP, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.INDETERMINATE, consequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE },\n ],\n hardFloorBindings: [{\n hardFloorRef: 'application-creation:hard-floor/build-plan-task-graph-valid',\n evidenceRequirementRefs: ['application-creation:evidence-requirement/build-plan-task-well-formedness-and-products'],\n }],\n hardFloorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n hardFloorShortcutAllowed: false,\n unresolvedConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE,\n evaluatorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n },\n authorityRequirement: {\n schemaVersion: 1,\n requirementRef: 'application-creation:authority-requirement/build-plan-coherent-result',\n requirementVersion: 1,\n consequenceClassRef: 'application-creation:authority-consequence/accept-build-plan-task-graph',\n riskClassRef: 'application-creation:risk/build-plan-accepted-family-mutation',\n decisionModePolicyRef: 'application-creation:authority-policy/explicit-operator-confirmation',\n assurancePolicyRef: 'application-creation:authority-policy/local-single-operator',\n channelPolicyRef: 'application-creation:authority-policy/interface-relay',\n principalPolicyRef: null,\n requiredDecisionMode: MetaWorkflow_AuthorityDecisionMode.EXPLICIT_OPERATOR_CONFIRMATION,\n minimumAssurance: MetaWorkflow_AuthorityAssuranceClass.LOCAL_OS_SESSION,\n admittedChannels: [MetaWorkflow_AuthorityInteractionChannel.INTERFACE_RELAY],\n requiredEvidenceRequirementRefs: ['application-creation:evidence-requirement/build-plan-module-and-resource-coverage'],\n expiryPolicyRef: 'application-creation:authority-expiry/current-interface-session',\n noncePolicyRef: 'application-creation:authority-nonce/random-per-request',\n hardFloorPosture: MetaWorkflow_HardFloorPosture.NON_WAIVABLE,\n hardFloorOverrideAllowed: false,\n },\n continuationPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:continuation-policy/build-plan-coherent',\n policyVersion: 1,\n mappings: [\n { decisionConsequence: MetaWorkflow_DecisionConsequence.CONTINUE, action: MetaWorkflow_ContinuationAction.CONTINUE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REVISE, action: MetaWorkflow_ContinuationAction.REVISE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE, action: MetaWorkflow_ContinuationAction.REQUEST_EVIDENCE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY, action: MetaWorkflow_ContinuationAction.REQUEST_AUTHORITY },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.BLOCK, action: MetaWorkflow_ContinuationAction.BLOCK },\n ],\n maximumRevisionAttempts: 3,\n maximumEvidenceRequests: 2,\n maximumAuthorityReviews: 1,\n fallbackAction: MetaWorkflow_ContinuationAction.BLOCK,\n },\n} satisfies MetaWorkflowEvaluationTreatmentSource;\n"]}
1
+ {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.build-decompose/playbook.definition.ts"],"names":[],"mappings":"AACA,OAAO,EACL,oCAAoC,EACpC,kCAAkC,EAClC,wCAAwC,EACxC,+BAA+B,EAC/B,gCAAgC,EAChC,sCAAsC,EACtC,0CAA0C,EAC1C,6CAA6C,EAC7C,8BAA8B,EAC9B,oCAAoC,EACpC,6BAA6B,GAC9B,MAAM,sCAAsC,CAAC;AAE9C;;;;;;;;;;;;;;;GAeG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,2BAA2B;IAClC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,+6DAA+6D;IACz7D,eAAe,EAAE;QACf,EAAE,MAAM,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,aAAa,EAAE,EAAE;QACtE;YACE,MAAM,EAAE,mBAAmB;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,gBAAgB,EAAE;YAC1C,IAAI,EAAE,g1BAAg1B;SACv1B;QACD;YACE,MAAM,EAAE,mBAAmB;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,iBAAiB,EAAE;YAC3C,IAAI,EAAE,2gBAA2gB;SAClhB;QACD;YACE,MAAM,EAAE,mBAAmB;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,kBAAkB,EAAE;YAC5C,IAAI,EAAE,iMAAiM;SACxM;QACD;YACE,MAAM,EAAE,mBAAmB;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,cAAc,EAAE;YACxC,MAAM,EAAE,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,wBAAwB,EAAE,EAAE,UAAU,EAAE,aAAa,EAAE,QAAQ,EAAE,QAAQ,EAAE;YAC7G,IAAI,EAAE,0LAA0L;SACjM;QACD;YACE,MAAM,EAAE,mBAAmB;YAC3B,UAAU,EAAE,EAAE,QAAQ,EAAE,oBAAoB,EAAE;YAC9C,MAAM,EAAE,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,wBAAwB,EAAE,EAAE,UAAU,EAAE,mBAAmB,EAAE,QAAQ,EAAE,QAAQ,EAAE;YACnH,IAAI,EAAE,yFAAyF;SAChG;KACF;IACD,QAAQ,EAAE;QACR,EAAE,QAAQ,EAAE,aAAa,EAAE;QAC3B,EAAE,QAAQ,EAAE,SAAS,EAAE;QACvB,EAAE,QAAQ,EAAE,cAAc,EAAE;QAC5B,EAAE,QAAQ,EAAE,gBAAgB,EAAE;QAC9B,EAAE,QAAQ,EAAE,gBAAgB,EAAE;QAC9B,EAAE,QAAQ,EAAE,cAAc,EAAE,IAAI,EAAE,8SAA8S,EAAE;QAClV,EAAE,QAAQ,EAAE,aAAa,EAAE,QAAQ,EAAE,KAAK,EAAE,IAAI,EAAE,2PAA2P,EAAE;QAC/S,EAAE,QAAQ,EAAE,iBAAiB,EAAE,IAAI,EAAE,gYAAgY,EAAE;QACva,EAAE,QAAQ,EAAE,oBAAoB,EAAE,IAAI,EAAE,gPAAgP,EAAE;QAC1R,EAAE,QAAQ,EAAE,kBAAkB,EAAE,IAAI,EAAE,yfAAyf,EAAE;QACjiB,EAAE,QAAQ,EAAE,gBAAgB,EAAE,IAAI,EAAE,qfAAqf,EAAE;QAC3hB,EAAE,QAAQ,EAAE,cAAc,EAAE,IAAI,EAAE,qVAAqV,EAAE;QACzX,EAAE,QAAQ,EAAE,YAAY,EAAE,IAAI,EAAE,kMAAkM,EAAE;KACrO;IACD,SAAS,EAAE;QACT;YACE,QAAQ,EAAE,YAAY;YACtB,WAAW,EAAE,wCAAwC;YACrD,aAAa,EAAE,8nJAA8nJ;SAC9oJ;KACF;IACD,QAAQ,EAAE;QACR,kBAAkB,EAAE,ywBAAywB;QAC7xB,gBAAgB,EAAE,CAAC,iBAAiB,EAAE,eAAe,EAAE,kBAAkB,CAAC;QAC1E,WAAW,EAAE;YACX,qBAAqB;YACrB,uBAAuB;YACvB,2BAA2B;YAC3B,wBAAwB;YACxB,sBAAsB;YACtB,4BAA4B;YAC5B,sBAAsB;YACtB,sBAAsB;YACtB,qBAAqB;YACrB,iCAAiC;SAClC;KACF;IACD,UAAU,EAAE,iBAAiB;IAC7B,UAAU,EAAE,gBAAgB;IAC5B,QAAQ,EAAE;QACR,SAAS,EAAE,CAAC;KACb;IACD,WAAW,EAAE,eAAe;CACpB,CAAC;AAEX,MAAM,CAAC,MAAM,yBAAyB,GAAG;IACvC,aAAa,EAAE,CAAC;IAChB,aAAa,EAAE,+DAA+D;IAC9E,6GAA6G;IAC7G,sGAAsG;IACtG,iHAAiH;IACjH,wHAAwH;IACxH,gIAAgI;IAChI,kGAAkG;IAClG,sGAAsG;IACtG,kHAAkH;IAClH,2GAA2G;IAC3G,+GAA+G;IAC/G,4HAA4H;IAC5H,qEAAqE;IACrE,0FAA0F;IAC1F,iBAAiB,EAAE,EAAE;IACrB,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,WAAW,EAAE,8DAA8D;QAC3E,eAAe,EAAE,CAAC;QAClB,sBAAsB,EAAE,6CAA6C,CAAC,8BAA8B;QACpG,mBAAmB,EAAE,0CAA0C,CAAC,2BAA2B;QAC3F,iBAAiB,EAAE,CAAC,8BAA8B,CAAC,GAAG,EAAE,8BAA8B,CAAC,aAAa,EAAE,8BAA8B,CAAC,OAAO,EAAE,8BAA8B,CAAC,IAAI,CAAC;QAClL,oBAAoB,EAAE,oEAAoE;QAC1F;;;;;;;WAOG;QACH,QAAQ,EAAE;YACV;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,wEAAwE;gBACtF,mFAAmF;gBACnF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,6wCAA6wC;gBAC/wC,eAAe,EAAE,CAAC,iBAAiB,EAAE,oBAAoB,EAAE,sBAAsB,CAAC;gBAClF,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,mFAAmF;wBACnG,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,+FAA+F;oBACtI,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,qQAAqQ;oBAC/S,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,wJAAwJ;oBAC9L,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,0GAA0G;iBAC3J;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,6EAA6E;gBAC3F,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,6iCAA6iC;gBAC/iC,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,wFAAwF;wBACxG,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,wIAAwI;oBAC/K,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,mHAAmH;oBAC7J,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,+UAA+U;oBACrX,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,uFAAuF;iBACxI;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,oEAAoE;gBAClF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,wXAAwX;gBAC1X,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,+EAA+E;wBAC/F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,4JAA4J;oBACnM,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,kKAAkK;oBAC5M,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sJAAsJ;oBAC5L,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,6FAA6F;iBAC9I;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,kEAAkE;gBAChF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,qlBAAqlB;gBACvlB,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,6EAA6E;wBAC7F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,sIAAsI;oBAC7K,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,kJAAkJ;oBAC5L,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,6OAA6O;oBACnR,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,6FAA6F;iBAC9I;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,iEAAiE;gBAC/E;;;;;;mBAMG;gBACH,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,ohBAAohB;gBACthB,eAAe,EAAE,CAAC,iBAAiB,EAAE,0BAA0B,CAAC;gBAChE,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,4EAA4E;wBAC5F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,2FAA2F;oBAClI,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,8JAA8J;oBACxM,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,oMAAoM;oBAC1O,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,4DAA4D;iBAC7G;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,2EAA2E;gBACzF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,kvBAAkvB;gBACpvB,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,sFAAsF;wBACtG,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,mJAAmJ;oBAC1L,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,sMAAsM;oBAChP,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,+JAA+J;oBACrM,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,kIAAkI;iBACnL;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,kEAAkE;gBAChF,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,0cAA0c;gBAC5c,eAAe,EAAE,CAAC,iBAAiB,CAAC;gBACpC,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,6EAA6E;wBAC7F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,yEAAyE;oBAChH,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,2HAA2H;oBACrK,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sGAAsG;oBAC5I,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,kCAAkC;iBACnF;aACF;YACD;;;;;;;;;;;;;;;;;;;;;;;;eAwBG;YACH;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,+DAA+D;gBAC7E,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,69CAA69C;gBAC/9C,eAAe,EAAE,CAAC,iBAAiB,EAAE,sBAAsB,EAAE,+BAA+B,EAAE,2BAA2B,EAAE,0BAA0B,EAAE,sBAAsB,CAAC;gBAC9K,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,0EAA0E;wBAC1F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,8NAA8N;oBACrQ,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,0MAA0M;oBACpP,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,yMAAyM;oBAC/O,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,mNAAmN;iBACpQ;aACF;YACD;;;;eAIG;YACH;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,yDAAyD;gBACvE,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,8yBAA8yB;gBAChzB,eAAe,EAAE,CAAC,iBAAiB,EAAE,yBAAyB,EAAE,6BAA6B,CAAC;gBAC9F,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,oEAAoE;wBACpF,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,yPAAyP;oBAChS,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,sLAAsL;oBAChO,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,yMAAyM;oBAC/O,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,yDAAyD;iBAC1G;aACF;YACD;;;;eAIG;YACH;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,gEAAgE;gBAC9E,yFAAyF;gBACzF,yGAAyG;gBACzG,0HAA0H;gBAC1H,6GAA6G;gBAC7G,mEAAmE;gBACnE,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,m+CAAm+C;gBACr+C,eAAe,EAAE,CAAC,iBAAiB,EAAE,yBAAyB,EAAE,oBAAoB,EAAE,sBAAsB,EAAE,uBAAuB,CAAC;gBACtI,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,2EAA2E;wBAC3F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,oLAAoL;oBAC3N,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,4KAA4K;oBACtN,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,2bAA2b;oBACje,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,yDAAyD;iBAC1G;aACF;YACD;;;;;;;eAOG;YACH;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,qDAAqD;gBACnE,gGAAgG;gBAChG,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,81CAA81C;gBACh2C,wHAAwH;gBACxH,+GAA+G;gBAC/G,eAAe,EAAE,CAAC,iBAAiB,EAAE,oBAAoB,EAAE,sBAAsB,EAAE,0BAA0B,EAAE,sBAAsB,EAAE,yBAAyB,CAAC;gBACjK,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,gEAAgE;wBAChF,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,0EAA0E;wBACtF,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,iFAAiF;wBACpG,kBAAkB,EAAE,6DAA6D;wBACjF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,qIAAqI;oBAC5K,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,2IAA2I;oBACrL,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,uSAAuS;oBAC7U,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,gHAAgH;iBACjK;aACF;SACA;KACF;IACD,sBAAsB,EAAE;QACtB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,mEAAmE;QAC9E,aAAa,EAAE,CAAC;QAChB,4BAA4B,EAAE,CAAC,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE,CAAC;QAC9H,wBAAwB,EAAE,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE;QACxH,sBAAsB,EAAE,EAAE,iBAAiB,EAAE,wEAAwE,EAAE,qBAAqB,EAAE,CAAC,EAAE;QACjJ,iBAAiB,EAAE,mDAAmD;QACtE,mBAAmB,EAAE,+DAA+D;QACpF,eAAe,EAAE,CAAC;QAClB,gBAAgB,EAAE,mEAAmE;QACrF,eAAe,EAAE,iEAAiE;QAClF,kBAAkB,EAAE,gEAAgE;KACrF;IACD,uBAAuB,EAAE;QACvB,aAAa,EAAE,CAAC;QAChB,gBAAgB,EAAE,gEAAgE;QAClF,oBAAoB,EAAE,CAAC;QACvB,WAAW,EAAE,CAAC,qEAAqE,CAAC;QACpF,aAAa,EAAE,CAAC,6DAA6D,CAAC;QAC9E,aAAa,EAAE,2EAA2E;QAC1F,qBAAqB,EAAE,4DAA4D;KACpF;IACD,YAAY,EAAE;QACZ,aAAa,EAAE,CAAC;QAChB,OAAO,EAAE,+DAA+D;QACxE,WAAW,EAAE,CAAC;QACd,aAAa,EAAE,sCAAsC,CAAC,sBAAsB;QAC5E,sBAAsB,EAAE,oEAAoE;QAC5F,cAAc,EAAE;YACd,EAAE,OAAO,EAAE,8BAA8B,CAAC,IAAI,EAAE,WAAW,EAAE,gCAAgC,CAAC,iBAAiB,EAAE;YACjH,EAAE,OAAO,EAAE,8BAA8B,CAAC,OAAO,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACzG,EAAE,OAAO,EAAE,8BAA8B,CAAC,GAAG,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACrG,EAAE,OAAO,EAAE,8BAA8B,CAAC,aAAa,EAAE,WAAW,EAAE,gCAAgC,CAAC,gBAAgB,EAAE;SAC1H;QACD,iBAAiB,EAAE,CAAC;gBAClB,YAAY,EAAE,6DAA6D;gBAC3E,uBAAuB,EAAE,CAAC,wFAAwF,CAAC;aACpH,CAAC;QACF,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;QACnE,wBAAwB,EAAE,KAAK;QAC/B,qBAAqB,EAAE,gCAAgC,CAAC,gBAAgB;QACxE,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;KACpE;IACD,oBAAoB,EAAE;QACpB,aAAa,EAAE,CAAC;QAChB,cAAc,EAAE,uEAAuE;QACvF,kBAAkB,EAAE,CAAC;QACrB,mBAAmB,EAAE,yEAAyE;QAC9F,YAAY,EAAE,+DAA+D;QAC7E,qBAAqB,EAAE,sEAAsE;QAC7F,kBAAkB,EAAE,6DAA6D;QACjF,gBAAgB,EAAE,uDAAuD;QACzE,kBAAkB,EAAE,IAAI;QACxB,oBAAoB,EAAE,kCAAkC,CAAC,8BAA8B;QACvF,gBAAgB,EAAE,oCAAoC,CAAC,gBAAgB;QACvE,gBAAgB,EAAE,CAAC,wCAAwC,CAAC,eAAe,CAAC;QAC5E,+BAA+B,EAAE,CAAC,mFAAmF,CAAC;QACtH,eAAe,EAAE,iEAAiE;QAClF,cAAc,EAAE,yDAAyD;QACzE,gBAAgB,EAAE,6BAA6B,CAAC,YAAY;QAC5D,wBAAwB,EAAE,KAAK;KAChC;IACD,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,8DAA8D;QACzE,aAAa,EAAE,CAAC;QAChB,QAAQ,EAAE;YACR,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,QAAQ,EAAE,MAAM,EAAE,+BAA+B,CAAC,QAAQ,EAAE;YACpH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,MAAM,EAAE,MAAM,EAAE,+BAA+B,CAAC,MAAM,EAAE;YAChH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,gBAAgB,EAAE,MAAM,EAAE,+BAA+B,CAAC,gBAAgB,EAAE;YACpI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,iBAAiB,EAAE,MAAM,EAAE,+BAA+B,CAAC,iBAAiB,EAAE;YACtI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,KAAK,EAAE,MAAM,EAAE,+BAA+B,CAAC,KAAK,EAAE;SAC/G;QACD,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,cAAc,EAAE,+BAA+B,CAAC,KAAK;KACtD;CAC8C,CAAC","sourcesContent":["import type { MetaWorkflowEvaluationTreatmentSource } from '@wildo-ai/saas-backend-lib/meta-workflow-runtime';\nimport {\n MetaWorkflow_AuthorityAssuranceClass,\n MetaWorkflow_AuthorityDecisionMode,\n MetaWorkflow_AuthorityInteractionChannel,\n MetaWorkflow_ContinuationAction,\n MetaWorkflow_DecisionConsequence,\n MetaWorkflow_DecisionRuleBoundaryClass,\n MetaWorkflow_EvaluationAggregationStrategy,\n MetaWorkflow_EvaluationPromptAssemblyStrategy,\n MetaWorkflow_EvaluationVerdict,\n MetaWorkflow_EvidenceRequirementKind,\n MetaWorkflow_HardFloorPosture,\n} from '@wildo-ai/saas-models/meta-workflows';\n\n/**\n * Canonical native declaration for this reusable application-creation method.\n *\n * The structured method remains intentionally rich: its intent, inputs, output\n * contracts, elicitation, deterministic verification and skill routing are the\n * application knowledge a later generic assessment loop composes.\n *\n * The `evaluationTreatmentSource` below is the `build-plan-coherent` reviewer checklist the\n * method carried as prose from the flexible-intelligence hard cut until 2026-09-22 (#1487) —\n * eight invariants that its own closing sentence said \"nothing executes\". Compiled here, the\n * ADVISORY judge reads them against the landed build plan and the domain plan it decomposes,\n * so a resource with no task, a relationship wired before its endpoints, or a product naming\n * only a scaffolded file is reported BEFORE a coding dispatch pays for it. Advisory as\n * everywhere in this lane: the plan is landed when the judge speaks, and a verdict is a note\n * for the creator's `approve_result` review, never a refusal.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-decompose\",\n \"version\": \"0.4.6\",\n \"phase\": \"bottom_up\",\n \"intent\": \"Bottom-up build decomposition — the FIRST build-execution playbook, the pivot from planning the domain (the domain-plan) to decomposing the BUILD. Reads the approved domain-plan (the ModuleBusinessSemantics module drafts + per-module resource inventory), the relationship drafts inside it (the inter-resource relationship intents), and the definition set (roadmap for phasing, requirements + feature-drafts for task-brief context), and the PLACEMENT PLAN (where each settings destination, resource operation and view sits in the shell, decided upstream), and DECOMPOSES the build work into an ordered set of coding-agent tasks. Each task is bound onto (a) the 7-topic functional taxonomy (configure_application_foundation -> model_domain_graph -> define_interaction_semantics -> shape_user_experience -> extend_application -> connect_runtime_and_external_capabilities -> assemble_verify_and_iterate) and (b) the app-knowledge skill catalog (each task names the skill(s) that carry its technical HOW). The tasks follow the per-resource inner order (schema -> config -> ui-behavior -> spec, then operations / interaction semantics, then UX, then extensions, then integrations), with companion-owned generation steps (i18n-labels, email-templates, logo, and database-migrations for applications with an accepted PostgreSQL schema plan) interleaved at the points their inputs exist. This playbook PRODUCES the ordered task graph (a build-plan artifact); it does NOT dispatch tasks to coding agents (that is the dispatch-orchestration playbook downstream), does NOT capture change-sets / lock or schedule runs / verify, and does NOT solve multi-agent scale or interleaving. It authors no schemas and generates no code. The typed BuildPlanTaskGraph contract and deterministic validator already exist. Declare prerequisiteTaskRefs explicitly: the host derives readiness from those edges; functionalTopic provides context and skill routing, not an implicit execution order.\",\n \"preconditions\": [\n { \"kind\": \"artifact_exists\", \"selector\": { \"family\": \"domain-plan\" } },\n {\n \"kind\": \"artifact_expected\",\n \"selector\": { \"family\": \"placement-plan\" },\n \"//\": \"SEQUENCING, not readiness — and the distinction is the whole point. `bottom_up.placement-plan` gates on the SAME `domain-plan` this does, so both become eligible at the same instant and decomposing first is legal. This method then says, at its placement section, 'No placement plan? Emit nothing here and say so' — which is honest per task and catastrophic per plan: the build proceeds with ZERO SHELL_PLACEMENT tasks and nothing refuses, so the finished application has no navigation and the cause is three playbooks upstream. `artifact_expected` is the kind written for exactly this (its own doc: use it whenever running early DEGRADES the output rather than invalidating it): the board reports `blocked only by sequencing`, a human may still run it deliberately, and `unmet` finally explains WHY the order matters instead of losing the signal.\"\n },\n {\n \"kind\": \"artifact_expected\",\n \"selector\": { \"family\": \"experience-plan\" },\n \"//\": \"The same shape for the experience plan (#2494): decomposing without it emits no view, no shell or design-system configuration, no milestone and no guidance, so the application ships with no home, the scaffold's colours and the default navigation. Inside the conception and build lanes every child is admitted past SEQUENCING, so this marks the board and a standalone run; what makes the LANE wait is the conception's stop condition, and what routes a plan decomposed without it back is the conception-buildable criterion.\"\n },\n {\n \"kind\": \"artifact_expected\",\n \"selector\": { \"family\": \"integration-plan\" },\n \"//\": \"Same reasoning: without it no worker, minion, provider binding or inbound-channel task is emitted. Its producer gates on the domain plan alone, so it is always producible and always expected.\"\n },\n {\n \"kind\": \"artifact_expected\",\n \"selector\": { \"family\": \"website-plan\" },\n \"when\": { \"selector\": { \"family\": \"capability-composition\" }, \"decision\": \"add-website\", \"equals\": \"NEEDED\" },\n \"//\": \"Expected only when the composition decided a website: an application without one has no website plan, and an unconditional expectation would wait for something its producer never runs.\"\n },\n {\n \"kind\": \"artifact_expected\",\n \"selector\": { \"family\": \"documentation-plan\" },\n \"when\": { \"selector\": { \"family\": \"capability-composition\" }, \"decision\": \"add-technical-doc\", \"equals\": \"NEEDED\" },\n \"//\": \"Expected only when the composition decided a documentation portal, for the same reason.\"\n }\n ],\n \"inputs\": [\n { \"family\": \"domain-plan\" },\n { \"family\": \"roadmap\" },\n { \"family\": \"requirements\" },\n { \"family\": \"feature-drafts\" },\n { \"family\": \"placement-plan\" },\n { \"family\": \"vision-brief\", \"//\": \"Carries the landed COMPLIANCE POSTURE and constraints. Measured 2026-09-04 (#309): without this input the decomposer, given a landed GDPR/ePrivacy posture, produced ZERO posture-derived tasks — the obligations lived in a family the brief never carried. No intent slice: the posture must arrive whole.\" },\n { \"family\": \"brand-brief\", \"render\": \"map\", \"//\": \"Whether the application HAS a brand decides whether the `logo` generation step is authored (method: companion generation steps; checklist invariant 6). The method only needs to know it exists, so it reads the brand as a map, not its content (#1424).\" },\n { \"family\": \"experience-plan\", \"//\": \"The application's own surfaces and its shell composition (#1493). Each view becomes a task over the product kind its KIND names, each configuration an APPLICATION_FRONTEND_CONFIG task, each planned milestone an APPLICATION_MILESTONE task and each planned piece of guidance an APPLICATION_GUIDANCE task — with the skill taken from the experience plan's total maps, never chosen here.\" },\n { \"family\": \"documentation-plan\", \"//\": \"Which chapters the documentation portal carries (#1494). Each becomes a DOCUMENTATION_CHAPTER task under the TECHNICAL_DOCUMENTATION target, whose scope prohibits the portal's generated tree. A NOT_APPLICABLE plan, or none, emits nothing.\" },\n { \"family\": \"integration-plan\", \"//\": \"What runs beside the backend and what the application reaches out to (#1495). Each worker, minion and provider binding becomes a task over its own target kind, with the skill taken from the three total maps rather than chosen here — which is what makes the worker, minion and provider skills reachable. Each declared inbound channel becomes an INBOUND_CHANNEL_HANDLER task in the module its messages concern (#1832), routed to `inbound-channels` by the dispatch. No plan, or an empty one, emits nothing.\" },\n { \"family\": \"business-model\", \"//\": \"The pricing plans the application sells (#1835). Each becomes a product of the billing catalogue — one BILLING_CATALOG task producing an APPLICATION_BILLING_PRODUCT per plan — so the backend has something to sell and the website's pricing page reads the catalogue instead of re-typing the plans' prices. Measured on the first journey-built application: with no such task its catalogue stayed EMPTY and the website agent hand-copied the prices. No business model, or one with no plans, emits nothing.\" },\n { \"family\": \"website-plan\", \"//\": \"What the marketing site says, page by page (#1492). The decomposer turns each page into a WEBSITE_PAGE task and each section into a WEBSITE_SECTION task bound to the skill its KIND names — so the website skills are reached by construction rather than by a model recalling folder names. A NOT_APPLICABLE plan, or none at all, emits nothing.\" },\n { \"family\": \"build-plan\", \"//\": \"Its own family: its method refines its own prior output and keeps its refs, so it must be GIVEN that output (#1430). Input, not precondition: a first run, with no prior output, stays eligible.\" }\n ],\n \"outputs\": [\n {\n \"family\": \"build-plan\",\n \"schemaRef\": \"saas-specifications:BuildPlanTaskGraph\",\n \"description\": \"The build decomposition — an ORDERED set of coding-agent build tasks (a task graph) that turns the approved domain plan into a sequence of buildable units. Each task carries: a stable task ref, the target it builds (a module, a resource + one of its build stages, a relationship, a companion-generation step, a shell-surface placement config), WHAT IT PRODUCES (`produces` — the artifacts whose presence in the finished application proves the task landed; distinct from the target, which is a write scope several tasks may share), the ONE functional topic it belongs to (a real MetaWorkflow_FunctionalTopic value), the skill(s) that carry its technical HOW (real folders from the app-knowledge skill catalog, resolved via the skills router), and its ordering intent (which tasks must precede it — expressed as typed prerequisiteTaskRefs, which the host resolves for readiness). Author prerequisiteTaskRefs to express the actual dependencies, using these planning considerations: (a) the cross-app topic dependency edges (model_domain_graph before define_interaction_semantics before app-level shape_user_experience before extend_application before connect_runtime_and_external_capabilities; foundation and assemble/verify are owned by sibling playbooks) and (b) the per-resource stage sequence schema -> config -> ui-behavior -> spec — which deliberately CROSSES topics (ui-behavior is shape_user_experience; the spec is a model_domain_graph documentation capstone ordered last) and so is not monotonic on axis (a); a roadmap-driven MVP-first preference breaks ties within a band. TYPED since the flexible-intelligence Block 3: the `_core` build-task-graph contract (`BuildPlanTaskGraph` — `tasks[]` with a stable `taskRef`, a closed `BuildPlanTaskTargetKind` target (MODULE / RESOURCE_STAGE / RELATIONSHIP / COMPANION_GENERATION_STEP / SHELL_PLACEMENT / MODULE_FRONTEND / MODULE_BACKEND / APPLICATION_FRONTEND_CONFIG / WEBSITE / TECHNICAL_DOCUMENTATION / WORKER / MINION / PROVIDER_BINDING / BILLING_CATALOG), a `produces` list over the closed `BuildPlanTaskProductKind` vocabulary (the resource products — schema fields, registration, ui-behavior, specification, relationship, operation, composite / custom / chart view, PDF template; the application products — view, document, module, frontend configuration, custom component, milestone, guidance; and the runtime products — worker jobs, minion behaviours, provider binding, website page and section, documentation chapter, inbound channel handler; and the billing product the catalogue sells), exactly one `functionalTopic`, `skillRefs`, DECLARED `prerequisiteTaskRefs` the host resolves for readiness, and traceability `servesRefs`) is the family schema; the provider answers the strict `BuildPlanTaskGraphGeneration` shape and the trusted runtime stamps refs and version. The task never carries paths, commands, prompts or runtime controls — the dispatch host derives mutation scope and verification from the target kind. `validateBuildPlanTaskGraph` is the deterministic validator. A task's products must name something COMPOSITION DOES NOT ALREADY WRITE (the fields a schema gains, not its scaffolded file) and no two tasks may claim the same artifact — that is what makes landing decidable; a coding task declaring none is reported as `TASK_DECLARES_NO_PRODUCT`. If such a task has a COMPLETED durable run, the host advances past it but reports its ref in `unverifiableLandedTaskRefs`: it ran, but its output is not proven. Without that completed run it remains unlanded. Companion-generation tasks use their own landed conditions; migrations require the schema plan to be in sync. Product probes inspect committed files and named declarations, not runtime correctness. Two things are HARD FLOORS: a prerequisite cycle, and a resource stage that declares its predecessor stage in the SAME graph without depending on it — dispatch order comes solely from `prerequisiteTaskRefs`, so an undeclared stage edge lets the host author a resources-config for a schema that has not landed. A predecessor stage that is ABSENT from the plan is an authoring WARNING instead, because a plan may legitimately author one stage of a resource the tree already carries; the coherence reviewer checklist (`build-plan-coherent`, in the method) remains the semantic check and the creator's approve_result review the trust floor. Consumed by the bottom-up DISPATCH-ORCHESTRATION playbook (which dispatches the tasks through the coding-agent contract in parallel waves, up to the application's build parallelism at once) and the SCALE playbook (which describes how those waves are scheduled, interleaved with the companion generation steps, and reconciled) — both downstream of this decomposition.\"\n }\n ],\n \"method\": {\n \"//contextSources\": \"WORKSPACE_TRUTH — this playbook plans against CODE, not against definition artifacts: it needs real module ids and per-resource present schema fields, or it invents ids that do not resolve and every task it emits fails at dispatch. SKILL_CATALOG — its method routes THROUGH the skills router and binds every emitted task to a skill folder, so it must choose from the real set; measured 2026-08-27 it was choosing from recall, and a dangling skill ref is a task the dispatch playbook cannot run. COHERENCE_REPORT — the computed cross-family findings over the conception it builds on (dangling edges into the domain plan, a composition surface no plan realises), so its judge can tell a conception fault from its own (#1638): the build lane routes the first back to conception.\",\n \"contextSources\": [\"workspace_truth\", \"skill_catalog\", \"coherence_report\"],\n \"skillRefs\": [\n \"resource-add-module\",\n \"resource-add-resource\",\n \"resource-schema-authoring\",\n \"resource-config-wiring\",\n \"resource-ui-behavior\",\n \"frontend-component-catalog\",\n \"spec-resource-update\",\n \"module-relationships\",\n \"module-registration\",\n \"application-database-migrations\"\n ]\n },\n \"executor\": \"companion_agent\",\n \"approval\": \"approve_result\",\n \"budget\": {\n \"maxRuns\": 3\n },\n \"onFailure\": \"keep_and_flag\"\n} as const;\n\nexport const evaluationTreatmentSource = {\n schemaVersion: 1,\n definitionRef: 'application-creation:evaluation-treatment/build-plan-coherent',\n // 2 since #1638: `conception-buildable` faults the CONCEPTION, not the plan, which changes what a GAP means.\n // 3: relationship coverage leaves a relationship to an undeclared resource to `conception-buildable`.\n // 4: experience coverage (#2235) — the experience plan's surfaces each have a task, and its absence is recorded.\n // 5: module-and-resource coverage also asks for demonstration data (#2234), so a built application does not open empty.\n // 6: experience coverage keys its absence case on the accepted-truth statement, not on a heading it did not see (#2235 review).\n // 7: module-and-resource coverage orders a linked demo seed after the seed it references (#2392).\n // 8: role coverage (#2490) — a requirement naming user groups is served by an APPLICATION_ROLES task.\n // 9: interaction coverage (#2493) — a requirement verb beyond the default verbs is served by an interaction task.\n // 10: interaction coverage also requires a task per lifecycle transition the domain plan declares (#2491).\n // 11: interaction coverage also requires the UPDATE freeze of a lifecycle with final states (#2491 review F4).\n // 12: that freeze lives in the objective of the transition into a final state, never in an `update` task (#2491 re-review).\n // 13: locked states are frozen like final ones (#2491 re-review M1).\n // 14: conception-buildable reports an absent experience plan as a conception gap (#2494).\n definitionVersion: 14,\n evaluationProtocol: {\n schemaVersion: 1,\n protocolRef: 'application-creation:evaluation-protocol/build-plan-coherent',\n protocolVersion: 1,\n promptAssemblyStrategy: MetaWorkflow_EvaluationPromptAssemblyStrategy.CANONICAL_PROTOCOL_EVIDENCE_V1,\n aggregationStrategy: MetaWorkflow_EvaluationAggregationStrategy.WORST_VERDICT_PRECEDENCE_V1,\n verdictPrecedence: [MetaWorkflow_EvaluationVerdict.GAP, MetaWorkflow_EvaluationVerdict.INDETERMINATE, MetaWorkflow_EvaluationVerdict.CONCERN, MetaWorkflow_EvaluationVerdict.PASS],\n aggregationPolicyRef: 'application-creation:aggregation/worst-build-plan-coherent-verdict',\n /*\n * One criterion per invariant of the method's `build-plan-coherent` checklist (its invariants 2 and 2b\n * share one criterion, because well-formedness and product declaration are read off the same task).\n * `assessesAspects` scopes a criterion to the families it actually reads (#1423): coverage reads the\n * domain plan's modules and resources beside the tasks; relationship coverage reads its relationship\n * drafts; the interleave criterion names no aspects because it needs the brand MAP and the store\n * selection, which are not aspects of a family, and so reads the whole evidence.\n */\n criteria: [\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-module-and-resource-coverage',\n // 3: a linked demo seed not ordered after the seed it references is a gap (#2392).\n criterionVersion: 3,\n instruction:\n \"Determine whether every resource in every module's inventory (mainResources and supportingResources) of the domain plan has build tasks, and whether every task's moduleRef names a module the domain plan declares. A module whose resources have tasks but which carries no redundant scaffold task is NOT a finding: module slices are scaffolded by the foundation step. A module added after foundation with neither a foundation slice nor an ensure-module task IS a gap. The billing catalogue is covered the same way: every pricing plan the business model declares must be an APPLICATION_BILLING_PRODUCT of a BILLING_CATALOG task whose servesRefs name the plan; a declared plan with no billing product is a gap (the backend would have nothing to sell and the website would re-type its price). Seeding is covered the same way: a plan whose domain has main resources and no APPLICATION_DATA_SEED task of content DEMONSTRATION is a concern — the application would open empty, with nothing a creator can judge or show (#2234). A seed task whose rows point at rows another seed writes (a contact's customer, a quote's customer) and that is not ordered after that seed's task is a gap: the seed links them with referenceDataSeedRow and dependsOn, which resolve only against rows already written (#2392).\",\n assessesAspects: ['build-plan.task', 'domain-plan.module', 'domain-plan.resource'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-module-and-resource-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every domain-plan resource has build tasks and every moduleRef resolves to a declared module.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"Coverage is complete, but a task's objective CREATES a resource the domain plan shows as already existing instead of enriching it (a no-op dispatch), a supporting resource's coverage is thin, or no DEMONSTRATION data seed gives the main resources sample rows.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A resource with no task (the build would not produce it), or a task naming a module the domain plan does not declare (the dispatcher cannot route it).',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The domain plan or the build plan is absent, truncated or unreadable, so coverage cannot be established.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-task-well-formedness-and-products',\n criterionVersion: 1,\n instruction:\n \"Determine whether every task names exactly one real functional topic and at least one skill from the app-knowledge skill catalog, and whether every task except a COMPANION_GENERATION_STEP declares at least one product that names something composition does not already write (the fields a schema gains, the verbs a config gains, both endpoints of a relationship, the declarations a config file gains, the jobs a worker gains — not a scaffolded file or a composed package). Every product must be of the kind that names its surface: a view is a RESOURCE_COMPOSITE_VIEW / RESOURCE_CUSTOM_VIEW / RESOURCE_CHART_VIEW / APPLICATION_VIEW, a page a WEBSITE_PAGE, a worker an APPLICATION_WORKER, a provider a PROVIDER_BINDING — a non-resource surface declared under a MODULE target with a resource-shaped product, or with no product at all, is a gap. No two tasks may claim the same artifact; two tasks enriching one resource with DIFFERENT fields is correct. A cross-resource foreign key declared on a schema task's products is a gap: the relationship task is its single home.\",\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-task-well-formedness-and-products',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every task is bound to a real topic and skill, declares products composition does not already write, and no artifact is claimed twice.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"A task's products are meaningful but thinly described, or a generation step's landed condition is stated loosely.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: 'An invented topic or dangling skill; a coding task with empty products; a product naming only a scaffolded artifact or a composed package; a non-resource surface (a view, a page, a worker, a provider, a config file) declared under a resource-shaped kind; two tasks claiming one artifact; or a foreign key attributed to a schema task.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The skill catalog or the task list is not in evidence, so bindings cannot be checked.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-per-resource-stage-order',\n criterionVersion: 1,\n instruction:\n 'For each resource, determine whether its tasks respect the inner order schema -> config -> ui-behavior -> spec through their declared prerequisiteTaskRefs. A supporting resource may legitimately omit stages it does not need (a junction with schema and config and no ui-behavior is fine); only an out-of-order stage, or a main resource missing schema or config, is a finding.',\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-per-resource-stage-order',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: \"Every resource's stages are ordered schema -> config -> ui-behavior -> spec through declared prerequisites, and every main resource has schema and config.\",\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'Stages are ordered but a prerequisite edge is carried by prose rather than by prerequisiteTaskRefs, or an omitted stage on a supporting resource is unexplained.',\n [MetaWorkflow_EvaluationVerdict.GAP]: \"A config task ordered before its resource's schema task, a spec task before its ui-behavior task, or a main resource with no schema or config stage.\",\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Tasks do not carry enough target and prerequisite detail to reconstruct per-resource order.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-topic-dependency-order',\n criterionVersion: 1,\n instruction:\n \"Determine whether tasks respect the topic dependency edges: model_domain_graph before define_interaction_semantics; an app-level shape_user_experience task (views or navigation composing several resources or operations) after the interaction semantics and resources it composes; extend_application after the UX it extends; connect_runtime_and_external_capabilities after the resources it connects; and a resource's spec task after the stages it documents. A resource's OWN ui-behavior depends only on its own schema and config and MAY precede cross-resource operations — that is not a violation.\",\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-topic-dependency-order',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every cross-topic dependency is honoured by declared prerequisites, and the per-resource ui-behavior exception is applied correctly.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"The order is right but relies on band position rather than a declared prerequisite, or an MVP-first tie-break contradicts the roadmap's phasing.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: \"An app-level view composing resources or operations placed before they exist, an integration task before the resources it connects, a user-experience task before that resource's schema task, or a spec task before its ui-behavior stage.\",\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Topics or prerequisites are missing from the evidence, so ordering cannot be reconstructed.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-relationship-coverage',\n /*\n * Version 2 (2026-09-25): a relationship whose endpoint no module declares is excluded. Measured on\n * scratch-journey with a planted relationship to an undeclared resource: `conception-buildable` gave\n * GAP and version 1 of this criterion ALSO gave GAP (\"no wiring task\"). This one's GAP re-opens the\n * decomposer inside the build lane, so the lane re-ran decomposition on a relationship no task can\n * wire, up to its iteration cap, before the conception verdict reached the root.\n */\n criterionVersion: 2,\n instruction:\n \"Determine whether every relationship draft in the domain plan has a wiring task bound to the module-relationships skill, ordered after BOTH endpoint resources' schema tasks, and whether the wiring task is the single home of the relationship's foreign-key product. A relationship whose source or target resource is declared by no module of the domain plan is NOT this criterion's finding: no task can wire it, so it is the conception's fault and `conception-buildable` judges it. Judge the relationships whose endpoints both exist.\",\n assessesAspects: ['build-plan.task', 'domain-plan.relationship'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-relationship-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: \"Every relationship draft has one wiring task, ordered after both endpoints' schema tasks.\",\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"Every relationship is wired, but a wiring task's ordering relies on prose rather than declared prerequisites, or its cardinality intent is restated loosely.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: \"A relationship draft whose endpoints both exist with no wiring task, a wiring task ordered before an endpoint's schema task, or a relationship whose foreign key is also claimed by a schema task.\",\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: \"The domain plan's relationship drafts are not in evidence.\",\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-companion-generation-interleave',\n criterionVersion: 1,\n instruction:\n 'Determine whether the executable companion-owned generation steps are present and placed after the surfaces whose output they consume: i18n-labels after the resources it labels; email-templates after the surfaces it serves; database-migrations after the schema stages whose drift it migrates, and only for a PostgreSQL-backed application; logo present whenever the application has a brand brief, and unordered with respect to resource work because it consumes the brand and no code surface. Do NOT flag the absence of an i18n-translations step: the dispatch host derives it after i18n-labels. Do NOT flag the absence of a seeds GENERATION step: none exists, and seeding is an APPLICATION_DATA_SEED coding task judged under module-and-resource coverage.',\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-companion-generation-interleave',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every executable generation step the application needs is present and placed after the surfaces it consumes; logo is present when a brand exists.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'A labels or email step is ordered before some surface it consumes, a migration step is missing on a PostgreSQL-backed application, or the logo step is missing on an application with a brand brief.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A generation step the pipeline cannot execute is authored (an unknown generationStepRef, or a seeds generation step), or a generation step declares products.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Whether the application has a brand brief or which store it uses is not in evidence, so the required step set cannot be decided.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-decomposition-boundary',\n criterionVersion: 1,\n instruction:\n 'Determine whether the plan stays at DECOMPOSITION depth: tasks name what they build, their topic, their skills, their target, their products and their ordering intent, and do not specify how a task is dispatched (dispatch locking and concurrency, change-set capture, git baseline, verify mechanics), do not solve multi-agent scale or interleaving concurrency, and do not author a schema, resolve a cardinality into a concrete foreign key, or generate code.',\n assessesAspects: ['build-plan.task'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-decomposition-boundary',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Every task describes WHAT it builds and none describes how it executes.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'A task brief drifts toward execution detail or names a concrete field type or foreign key the coding agent should decide.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A task that specifies dispatch mechanics, concurrency, or authors schema or code in the plan itself.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'Task briefs are not in evidence.',\n },\n },\n /*\n * The experience plan's surfaces each have a task, and an ABSENT experience plan is recorded rather than\n * silent (#2235).\n *\n * Measured on app-creation-test-004 (2026-10-01): `bottom_up.experience-plan` was refused twice, the build\n * plan was decomposed anyway, and the application shipped with no app-level views, no onboarding and no\n * milestones. The method is right to emit no such task without a plan (\"an improvised surface is the state\n * this family replaced\"), and the plan read as complete — no criterion here looked at the experience plan.\n *\n * Why an absent plan is PASS with a marked rationale, and not a weaker verdict: this treatment DECLARES every\n * non-PASS verdict as routing back to the decomposer (CONCERN and GAP → REVISE, INDETERMINATE →\n * REQUEST_EVIDENCE, which ends in BLOCK), and the decomposer cannot produce an upstream family by revising.\n * Corrected 2026-10-05 (#2494 review G4): those consequences are declarations only — the treatment compiler\n * copies the continuation policy and nothing acts on it, and the judge is advisory. What a verdict DOES today\n * is what a composite's `reopenOnVerdict` table says, keyed on the criterion and the verdict; the build lane's\n * table re-opens this decomposer for module and relationship coverage only. So the PASS rule keeps this\n * criterion's verdict truthful against the declared treatment, not against a live routing.\n *\n * The absence is still not left at a marked PASS (#2494): it is a CONCEPTION fault, and `conception-buildable`\n * reports it as a GAP. The root's `reopenOnVerdict` re-opens the conception and build lanes on exactly that GAP\n * (exported by the build lane as `judge:bottom_up.build-decompose`), which is the routing that exists. The\n * `artifact_expected` precondition on the family, rejected here before because every lane child is admitted\n * past SEQUENCING, was added anyway for the board and standalone runs; what makes the lane wait is the\n * conception's stop condition, which now names the experience plan.\n */\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-experience-coverage',\n criterionVersion: 3,\n instruction:\n \"Determine whether every surface the experience plan decides has its build task: one task per VIEW (target MODULE_FRONTEND on the view's module, a product of the view's kind carrying the plan's viewRef verbatim), one APPLICATION_FRONTEND_CONFIG task per CONFIGURATION, one APPLICATION_MILESTONE task per planned MILESTONE, and one APPLICATION_GUIDANCE task per planned piece of GUIDANCE (an onboarding document's objective naming the hostViewRef that embeds it). When the plan decides a HOME, the GLOBAL_VIEWS configuration task's objective must set it: name `homeDefinitionFactory` and the home's view or resource operation. A view, configuration, milestone or guidance entry with no task, or a decided home no objective sets, is a gap: the application would ship without it (a missing home opens on the framework's welcome page) while the plan reads complete. Never conclude the plan is absent because this criterion's own slice does not show it: the accepted application truth either renders the experience plan or says it has none. When the accepted application truth STATES that `experience-plan` has no accepted content, the decomposer has rightly emitted none of these tasks and cannot repair the absence by revising: record PASS, and begin the rationale with the words 'NO EXPERIENCE PLAN:' followed by what the application will therefore lack (its app-level views, its shell and navigation configuration, its milestones and its onboarding), so the absence is on the record instead of silent.\",\n assessesAspects: ['build-plan.task', 'experience-plan.view', 'experience-plan.configuration', 'experience-plan.milestone', 'experience-plan.guidance', 'experience-plan.home'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-experience-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 1,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: \"Every view, configuration, milestone and guidance entry of the experience plan has its task — or no experience plan is in evidence, and the rationale begins 'NO EXPERIENCE PLAN:' and names what the application will lack.\",\n [MetaWorkflow_EvaluationVerdict.CONCERN]: \"Every entry has a task, but a task's objective drops what the plan decided for it: a view's reusesComponentRefs, a milestone's moment, a guidance entry's gate, or an onboarding document's hostViewRef.\",\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A view, configuration, milestone or guidance entry the experience plan declares has no task, a decided home is set by no task\\'s objective, or a view task carries a viewRef the plan does not declare.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The build plan is not in evidence, or the accepted application truth neither renders the experience plan nor states that it has none. (A STATED absence is not indeterminate: it is the PASS case above, marked.)',\n },\n },\n /*\n * #2490: app-creation-test-005's requirement \"office and field users see different areas\" was served by\n * per-resource config tasks that all left every verb on ORG_MEMBER, plus an access-role RESOURCE nothing\n * reads. No criterion asked whether the plan could enforce a role at all.\n */\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-role-coverage',\n criterionVersion: 1,\n instruction:\n \"Determine whether every requirement that names groups of users with different access (office and field staff, technicians, accountants, read-only reviewers, 'only administrators may …') is served by an APPLICATION_ROLES task producing one APPLICATION_ROLE per group that no core role already covers (ORG_OWNER, ORG_ADMIN, ORG_MANAGER, ORG_MEMBER, ORG_GUEST), ordered after the config tasks of the resources whose operations it narrows. A requirement satisfied by the core roles alone (only administrators may delete) needs no APPLICATION_ROLES task, but the config tasks of the resources it covers must say which operations are restricted. A task, product or resource that models roles, permissions or role assignments as DATA (an access-role or permission resource) is never a way to satisfy such a requirement.\",\n assessesAspects: ['build-plan.task', 'requirements.functional', 'requirements.non-functional'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-role-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 1,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'No requirement names user groups with different access, or every such group has an APPLICATION_ROLE product of an APPLICATION_ROLES task ordered after the config tasks it narrows, or is covered by a core role the relevant config tasks restrict to.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'Each group has its role, but the APPLICATION_ROLES task is ordered before a config task of a resource it narrows, or its objective does not say which operations each role may call.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A requirement names a user group no core role covers and no APPLICATION_ROLE product declares, or the plan answers a role requirement with a task or resource that stores roles or permissions as data.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The build plan or the requirements are not in evidence.',\n },\n },\n /*\n * #2493: app-creation-test-004 (92 tasks) and -005 (86) planned no operation, document or email at all,\n * and every lifecycle step shipped as a status users edit by hand. Each requirement was \"served\" by CRUD\n * tasks citing it in servesRefs, and no criterion weighed whether those tasks could realise its verbs.\n */\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-plan-interaction-coverage',\n // 2: every lifecycle transition the domain plan declares has its operation task (#2491).\n // 3: every lifecycle with final states has its UPDATE freeze, as the method places it (#2491 review F4).\n // 4: the freeze lives in the objective of the transition into a final state, never in an `update` task (#2491 re-review).\n // 5: locked states (no edits, may still move on) are frozen the same way as final ones (#2491 re-review M1),\n // in both its lifecycle clause and its requirement-verb clause.\n criterionVersion: 5,\n instruction:\n \"Determine whether every transition the domain plan's lifecycles declare has a RESOURCE_OPERATION task on its resource (plus a MODULE_BACKEND task when the transition creates another resource), whether, for every lifecycle with locked or final states, the objective of a transition task moving into each of them restricts that resource's UPDATE to the states that are neither locked nor final (a separate RESOURCE_OPERATION named update is not a realisation: the scaffold already writes update, so it reads as built before it runs), and whether every functional acceptance criterion whose verb goes beyond the default resource verbs (create, read, update, list, delete) is served by a task able to realise it: a state change ('an accepted quote', 'issue the invoice', 'mark it paid') by a RESOURCE_OPERATION on the resource whose state changes; one record creating or filling another ('an accepted quote creates a job') by a RESOURCE_OPERATION on the source resource with a MODULE_BACKEND implementation; a record that must stop changing by the objective of the transition task into the locked or final state; a produced document by a PDF_TEMPLATE task; a sent message by the email generation step plus the triggering operation's task. A task citing the requirement in servesRefs does not realise a verb its kind cannot carry: a config or schema task leaves a status freely editable. A value derived from other records (a next action, an overdue flag) planned as a stored field is not a realisation either.\",\n assessesAspects: ['build-plan.task', 'requirements.functional', 'domain-plan.module', 'domain-plan.resource', 'domain-plan.lifecycle'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-plan-interaction-coverage',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 1,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'No functional criterion names a verb beyond the default resource verbs, or each such verb is served by a task of a kind that can realise it, naming the requirement in servesRefs.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'Every verb has a task, but a derived value (a next action, an overdue flag) is planned as a stored field, or an operation task does not say which states it moves between.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'A declared lifecycle transition has no operation task, or no transition task into a locked or final state carries the UPDATE freeze (or it is planned as a separate update task); or a state change, a record creating another, a record that must stop changing, a produced document or a sent message named by a functional criterion has no task of a kind that can realise it — including a workflow-describing plan with no interaction task at all.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The build plan or the requirements are not in evidence.',\n },\n },\n /*\n * The one criterion that faults the CONCEPTION rather than the plan (#1638). Every other criterion\n * here is the decomposer's own, and its GAP re-opens the decomposer. This one says the plan could not\n * be right however it was decomposed, because what it rests on is wrong — and the root routes that\n * GAP back to the conception lane through the build lane's exported verdict. Keeping it separate from\n * module-and-resource coverage is the point: a resource the plan merely FORGOT is not a conception\n * fault, and re-running the conception for it would be the most expensive way to fix an omission.\n */\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/conception-buildable',\n // 2: an absent experience plan is a conception gap, routed back to the conception lane (#2494).\n criterionVersion: 2,\n instruction:\n \"Determine whether the CONCEPTION this plan rests on can be built as declared. This criterion faults the domain plan, the capability composition or the surface plans — never the build plan. It is a GAP when (a) the domain plan declares a module, resource or relationship that no build task target can express, however it is decomposed, or (b) the computed coherence report shows a dangling reference or an unrealised decision in the conception (a domain-plan resource another family names that does not exist, a composition surface no plan realises) that the build would have to invent to proceed, or (c) the accepted application truth STATES that `experience-plan` has no accepted content: every application with a frontend has an experience, and without its plan the build has no home, no design system from the brand, no navigation decision and no application views, which no revision of this plan can supply; the same when it STATES that `integration-plan` has none, since then nothing decided whether the application runs workers, minions, provider bindings or inbound channels (an integration plan that decides none is content, not an absence). A domain-plan element declared in an expressible shape that the build plan simply omits is NOT this criterion: that is module-and-resource coverage, the decomposer's own fault. Name the conception element in the rationale.\",\n // An aspect of each family clause (c) reads, so the slice states an ABSENT experience or integration plan and points at\n // the accepted truth (#2494 review G1, G6); a criterion naming no aspect of a family is told nothing about it.\n assessesAspects: ['build-plan.task', 'domain-plan.module', 'domain-plan.resource', 'domain-plan.relationship', 'experience-plan.view', 'integration-plan.worker'],\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/conception-buildable',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/domain-plan-and-build-plan-candidate',\n minCount: 2,\n maxCount: 8,\n coveragePolicyRef: 'application-creation:evidence-policy/exact-build-decompose-inputs-and-candidate',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-action-binding',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'Everything the conception declares has a build target, and the coherence report shows nothing in it the build would have to invent.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'A conception element is expressible only awkwardly, or the coherence report shows an unrealised item that reads as a deliberate deferral.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'The domain plan declares something no build target can express, the coherence report shows a dangling reference or unrealised decision in the conception that the build cannot proceed past without inventing it, or the accepted truth states the experience plan or the integration plan is absent.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The domain plan or the coherence report is not in evidence, so the conception cannot be read against the plan.',\n },\n },\n ],\n },\n evaluatorBindingPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:evaluator-binding-policy/build-plan-coherent',\n policyVersion: 1,\n admissibleEvaluatorSelectors: [{ evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 }],\n defaultEvaluatorSelector: { evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 },\n outputContractSelector: { outputContractRef: 'meta-workflow:output-contract/structured-semantic-evaluation-candidate', outputContractVersion: 1 },\n fallbackPolicyRef: 'application-creation:evaluator-policy/fail-closed',\n escalationPolicyRef: 'application-creation:evaluator-policy/request-explicit-review',\n maximumAttempts: 2,\n timeoutPolicyRef: 'application-creation:evaluator-policy/bounded-semantic-evaluation',\n budgetPolicyRef: 'application-creation:evaluator-policy/current-work-cycle-budget',\n selectionPolicyRef: 'application-creation:evaluator-policy/scoped-risk-and-evidence',\n },\n decisionPointDefinition: {\n schemaVersion: 1,\n decisionPointRef: 'application-creation:decision-point/build-plan-coherent-result',\n decisionPointVersion: 1,\n triggerRefs: ['application-creation:trigger/build-plan-task-graph-staged-and-valid'],\n hardFloorRefs: ['application-creation:hard-floor/build-plan-task-graph-valid'],\n riskPolicyRef: 'application-creation:risk-policy/scoped-application-and-execution-context',\n significancePolicyRef: 'application-creation:significance-policy/build-plan-change',\n },\n decisionRule: {\n schemaVersion: 1,\n ruleRef: 'application-creation:decision-rule/build-plan-coherent-result',\n ruleVersion: 1,\n boundaryClass: MetaWorkflow_DecisionRuleBoundaryClass.QUALITY_INTERPRETATION,\n evidenceAggregationRef: 'application-creation:aggregation/worst-build-plan-coherent-verdict',\n resultMappings: [\n { verdict: MetaWorkflow_EvaluationVerdict.PASS, consequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY },\n { verdict: MetaWorkflow_EvaluationVerdict.CONCERN, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.GAP, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.INDETERMINATE, consequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE },\n ],\n hardFloorBindings: [{\n hardFloorRef: 'application-creation:hard-floor/build-plan-task-graph-valid',\n evidenceRequirementRefs: ['application-creation:evidence-requirement/build-plan-task-well-formedness-and-products'],\n }],\n hardFloorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n hardFloorShortcutAllowed: false,\n unresolvedConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE,\n evaluatorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n },\n authorityRequirement: {\n schemaVersion: 1,\n requirementRef: 'application-creation:authority-requirement/build-plan-coherent-result',\n requirementVersion: 1,\n consequenceClassRef: 'application-creation:authority-consequence/accept-build-plan-task-graph',\n riskClassRef: 'application-creation:risk/build-plan-accepted-family-mutation',\n decisionModePolicyRef: 'application-creation:authority-policy/explicit-operator-confirmation',\n assurancePolicyRef: 'application-creation:authority-policy/local-single-operator',\n channelPolicyRef: 'application-creation:authority-policy/interface-relay',\n principalPolicyRef: null,\n requiredDecisionMode: MetaWorkflow_AuthorityDecisionMode.EXPLICIT_OPERATOR_CONFIRMATION,\n minimumAssurance: MetaWorkflow_AuthorityAssuranceClass.LOCAL_OS_SESSION,\n admittedChannels: [MetaWorkflow_AuthorityInteractionChannel.INTERFACE_RELAY],\n requiredEvidenceRequirementRefs: ['application-creation:evidence-requirement/build-plan-module-and-resource-coverage'],\n expiryPolicyRef: 'application-creation:authority-expiry/current-interface-session',\n noncePolicyRef: 'application-creation:authority-nonce/random-per-request',\n hardFloorPosture: MetaWorkflow_HardFloorPosture.NON_WAIVABLE,\n hardFloorOverrideAllowed: false,\n },\n continuationPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:continuation-policy/build-plan-coherent',\n policyVersion: 1,\n mappings: [\n { decisionConsequence: MetaWorkflow_DecisionConsequence.CONTINUE, action: MetaWorkflow_ContinuationAction.CONTINUE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REVISE, action: MetaWorkflow_ContinuationAction.REVISE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE, action: MetaWorkflow_ContinuationAction.REQUEST_EVIDENCE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY, action: MetaWorkflow_ContinuationAction.REQUEST_AUTHORITY },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.BLOCK, action: MetaWorkflow_ContinuationAction.BLOCK },\n ],\n maximumRevisionAttempts: 3,\n maximumEvidenceRequests: 2,\n maximumAuthorityReviews: 1,\n fallbackAction: MetaWorkflow_ContinuationAction.BLOCK,\n },\n} satisfies MetaWorkflowEvaluationTreatmentSource;\n"]}
@@ -14,7 +14,7 @@ export declare const playbookDefinition: {
14
14
  readonly ref: "bottom_up.build-dispatch";
15
15
  readonly version: "0.1.0";
16
16
  readonly phase: "bottom_up";
17
- readonly intent: "Bottom-up build dispatch — the SECOND build-execution playbook, the pivot from DECOMPOSING the build (the build-plan task graph) to DISPATCHING it: turning one ordered task into an actually-run, verified coding-agent run under the D4 dispatch contract. Reads the approved TYPED build-plan (`BuildPlanTaskGraph` — each task carries a closed target kind, ONE MetaWorkflow_FunctionalTopic, its skill refs, and DECLARED prerequisite task refs) and the current journey state, selects the NEXT READY task (`selectReadyBuildPlanTasks`: every declared prerequisite has landed — resolved by the host, never inferred from prose; SINGLE-FLIGHT — exactly ONE workspace-mutating run at a time), and dispatches exactly that typed task: (1) the runner builds the context pack (task brief + the task's skill pointers + the relevant journey/definition artifacts + introspected app reality + repo paths); (2) it runs ONE prompt turn against the coding agent over the Agent Client Protocol, in a session rooted at the app workspace (cwd = app root, so CLAUDE.md / .claude skills load naturally), answering the agent's permission requests within the execution profile's declared ceiling and refusing anything above it or outside the task's mutation scope; (3) it captures the change-set around the run (git baseline/post-run worktree snapshots → per-file attribution → a structured GitChangeSetCapture recorded on the task row); (4) it runs the VERIFY gate OUTSIDE the coding agent (a deterministic typecheck the runner maps onto the dispatch verification hook — pnpm exec tsc --noEmit — the trust-but-verify floor); (5) it records the result + applies the onFailure disposition (keep_and_flag: a failed/timed-out run keeps its captured change-set flagged for human triage, never a silent half-applied state). Then loop to the next ready task. This playbook PRODUCES the per-task dispatch contract + execution semantics; it authors no schemas and generates no code (the coding agent does that at dispatch time). It does NOT decompose the plan (that is the build-decompose playbook, upstream — it owns the task graph) and does NOT solve multi-agent SCALE — parallelism across several coding agents, the concurrency schedule, and interleaving the companion generation steps at scale are the downstream scale playbook. v1 scaffold: the single-flight dispatch contract; multi-agent parallelism, a run-completion serializer, and a revert_changeset failure path are later phases (revert is a MUTATING git op outside the read-only change-set carve-out, deliberately deferred).";
17
+ readonly intent: "Bottom-up build dispatch — the SECOND build-execution playbook, the pivot from DECOMPOSING the build (the build-plan task graph) to DISPATCHING it: turning one ordered task into an actually-run, verified coding-agent run under the D4 dispatch contract. Reads the approved TYPED build-plan (`BuildPlanTaskGraph` — each task carries a closed target kind, ONE MetaWorkflow_FunctionalTopic, its skill refs, and DECLARED prerequisite task refs) and the current journey state, selects the READY tasks (`selectReadyBuildPlanTasks`: every declared prerequisite has landed — resolved by the host, never inferred from prose) and dispatches them as a WAVE: up to the application's build parallelism at once (`wildo workbench parallelism`, 5 by default; 1 = one workspace-mutating run at a time), in ONE shared worktree, each slot refilled as its run settles. Each task in the wave runs the same typed contract: (1) the runner builds the context pack (task brief + the task's skill pointers + the relevant journey/definition artifacts + introspected app reality + repo paths); (2) it runs ONE prompt turn against the coding agent over the Agent Client Protocol, in a session rooted at the app workspace (cwd = app root, so CLAUDE.md / .claude skills load naturally), answering the agent's permission requests within the execution profile's declared ceiling and refusing anything above it or outside the task's mutation scope; (3) it captures the change-set around the run (git baseline/post-run worktree snapshots → per-file attribution → a structured GitChangeSetCapture recorded on the task row); (4) it runs the VERIFY gate OUTSIDE the coding agent (a deterministic typecheck the runner maps onto the dispatch verification hook — pnpm exec tsc --noEmit — the trust-but-verify floor); (5) it records the result + applies the onFailure disposition (keep_and_flag: a failed/timed-out run keeps its captured change-set flagged for human triage, never a silent half-applied state). When the wave's runs have settled, the runner commits what their own accepts left as one change naming every run it carries, and re-runs ALONE each task whose finished product a sibling overwrote; each run's record names what overlapped it (`concurrency`, `interferenceSuspected`). One run of this playbook is one bounded wave; run it again for the next. This playbook PRODUCES the per-task dispatch contract + execution semantics; it authors no schemas and generates no code (the coding agent does that at dispatch time). It does NOT decompose the plan (that is the build-decompose playbook, upstream — it owns the task graph) and does NOT choose the wave's width (the build parallelism is the person's setting). A revert_changeset failure path is a later phase (revert is a MUTATING git op outside the read-only change-set carve-out, deliberately deferred).";
18
18
  readonly preconditions: readonly [{
19
19
  readonly kind: "artifact_exists";
20
20
  readonly selector: {
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-dispatch/playbook.definition.ts"],"names":[],"mappings":"AACA,OAAO,EACL,oCAAoC,EACpC,kCAAkC,EAClC,wCAAwC,EACxC,+BAA+B,EAC/B,gCAAgC,EAChC,sCAAsC,EACtC,0CAA0C,EAC1C,6CAA6C,EAC7C,8BAA8B,EAC9B,oCAAoC,EACpC,6BAA6B,EAC9B,MAAM,sCAAsC,CAAC;AAE9C;;;;;;;;;;GAUG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAwCrB,CAAC;AAEX;;;;;;;;;;GAUG;AACH,eAAO,MAAM,yBAAyB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAsKW,CAAC"}
1
+ {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.build-dispatch/playbook.definition.ts"],"names":[],"mappings":"AACA,OAAO,EACL,oCAAoC,EACpC,kCAAkC,EAClC,wCAAwC,EACxC,+BAA+B,EAC/B,gCAAgC,EAChC,sCAAsC,EACtC,0CAA0C,EAC1C,6CAA6C,EAC7C,8BAA8B,EAC9B,oCAAoC,EACpC,6BAA6B,EAC9B,MAAM,sCAAsC,CAAC;AAE9C;;;;;;;;;;GAUG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAwCrB,CAAC;AAEX;;;;;;;;;;GAUG;AACH,eAAO,MAAM,yBAAyB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAsKW,CAAC"}
@@ -14,7 +14,7 @@ export const playbookDefinition = {
14
14
  "ref": "bottom_up.build-dispatch",
15
15
  "version": "0.1.0",
16
16
  "phase": "bottom_up",
17
- "intent": "Bottom-up build dispatch — the SECOND build-execution playbook, the pivot from DECOMPOSING the build (the build-plan task graph) to DISPATCHING it: turning one ordered task into an actually-run, verified coding-agent run under the D4 dispatch contract. Reads the approved TYPED build-plan (`BuildPlanTaskGraph` — each task carries a closed target kind, ONE MetaWorkflow_FunctionalTopic, its skill refs, and DECLARED prerequisite task refs) and the current journey state, selects the NEXT READY task (`selectReadyBuildPlanTasks`: every declared prerequisite has landed — resolved by the host, never inferred from prose; SINGLE-FLIGHT — exactly ONE workspace-mutating run at a time), and dispatches exactly that typed task: (1) the runner builds the context pack (task brief + the task's skill pointers + the relevant journey/definition artifacts + introspected app reality + repo paths); (2) it runs ONE prompt turn against the coding agent over the Agent Client Protocol, in a session rooted at the app workspace (cwd = app root, so CLAUDE.md / .claude skills load naturally), answering the agent's permission requests within the execution profile's declared ceiling and refusing anything above it or outside the task's mutation scope; (3) it captures the change-set around the run (git baseline/post-run worktree snapshots → per-file attribution → a structured GitChangeSetCapture recorded on the task row); (4) it runs the VERIFY gate OUTSIDE the coding agent (a deterministic typecheck the runner maps onto the dispatch verification hook — pnpm exec tsc --noEmit — the trust-but-verify floor); (5) it records the result + applies the onFailure disposition (keep_and_flag: a failed/timed-out run keeps its captured change-set flagged for human triage, never a silent half-applied state). Then loop to the next ready task. This playbook PRODUCES the per-task dispatch contract + execution semantics; it authors no schemas and generates no code (the coding agent does that at dispatch time). It does NOT decompose the plan (that is the build-decompose playbook, upstream — it owns the task graph) and does NOT solve multi-agent SCALE — parallelism across several coding agents, the concurrency schedule, and interleaving the companion generation steps at scale are the downstream scale playbook. v1 scaffold: the single-flight dispatch contract; multi-agent parallelism, a run-completion serializer, and a revert_changeset failure path are later phases (revert is a MUTATING git op outside the read-only change-set carve-out, deliberately deferred).",
17
+ "intent": "Bottom-up build dispatch — the SECOND build-execution playbook, the pivot from DECOMPOSING the build (the build-plan task graph) to DISPATCHING it: turning one ordered task into an actually-run, verified coding-agent run under the D4 dispatch contract. Reads the approved TYPED build-plan (`BuildPlanTaskGraph` — each task carries a closed target kind, ONE MetaWorkflow_FunctionalTopic, its skill refs, and DECLARED prerequisite task refs) and the current journey state, selects the READY tasks (`selectReadyBuildPlanTasks`: every declared prerequisite has landed — resolved by the host, never inferred from prose) and dispatches them as a WAVE: up to the application's build parallelism at once (`wildo workbench parallelism`, 5 by default; 1 = one workspace-mutating run at a time), in ONE shared worktree, each slot refilled as its run settles. Each task in the wave runs the same typed contract: (1) the runner builds the context pack (task brief + the task's skill pointers + the relevant journey/definition artifacts + introspected app reality + repo paths); (2) it runs ONE prompt turn against the coding agent over the Agent Client Protocol, in a session rooted at the app workspace (cwd = app root, so CLAUDE.md / .claude skills load naturally), answering the agent's permission requests within the execution profile's declared ceiling and refusing anything above it or outside the task's mutation scope; (3) it captures the change-set around the run (git baseline/post-run worktree snapshots → per-file attribution → a structured GitChangeSetCapture recorded on the task row); (4) it runs the VERIFY gate OUTSIDE the coding agent (a deterministic typecheck the runner maps onto the dispatch verification hook — pnpm exec tsc --noEmit — the trust-but-verify floor); (5) it records the result + applies the onFailure disposition (keep_and_flag: a failed/timed-out run keeps its captured change-set flagged for human triage, never a silent half-applied state). When the wave's runs have settled, the runner commits what their own accepts left as one change naming every run it carries, and re-runs ALONE each task whose finished product a sibling overwrote; each run's record names what overlapped it (`concurrency`, `interferenceSuspected`). One run of this playbook is one bounded wave; run it again for the next. This playbook PRODUCES the per-task dispatch contract + execution semantics; it authors no schemas and generates no code (the coding agent does that at dispatch time). It does NOT decompose the plan (that is the build-decompose playbook, upstream — it owns the task graph) and does NOT choose the wave's width (the build parallelism is the person's setting). A revert_changeset failure path is a later phase (revert is a MUTATING git op outside the read-only change-set carve-out, deliberately deferred).",
18
18
  "preconditions": [
19
19
  { "kind": "artifact_exists", "selector": { "family": "build-plan" } }
20
20
  ],
@@ -27,8 +27,8 @@ export const playbookDefinition = {
27
27
  },
28
28
  "executor": "coding_agent",
29
29
  "approval": "approve_before",
30
- // `maxRuns` is the dispatch-orchestration run budget (one task per run, across the
31
- // whole build), and since 2026-09-19 (#1344) the LOOP READS IT: a playbook that has spent
30
+ // `maxRuns` is the dispatch-orchestration run budget (one wave per run — one task when the
31
+ // build parallelism is 1 — across the whole build), and since 2026-09-19 (#1344) the LOOP READS IT: a playbook that has spent
32
32
  // the ceiling it declares stops being offered, reported in the eligibility trace's
33
33
  // `spentRunCeiling`. Sized as a stop against loops, not as cost control.
34
34
  //
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-dispatch/playbook.definition.ts"],"names":[],"mappings":"AACA,OAAO,EACL,oCAAoC,EACpC,kCAAkC,EAClC,wCAAwC,EACxC,+BAA+B,EAC/B,gCAAgC,EAChC,sCAAsC,EACtC,0CAA0C,EAC1C,6CAA6C,EAC7C,8BAA8B,EAC9B,oCAAoC,EACpC,6BAA6B,GAC9B,MAAM,sCAAsC,CAAC;AAE9C;;;;;;;;;;GAUG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,0BAA0B;IACjC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,u/EAAu/E;IACjgF,eAAe,EAAE;QACf,EAAE,MAAM,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,YAAY,EAAE,EAAE;KACtE;IACD,QAAQ,EAAE;QACR,EAAE,QAAQ,EAAE,YAAY,EAAE;KAC3B;IACD,SAAS,EAAE,EAAE;IACb,QAAQ,EAAE;QACR,WAAW,EAAE,EACZ;KACF;IACD,UAAU,EAAE,cAAc;IAC1B,UAAU,EAAE,gBAAgB;IAC5B,mFAAmF;IACnF,0FAA0F;IAC1F,mFAAmF;IACnF,yEAAyE;IACzE,EAAE;IACF,0FAA0F;IAC1F,4FAA4F;IAC5F,yFAAyF;IACzF,qFAAqF;IACrF,4FAA4F;IAC5F,2FAA2F;IAC3F,8FAA8F;IAC9F,gFAAgF;IAChF,QAAQ,EAAE;QACR,SAAS,EAAE,EAAE;QACb,gBAAgB,EAAE,QAAQ;QAC1B,iBAAiB,EAAE,OAAO;QAC1B,eAAe,EAAE,EAAE;QACnB,eAAe,EAAE,OAAO;KACzB;IACD,WAAW,EAAE,eAAe;CACpB,CAAC;AAEX;;;;;;;;;;GAUG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAAG;IACvC,aAAa,EAAE,CAAC;IAChB,aAAa,EAAE,+DAA+D;IAC9E,mGAAmG;IACnG,iBAAiB,EAAE,CAAC;IACpB,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,WAAW,EAAE,8DAA8D;QAC3E,eAAe,EAAE,CAAC;QAClB,sBAAsB,EAAE,6CAA6C,CAAC,8BAA8B;QACpG,mBAAmB,EAAE,0CAA0C,CAAC,2BAA2B;QAC3F,iBAAiB,EAAE;YACjB,8BAA8B,CAAC,GAAG;YAClC,8BAA8B,CAAC,aAAa;YAC5C,8BAA8B,CAAC,OAAO;YACtC,8BAA8B,CAAC,IAAI;SACpC;QACD,oBAAoB,EAAE,oEAAoE;QAC1F,QAAQ,EAAE;YACR;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,+DAA+D;gBAC7E,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,ufAAuf;gBACzf,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,0EAA0E;wBAC1F,wFAAwF;wBACxF,gDAAgD;wBAChD,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,qGAAqG;wBACrG,qGAAqG;wBACrG,UAAU,EAAE,kEAAkE;wBAC9E,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,mEAAmE;wBACtF,kBAAkB,EAAE,oEAAoE;wBACxF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,2IAA2I;oBAClL,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,+QAA+Q;oBACzT,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sFAAsF;oBAC5H,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,oFAAoF;iBACrI;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,iEAAiE;gBAC/E,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,mkBAAmkB;gBACrkB,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,0EAA0E;wBAC1F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,gEAAgE;wBAC5E,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,uEAAuE;wBAC1F,kBAAkB,EAAE,oEAAoE;wBACxF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,wGAAwG;oBAC/I,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,0HAA0H;oBACpK,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,+GAA+G;oBACrJ,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,+EAA+E;iBAChI;aACF;SACF;KACF;IACD,sBAAsB,EAAE;QACtB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,mEAAmE;QAC9E,aAAa,EAAE,CAAC;QAChB,4BAA4B,EAAE,CAAC,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE,CAAC;QAC9H,wBAAwB,EAAE,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE;QACxH,sBAAsB,EAAE;YACtB,iBAAiB,EAAE,wEAAwE;YAC3F,qBAAqB,EAAE,CAAC;SACzB;QACD,iBAAiB,EAAE,mDAAmD;QACtE,mBAAmB,EAAE,+DAA+D;QACpF,eAAe,EAAE,CAAC;QAClB,gBAAgB,EAAE,mEAAmE;QACrF,eAAe,EAAE,iEAAiE;QAClF,kBAAkB,EAAE,gEAAgE;KACrF;IACD,uBAAuB,EAAE;QACvB,aAAa,EAAE,CAAC;QAChB,gBAAgB,EAAE,yDAAyD;QAC3E,oBAAoB,EAAE,CAAC;QACvB,WAAW,EAAE,CAAC,6DAA6D,CAAC;QAC5E,aAAa,EAAE,CAAC,gEAAgE,CAAC;QACjF,aAAa,EAAE,2EAA2E;QAC1F,qBAAqB,EAAE,sEAAsE;KAC9F;IACD,YAAY,EAAE;QACZ,aAAa,EAAE,CAAC;QAChB,OAAO,EAAE,wDAAwD;QACjE,WAAW,EAAE,CAAC;QACd,aAAa,EAAE,sCAAsC,CAAC,sBAAsB;QAC5E,sBAAsB,EAAE,oEAAoE;QAC5F,cAAc,EAAE;YACd,EAAE,OAAO,EAAE,8BAA8B,CAAC,IAAI,EAAE,WAAW,EAAE,gCAAgC,CAAC,iBAAiB,EAAE;YACjH,EAAE,OAAO,EAAE,8BAA8B,CAAC,OAAO,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACzG,EAAE,OAAO,EAAE,8BAA8B,CAAC,GAAG,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACrG,EAAE,OAAO,EAAE,8BAA8B,CAAC,aAAa,EAAE,WAAW,EAAE,gCAAgC,CAAC,gBAAgB,EAAE;SAC1H;QACD,iBAAiB,EAAE,CAAC;gBAClB,YAAY,EAAE,gEAAgE;gBAC9E,uBAAuB,EAAE,CAAC,0EAA0E,CAAC;aACtG,CAAC;QACF,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;QACnE,wBAAwB,EAAE,KAAK;QAC/B,qBAAqB,EAAE,gCAAgC,CAAC,gBAAgB;QACxE,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;KACpE;IACD,oBAAoB,EAAE;QACpB,aAAa,EAAE,CAAC;QAChB,cAAc,EAAE,uEAAuE;QACvF,kBAAkB,EAAE,CAAC;QACrB,mBAAmB,EAAE,yEAAyE;QAC9F,YAAY,EAAE,mEAAmE;QACjF,qBAAqB,EAAE,sEAAsE;QAC7F,kBAAkB,EAAE,6DAA6D;QACjF,gBAAgB,EAAE,uDAAuD;QACzE,kBAAkB,EAAE,IAAI;QACxB,oBAAoB,EAAE,kCAAkC,CAAC,8BAA8B;QACvF,gBAAgB,EAAE,oCAAoC,CAAC,gBAAgB;QACvE,gBAAgB,EAAE,CAAC,wCAAwC,CAAC,eAAe,CAAC;QAC5E,+BAA+B,EAAE;YAC/B,0EAA0E;YAC1E,0EAA0E;SAC3E;QACD,eAAe,EAAE,iEAAiE;QAClF,cAAc,EAAE,yDAAyD;QACzE,gBAAgB,EAAE,6BAA6B,CAAC,YAAY;QAC5D,wBAAwB,EAAE,KAAK;KAChC;IACD,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,8DAA8D;QACzE,aAAa,EAAE,CAAC;QAChB,QAAQ,EAAE;YACR,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,QAAQ,EAAE,MAAM,EAAE,+BAA+B,CAAC,QAAQ,EAAE;YACpH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,MAAM,EAAE,MAAM,EAAE,+BAA+B,CAAC,MAAM,EAAE;YAChH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,gBAAgB,EAAE,MAAM,EAAE,+BAA+B,CAAC,gBAAgB,EAAE;YACpI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,iBAAiB,EAAE,MAAM,EAAE,+BAA+B,CAAC,iBAAiB,EAAE;YACtI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,KAAK,EAAE,MAAM,EAAE,+BAA+B,CAAC,KAAK,EAAE;SAC/G;QACD,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,cAAc,EAAE,+BAA+B,CAAC,KAAK;KACtD;CAC8C,CAAC","sourcesContent":["import type { MetaWorkflowEvaluationTreatmentSource } from '@wildo-ai/saas-backend-lib/meta-workflow-runtime';\nimport {\n MetaWorkflow_AuthorityAssuranceClass,\n MetaWorkflow_AuthorityDecisionMode,\n MetaWorkflow_AuthorityInteractionChannel,\n MetaWorkflow_ContinuationAction,\n MetaWorkflow_DecisionConsequence,\n MetaWorkflow_DecisionRuleBoundaryClass,\n MetaWorkflow_EvaluationAggregationStrategy,\n MetaWorkflow_EvaluationPromptAssemblyStrategy,\n MetaWorkflow_EvaluationVerdict,\n MetaWorkflow_EvidenceRequirementKind,\n MetaWorkflow_HardFloorPosture,\n} from '@wildo-ai/saas-models/meta-workflows';\n\n/**\n * Canonical native declaration for this reusable application-creation method.\n *\n * The structured method remains intentionally rich: its intent, inputs, output\n * contracts, elicitation, deterministic verification and skill routing are the\n * application knowledge the generic assessment loop composes. Since the build\n * vertical joined the private assessment episode, this playbook ALSO declares\n * the assessment policy, episode target, bounds and the semantic evaluation\n * Treatment that judge ONE dispatched build-plan task's worktree change-set\n * (the `dispatch-outcome-sound` rubric below, made operational).\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-dispatch\",\n \"version\": \"0.1.0\",\n \"phase\": \"bottom_up\",\n \"intent\": \"Bottom-up build dispatch — the SECOND build-execution playbook, the pivot from DECOMPOSING the build (the build-plan task graph) to DISPATCHING it: turning one ordered task into an actually-run, verified coding-agent run under the D4 dispatch contract. Reads the approved TYPED build-plan (`BuildPlanTaskGraph` — each task carries a closed target kind, ONE MetaWorkflow_FunctionalTopic, its skill refs, and DECLARED prerequisite task refs) and the current journey state, selects the NEXT READY task (`selectReadyBuildPlanTasks`: every declared prerequisite has landed — resolved by the host, never inferred from prose; SINGLE-FLIGHT — exactly ONE workspace-mutating run at a time), and dispatches exactly that typed task: (1) the runner builds the context pack (task brief + the task's skill pointers + the relevant journey/definition artifacts + introspected app reality + repo paths); (2) it runs ONE prompt turn against the coding agent over the Agent Client Protocol, in a session rooted at the app workspace (cwd = app root, so CLAUDE.md / .claude skills load naturally), answering the agent's permission requests within the execution profile's declared ceiling and refusing anything above it or outside the task's mutation scope; (3) it captures the change-set around the run (git baseline/post-run worktree snapshots → per-file attribution → a structured GitChangeSetCapture recorded on the task row); (4) it runs the VERIFY gate OUTSIDE the coding agent (a deterministic typecheck the runner maps onto the dispatch verification hook — pnpm exec tsc --noEmit — the trust-but-verify floor); (5) it records the result + applies the onFailure disposition (keep_and_flag: a failed/timed-out run keeps its captured change-set flagged for human triage, never a silent half-applied state). Then loop to the next ready task. This playbook PRODUCES the per-task dispatch contract + execution semantics; it authors no schemas and generates no code (the coding agent does that at dispatch time). It does NOT decompose the plan (that is the build-decompose playbook, upstream — it owns the task graph) and does NOT solve multi-agent SCALE — parallelism across several coding agents, the concurrency schedule, and interleaving the companion generation steps at scale are the downstream scale playbook. v1 scaffold: the single-flight dispatch contract; multi-agent parallelism, a run-completion serializer, and a revert_changeset failure path are later phases (revert is a MUTATING git op outside the read-only change-set carve-out, deliberately deferred).\",\n \"preconditions\": [\n { \"kind\": \"artifact_exists\", \"selector\": { \"family\": \"build-plan\" } }\n ],\n \"inputs\": [\n { \"family\": \"build-plan\" }\n ],\n \"outputs\": [],\n \"method\": {\n \"skillRefs\": [\n ]\n },\n \"executor\": \"coding_agent\",\n \"approval\": \"approve_before\",\n // `maxRuns` is the dispatch-orchestration run budget (one task per run, across the\n // whole build), and since 2026-09-19 (#1344) the LOOP READS IT: a playbook that has spent\n // the ceiling it declares stops being offered, reported in the eligibility trace's\n // `spentRunCeiling`. Sized as a stop against loops, not as cost control.\n //\n // The four ceilings below are NOT read by anything, and this comment said otherwise until\n // 2026-09-20. It described them as \"the WORKING-episode safety envelope the host turns into\n // the Driver's per-episode resource authority (`createApplicationPlaybookWorkingCeiling`\n // refuses a working episode without all four)\" — that function occurs nowhere in the\n // repository any more; it went with the execution-binding demolition of 2026-08-23, and the\n // Block-4 integration proof the note cites belongs to that era. They are KEPT deliberately\n // (Paul, 2026-09-20) as declared intent, not because a consumer reads them; real spend limits\n // belong at the model provider's account, which is the lane's standing posture.\n \"budget\": {\n \"maxRuns\": 30,\n \"maxInputTokens\": 15000000,\n \"maxOutputTokens\": 1000000,\n \"maxModelCalls\": 24,\n \"maxDurationMs\": 3600000\n },\n \"onFailure\": \"keep_and_flag\",\n} as const;\n\n/**\n * The `dispatch-outcome-sound` rubric as an operational semantic evaluation\n * Treatment. The hard floor is DETERMINISTIC and host-computed from the sealed\n * change-set evidence (the coding host's disposition and verification gate),\n * never from model output; the criteria below are the reviewer pass OVER that\n * floor. The mutation-scope assessment is NOT part of the floor: since\n * 2026-09-13 it only records `outOfScopePaths` — which may include a parallel\n * session's edits — for the reviewer to account for. Evidence requirements bind the accepted\n * current-horizon requirements the task serves; the change-set itself enters\n * the evaluation as the episode's working-revision context source.\n */\nexport const evaluationTreatmentSource = {\n schemaVersion: 1,\n definitionRef: 'application-creation:evaluation-treatment/build-task-dispatch',\n // v2 (2026-08-19): the verified-change-set evidence requirement moved to v2 (its subject changed).\n definitionVersion: 2,\n evaluationProtocol: {\n schemaVersion: 1,\n protocolRef: 'application-creation:evaluation-protocol/build-task-dispatch',\n protocolVersion: 1,\n promptAssemblyStrategy: MetaWorkflow_EvaluationPromptAssemblyStrategy.CANONICAL_PROTOCOL_EVIDENCE_V1,\n aggregationStrategy: MetaWorkflow_EvaluationAggregationStrategy.WORST_VERDICT_PRECEDENCE_V1,\n verdictPrecedence: [\n MetaWorkflow_EvaluationVerdict.GAP,\n MetaWorkflow_EvaluationVerdict.INDETERMINATE,\n MetaWorkflow_EvaluationVerdict.CONCERN,\n MetaWorkflow_EvaluationVerdict.PASS,\n ],\n aggregationPolicyRef: 'application-creation:aggregation/worst-build-task-dispatch-verdict',\n criteria: [\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-task-verified-change-set',\n criterionVersion: 1,\n instruction:\n 'Verify the sealed worktree change-set evidence of the dispatched build task. PASS only when the coding host recorded a working result, every required verification check succeeded, and every changed path outside the declared scope (`outOfScopePaths`, which may include a parallel session\\'s edits) is accounted for; an unresolved out-of-scope path is a CONCERN, not an absence of evidence. Never infer verification from the agent\\'s own narrative, and never treat an absent change-set as a passed task.',\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-task-verified-change-set',\n // v2 (2026-08-19): the evidence subject moved from the retired readiness receipt to the\n // current-horizon requirements the task serves.\n requirementVersion: 2,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n // The accepted current-horizon requirements the dispatched task serves; the change-set itself enters\n // the judgment as the working-subject source (it is not accepted knowledge and cannot be projected).\n subjectRef: 'application-creation:definition-set/requirements-current-horizon',\n minCount: 1,\n maxCount: 1,\n coveragePolicyRef: 'application-creation:evidence-policy/current-horizon-requirements',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-accepted-family-heads',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'A working result was recorded, the verification gate passed, and every changed path outside the declared mutation scope is accounted for.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'The gate passed, but the evidence shows a verification check the reviewer cannot independently confirm, or the result records out-of-scope paths (`outOfScopePaths`) whose authorship is unresolved — the change set cannot tell the run\\'s edits from a parallel session\\'s.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'No change-set was recorded, the run failed, or a required verification check failed.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The change-set evidence is absent, malformed or does not bind the dispatched task.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-task-accomplished-in-scope',\n criterionVersion: 1,\n instruction:\n 'Assess whether the attributed change-set actually implements the dispatched task\\'s target and stage (a schema task adds the persisted shape, a ui-behavior task adds field displays, a spec task documents the resource), stays within the task\\'s module/resource/stage, and is cleanly attributable to the run (RUN_EXCLUSIVE / APPEARED_DURING_RUN). Files that were already dirty at the dispatch baseline are review-required and must not be counted against the run. Do not re-decompose the plan, do not author code yourself, and do not reward edits sprawling into unrelated modules.',\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-task-serves-requirements',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/requirements-vision-market',\n minCount: 1,\n maxCount: 2,\n coveragePolicyRef: 'application-creation:evidence-policy/all-current-horizon-requirements',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-accepted-family-heads',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'The change-set advances exactly the dispatched target/stage, inside its scope, with clean attribution.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'The task is advanced but the change-set sprawls beyond its module/resource/stage or its attribution is partly ambiguous.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'The change-set does not advance the dispatched target, or is empty on a task that should have authored files.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The dispatched task or its change-set cannot be identified from the evidence.',\n },\n },\n ],\n },\n evaluatorBindingPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:evaluator-binding-policy/build-task-dispatch',\n policyVersion: 1,\n admissibleEvaluatorSelectors: [{ evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 }],\n defaultEvaluatorSelector: { evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 },\n outputContractSelector: {\n outputContractRef: 'meta-workflow:output-contract/structured-semantic-evaluation-candidate',\n outputContractVersion: 1,\n },\n fallbackPolicyRef: 'application-creation:evaluator-policy/fail-closed',\n escalationPolicyRef: 'application-creation:evaluator-policy/request-explicit-review',\n maximumAttempts: 2,\n timeoutPolicyRef: 'application-creation:evaluator-policy/bounded-semantic-evaluation',\n budgetPolicyRef: 'application-creation:evaluator-policy/current-work-cycle-budget',\n selectionPolicyRef: 'application-creation:evaluator-policy/scoped-risk-and-evidence',\n },\n decisionPointDefinition: {\n schemaVersion: 1,\n decisionPointRef: 'application-creation:decision-point/build-task-dispatch',\n decisionPointVersion: 1,\n triggerRefs: ['application-creation:trigger/build-task-change-set-recorded'],\n hardFloorRefs: ['application-creation:hard-floor/build-task-verified-change-set'],\n riskPolicyRef: 'application-creation:risk-policy/scoped-application-and-execution-context',\n significancePolicyRef: 'application-creation:significance-policy/application-worktree-change',\n },\n decisionRule: {\n schemaVersion: 1,\n ruleRef: 'application-creation:decision-rule/build-task-dispatch',\n ruleVersion: 1,\n boundaryClass: MetaWorkflow_DecisionRuleBoundaryClass.QUALITY_INTERPRETATION,\n evidenceAggregationRef: 'application-creation:aggregation/worst-build-task-dispatch-verdict',\n resultMappings: [\n { verdict: MetaWorkflow_EvaluationVerdict.PASS, consequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY },\n { verdict: MetaWorkflow_EvaluationVerdict.CONCERN, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.GAP, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.INDETERMINATE, consequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE },\n ],\n hardFloorBindings: [{\n hardFloorRef: 'application-creation:hard-floor/build-task-verified-change-set',\n evidenceRequirementRefs: ['application-creation:evidence-requirement/build-task-verified-change-set'],\n }],\n hardFloorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n hardFloorShortcutAllowed: false,\n unresolvedConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE,\n evaluatorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n },\n authorityRequirement: {\n schemaVersion: 1,\n requirementRef: 'application-creation:authority-requirement/build-task-dispatch-result',\n requirementVersion: 1,\n consequenceClassRef: 'application-creation:authority-consequence/accept-build-task-change-set',\n riskClassRef: 'application-creation:risk/application-worktree-horizon-acceptance',\n decisionModePolicyRef: 'application-creation:authority-policy/explicit-operator-confirmation',\n assurancePolicyRef: 'application-creation:authority-policy/local-single-operator',\n channelPolicyRef: 'application-creation:authority-policy/interface-relay',\n principalPolicyRef: null,\n requiredDecisionMode: MetaWorkflow_AuthorityDecisionMode.EXPLICIT_OPERATOR_CONFIRMATION,\n minimumAssurance: MetaWorkflow_AuthorityAssuranceClass.LOCAL_OS_SESSION,\n admittedChannels: [MetaWorkflow_AuthorityInteractionChannel.INTERFACE_RELAY],\n requiredEvidenceRequirementRefs: [\n 'application-creation:evidence-requirement/build-task-verified-change-set',\n 'application-creation:evidence-requirement/build-task-serves-requirements',\n ],\n expiryPolicyRef: 'application-creation:authority-expiry/current-interface-session',\n noncePolicyRef: 'application-creation:authority-nonce/random-per-request',\n hardFloorPosture: MetaWorkflow_HardFloorPosture.NON_WAIVABLE,\n hardFloorOverrideAllowed: false,\n },\n continuationPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:continuation-policy/build-task-dispatch',\n policyVersion: 1,\n mappings: [\n { decisionConsequence: MetaWorkflow_DecisionConsequence.CONTINUE, action: MetaWorkflow_ContinuationAction.CONTINUE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REVISE, action: MetaWorkflow_ContinuationAction.REVISE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE, action: MetaWorkflow_ContinuationAction.REQUEST_EVIDENCE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY, action: MetaWorkflow_ContinuationAction.REQUEST_AUTHORITY },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.BLOCK, action: MetaWorkflow_ContinuationAction.BLOCK },\n ],\n maximumRevisionAttempts: 3,\n maximumEvidenceRequests: 2,\n maximumAuthorityReviews: 1,\n fallbackAction: MetaWorkflow_ContinuationAction.BLOCK,\n },\n} satisfies MetaWorkflowEvaluationTreatmentSource;\n"]}
1
+ {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-dispatch/playbook.definition.ts"],"names":[],"mappings":"AACA,OAAO,EACL,oCAAoC,EACpC,kCAAkC,EAClC,wCAAwC,EACxC,+BAA+B,EAC/B,gCAAgC,EAChC,sCAAsC,EACtC,0CAA0C,EAC1C,6CAA6C,EAC7C,8BAA8B,EAC9B,oCAAoC,EACpC,6BAA6B,GAC9B,MAAM,sCAAsC,CAAC;AAE9C;;;;;;;;;;GAUG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,0BAA0B;IACjC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,6wFAA6wF;IACvxF,eAAe,EAAE;QACf,EAAE,MAAM,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,YAAY,EAAE,EAAE;KACtE;IACD,QAAQ,EAAE;QACR,EAAE,QAAQ,EAAE,YAAY,EAAE;KAC3B;IACD,SAAS,EAAE,EAAE;IACb,QAAQ,EAAE;QACR,WAAW,EAAE,EACZ;KACF;IACD,UAAU,EAAE,cAAc;IAC1B,UAAU,EAAE,gBAAgB;IAC5B,2FAA2F;IAC3F,8HAA8H;IAC9H,mFAAmF;IACnF,yEAAyE;IACzE,EAAE;IACF,0FAA0F;IAC1F,4FAA4F;IAC5F,yFAAyF;IACzF,qFAAqF;IACrF,4FAA4F;IAC5F,2FAA2F;IAC3F,8FAA8F;IAC9F,gFAAgF;IAChF,QAAQ,EAAE;QACR,SAAS,EAAE,EAAE;QACb,gBAAgB,EAAE,QAAQ;QAC1B,iBAAiB,EAAE,OAAO;QAC1B,eAAe,EAAE,EAAE;QACnB,eAAe,EAAE,OAAO;KACzB;IACD,WAAW,EAAE,eAAe;CACpB,CAAC;AAEX;;;;;;;;;;GAUG;AACH,MAAM,CAAC,MAAM,yBAAyB,GAAG;IACvC,aAAa,EAAE,CAAC;IAChB,aAAa,EAAE,+DAA+D;IAC9E,mGAAmG;IACnG,iBAAiB,EAAE,CAAC;IACpB,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,WAAW,EAAE,8DAA8D;QAC3E,eAAe,EAAE,CAAC;QAClB,sBAAsB,EAAE,6CAA6C,CAAC,8BAA8B;QACpG,mBAAmB,EAAE,0CAA0C,CAAC,2BAA2B;QAC3F,iBAAiB,EAAE;YACjB,8BAA8B,CAAC,GAAG;YAClC,8BAA8B,CAAC,aAAa;YAC5C,8BAA8B,CAAC,OAAO;YACtC,8BAA8B,CAAC,IAAI;SACpC;QACD,oBAAoB,EAAE,oEAAoE;QAC1F,QAAQ,EAAE;YACR;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,+DAA+D;gBAC7E,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,ufAAuf;gBACzf,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,0EAA0E;wBAC1F,wFAAwF;wBACxF,gDAAgD;wBAChD,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,qGAAqG;wBACrG,qGAAqG;wBACrG,UAAU,EAAE,kEAAkE;wBAC9E,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,mEAAmE;wBACtF,kBAAkB,EAAE,oEAAoE;wBACxF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,2IAA2I;oBAClL,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,+QAA+Q;oBACzT,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,sFAAsF;oBAC5H,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,oFAAoF;iBACrI;aACF;YACD;gBACE,aAAa,EAAE,CAAC;gBAChB,YAAY,EAAE,iEAAiE;gBAC/E,gBAAgB,EAAE,CAAC;gBACnB,WAAW,EACT,mkBAAmkB;gBACrkB,oBAAoB,EAAE,CAAC;wBACrB,aAAa,EAAE,CAAC;wBAChB,cAAc,EAAE,0EAA0E;wBAC1F,kBAAkB,EAAE,CAAC;wBACrB,IAAI,EAAE,oCAAoC,CAAC,SAAS;wBACpD,UAAU,EAAE,gEAAgE;wBAC5E,QAAQ,EAAE,CAAC;wBACX,QAAQ,EAAE,CAAC;wBACX,iBAAiB,EAAE,uEAAuE;wBAC1F,kBAAkB,EAAE,oEAAoE;wBACxF,YAAY,EAAE,IAAI;wBAClB,qBAAqB,EAAE,IAAI;wBAC3B,kBAAkB,EAAE,IAAI;wBACxB,oBAAoB,EAAE,IAAI;qBAC3B,CAAC;gBACF,eAAe,EAAE;oBACf,CAAC,8BAA8B,CAAC,IAAI,CAAC,EAAE,wGAAwG;oBAC/I,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,0HAA0H;oBACpK,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,+GAA+G;oBACrJ,CAAC,8BAA8B,CAAC,aAAa,CAAC,EAAE,+EAA+E;iBAChI;aACF;SACF;KACF;IACD,sBAAsB,EAAE;QACtB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,mEAAmE;QAC9E,aAAa,EAAE,CAAC;QAChB,4BAA4B,EAAE,CAAC,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE,CAAC;QAC9H,wBAAwB,EAAE,EAAE,YAAY,EAAE,uDAAuD,EAAE,gBAAgB,EAAE,CAAC,EAAE;QACxH,sBAAsB,EAAE;YACtB,iBAAiB,EAAE,wEAAwE;YAC3F,qBAAqB,EAAE,CAAC;SACzB;QACD,iBAAiB,EAAE,mDAAmD;QACtE,mBAAmB,EAAE,+DAA+D;QACpF,eAAe,EAAE,CAAC;QAClB,gBAAgB,EAAE,mEAAmE;QACrF,eAAe,EAAE,iEAAiE;QAClF,kBAAkB,EAAE,gEAAgE;KACrF;IACD,uBAAuB,EAAE;QACvB,aAAa,EAAE,CAAC;QAChB,gBAAgB,EAAE,yDAAyD;QAC3E,oBAAoB,EAAE,CAAC;QACvB,WAAW,EAAE,CAAC,6DAA6D,CAAC;QAC5E,aAAa,EAAE,CAAC,gEAAgE,CAAC;QACjF,aAAa,EAAE,2EAA2E;QAC1F,qBAAqB,EAAE,sEAAsE;KAC9F;IACD,YAAY,EAAE;QACZ,aAAa,EAAE,CAAC;QAChB,OAAO,EAAE,wDAAwD;QACjE,WAAW,EAAE,CAAC;QACd,aAAa,EAAE,sCAAsC,CAAC,sBAAsB;QAC5E,sBAAsB,EAAE,oEAAoE;QAC5F,cAAc,EAAE;YACd,EAAE,OAAO,EAAE,8BAA8B,CAAC,IAAI,EAAE,WAAW,EAAE,gCAAgC,CAAC,iBAAiB,EAAE;YACjH,EAAE,OAAO,EAAE,8BAA8B,CAAC,OAAO,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACzG,EAAE,OAAO,EAAE,8BAA8B,CAAC,GAAG,EAAE,WAAW,EAAE,gCAAgC,CAAC,MAAM,EAAE;YACrG,EAAE,OAAO,EAAE,8BAA8B,CAAC,aAAa,EAAE,WAAW,EAAE,gCAAgC,CAAC,gBAAgB,EAAE;SAC1H;QACD,iBAAiB,EAAE,CAAC;gBAClB,YAAY,EAAE,gEAAgE;gBAC9E,uBAAuB,EAAE,CAAC,0EAA0E,CAAC;aACtG,CAAC;QACF,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;QACnE,wBAAwB,EAAE,KAAK;QAC/B,qBAAqB,EAAE,gCAAgC,CAAC,gBAAgB;QACxE,2BAA2B,EAAE,gCAAgC,CAAC,KAAK;KACpE;IACD,oBAAoB,EAAE;QACpB,aAAa,EAAE,CAAC;QAChB,cAAc,EAAE,uEAAuE;QACvF,kBAAkB,EAAE,CAAC;QACrB,mBAAmB,EAAE,yEAAyE;QAC9F,YAAY,EAAE,mEAAmE;QACjF,qBAAqB,EAAE,sEAAsE;QAC7F,kBAAkB,EAAE,6DAA6D;QACjF,gBAAgB,EAAE,uDAAuD;QACzE,kBAAkB,EAAE,IAAI;QACxB,oBAAoB,EAAE,kCAAkC,CAAC,8BAA8B;QACvF,gBAAgB,EAAE,oCAAoC,CAAC,gBAAgB;QACvE,gBAAgB,EAAE,CAAC,wCAAwC,CAAC,eAAe,CAAC;QAC5E,+BAA+B,EAAE;YAC/B,0EAA0E;YAC1E,0EAA0E;SAC3E;QACD,eAAe,EAAE,iEAAiE;QAClF,cAAc,EAAE,yDAAyD;QACzE,gBAAgB,EAAE,6BAA6B,CAAC,YAAY;QAC5D,wBAAwB,EAAE,KAAK;KAChC;IACD,kBAAkB,EAAE;QAClB,aAAa,EAAE,CAAC;QAChB,SAAS,EAAE,8DAA8D;QACzE,aAAa,EAAE,CAAC;QAChB,QAAQ,EAAE;YACR,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,QAAQ,EAAE,MAAM,EAAE,+BAA+B,CAAC,QAAQ,EAAE;YACpH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,MAAM,EAAE,MAAM,EAAE,+BAA+B,CAAC,MAAM,EAAE;YAChH,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,gBAAgB,EAAE,MAAM,EAAE,+BAA+B,CAAC,gBAAgB,EAAE;YACpI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,iBAAiB,EAAE,MAAM,EAAE,+BAA+B,CAAC,iBAAiB,EAAE;YACtI,EAAE,mBAAmB,EAAE,gCAAgC,CAAC,KAAK,EAAE,MAAM,EAAE,+BAA+B,CAAC,KAAK,EAAE;SAC/G;QACD,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,uBAAuB,EAAE,CAAC;QAC1B,cAAc,EAAE,+BAA+B,CAAC,KAAK;KACtD;CAC8C,CAAC","sourcesContent":["import type { MetaWorkflowEvaluationTreatmentSource } from '@wildo-ai/saas-backend-lib/meta-workflow-runtime';\nimport {\n MetaWorkflow_AuthorityAssuranceClass,\n MetaWorkflow_AuthorityDecisionMode,\n MetaWorkflow_AuthorityInteractionChannel,\n MetaWorkflow_ContinuationAction,\n MetaWorkflow_DecisionConsequence,\n MetaWorkflow_DecisionRuleBoundaryClass,\n MetaWorkflow_EvaluationAggregationStrategy,\n MetaWorkflow_EvaluationPromptAssemblyStrategy,\n MetaWorkflow_EvaluationVerdict,\n MetaWorkflow_EvidenceRequirementKind,\n MetaWorkflow_HardFloorPosture,\n} from '@wildo-ai/saas-models/meta-workflows';\n\n/**\n * Canonical native declaration for this reusable application-creation method.\n *\n * The structured method remains intentionally rich: its intent, inputs, output\n * contracts, elicitation, deterministic verification and skill routing are the\n * application knowledge the generic assessment loop composes. Since the build\n * vertical joined the private assessment episode, this playbook ALSO declares\n * the assessment policy, episode target, bounds and the semantic evaluation\n * Treatment that judge ONE dispatched build-plan task's worktree change-set\n * (the `dispatch-outcome-sound` rubric below, made operational).\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-dispatch\",\n \"version\": \"0.1.0\",\n \"phase\": \"bottom_up\",\n \"intent\": \"Bottom-up build dispatch — the SECOND build-execution playbook, the pivot from DECOMPOSING the build (the build-plan task graph) to DISPATCHING it: turning one ordered task into an actually-run, verified coding-agent run under the D4 dispatch contract. Reads the approved TYPED build-plan (`BuildPlanTaskGraph` — each task carries a closed target kind, ONE MetaWorkflow_FunctionalTopic, its skill refs, and DECLARED prerequisite task refs) and the current journey state, selects the READY tasks (`selectReadyBuildPlanTasks`: every declared prerequisite has landed — resolved by the host, never inferred from prose) and dispatches them as a WAVE: up to the application's build parallelism at once (`wildo workbench parallelism`, 5 by default; 1 = one workspace-mutating run at a time), in ONE shared worktree, each slot refilled as its run settles. Each task in the wave runs the same typed contract: (1) the runner builds the context pack (task brief + the task's skill pointers + the relevant journey/definition artifacts + introspected app reality + repo paths); (2) it runs ONE prompt turn against the coding agent over the Agent Client Protocol, in a session rooted at the app workspace (cwd = app root, so CLAUDE.md / .claude skills load naturally), answering the agent's permission requests within the execution profile's declared ceiling and refusing anything above it or outside the task's mutation scope; (3) it captures the change-set around the run (git baseline/post-run worktree snapshots → per-file attribution → a structured GitChangeSetCapture recorded on the task row); (4) it runs the VERIFY gate OUTSIDE the coding agent (a deterministic typecheck the runner maps onto the dispatch verification hook — pnpm exec tsc --noEmit — the trust-but-verify floor); (5) it records the result + applies the onFailure disposition (keep_and_flag: a failed/timed-out run keeps its captured change-set flagged for human triage, never a silent half-applied state). When the wave's runs have settled, the runner commits what their own accepts left as one change naming every run it carries, and re-runs ALONE each task whose finished product a sibling overwrote; each run's record names what overlapped it (`concurrency`, `interferenceSuspected`). One run of this playbook is one bounded wave; run it again for the next. This playbook PRODUCES the per-task dispatch contract + execution semantics; it authors no schemas and generates no code (the coding agent does that at dispatch time). It does NOT decompose the plan (that is the build-decompose playbook, upstream — it owns the task graph) and does NOT choose the wave's width (the build parallelism is the person's setting). A revert_changeset failure path is a later phase (revert is a MUTATING git op outside the read-only change-set carve-out, deliberately deferred).\",\n \"preconditions\": [\n { \"kind\": \"artifact_exists\", \"selector\": { \"family\": \"build-plan\" } }\n ],\n \"inputs\": [\n { \"family\": \"build-plan\" }\n ],\n \"outputs\": [],\n \"method\": {\n \"skillRefs\": [\n ]\n },\n \"executor\": \"coding_agent\",\n \"approval\": \"approve_before\",\n // `maxRuns` is the dispatch-orchestration run budget (one wave per run — one task when the\n // build parallelism is 1 — across the whole build), and since 2026-09-19 (#1344) the LOOP READS IT: a playbook that has spent\n // the ceiling it declares stops being offered, reported in the eligibility trace's\n // `spentRunCeiling`. Sized as a stop against loops, not as cost control.\n //\n // The four ceilings below are NOT read by anything, and this comment said otherwise until\n // 2026-09-20. It described them as \"the WORKING-episode safety envelope the host turns into\n // the Driver's per-episode resource authority (`createApplicationPlaybookWorkingCeiling`\n // refuses a working episode without all four)\" — that function occurs nowhere in the\n // repository any more; it went with the execution-binding demolition of 2026-08-23, and the\n // Block-4 integration proof the note cites belongs to that era. They are KEPT deliberately\n // (Paul, 2026-09-20) as declared intent, not because a consumer reads them; real spend limits\n // belong at the model provider's account, which is the lane's standing posture.\n \"budget\": {\n \"maxRuns\": 30,\n \"maxInputTokens\": 15000000,\n \"maxOutputTokens\": 1000000,\n \"maxModelCalls\": 24,\n \"maxDurationMs\": 3600000\n },\n \"onFailure\": \"keep_and_flag\",\n} as const;\n\n/**\n * The `dispatch-outcome-sound` rubric as an operational semantic evaluation\n * Treatment. The hard floor is DETERMINISTIC and host-computed from the sealed\n * change-set evidence (the coding host's disposition and verification gate),\n * never from model output; the criteria below are the reviewer pass OVER that\n * floor. The mutation-scope assessment is NOT part of the floor: since\n * 2026-09-13 it only records `outOfScopePaths` — which may include a parallel\n * session's edits — for the reviewer to account for. Evidence requirements bind the accepted\n * current-horizon requirements the task serves; the change-set itself enters\n * the evaluation as the episode's working-revision context source.\n */\nexport const evaluationTreatmentSource = {\n schemaVersion: 1,\n definitionRef: 'application-creation:evaluation-treatment/build-task-dispatch',\n // v2 (2026-08-19): the verified-change-set evidence requirement moved to v2 (its subject changed).\n definitionVersion: 2,\n evaluationProtocol: {\n schemaVersion: 1,\n protocolRef: 'application-creation:evaluation-protocol/build-task-dispatch',\n protocolVersion: 1,\n promptAssemblyStrategy: MetaWorkflow_EvaluationPromptAssemblyStrategy.CANONICAL_PROTOCOL_EVIDENCE_V1,\n aggregationStrategy: MetaWorkflow_EvaluationAggregationStrategy.WORST_VERDICT_PRECEDENCE_V1,\n verdictPrecedence: [\n MetaWorkflow_EvaluationVerdict.GAP,\n MetaWorkflow_EvaluationVerdict.INDETERMINATE,\n MetaWorkflow_EvaluationVerdict.CONCERN,\n MetaWorkflow_EvaluationVerdict.PASS,\n ],\n aggregationPolicyRef: 'application-creation:aggregation/worst-build-task-dispatch-verdict',\n criteria: [\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-task-verified-change-set',\n criterionVersion: 1,\n instruction:\n 'Verify the sealed worktree change-set evidence of the dispatched build task. PASS only when the coding host recorded a working result, every required verification check succeeded, and every changed path outside the declared scope (`outOfScopePaths`, which may include a parallel session\\'s edits) is accounted for; an unresolved out-of-scope path is a CONCERN, not an absence of evidence. Never infer verification from the agent\\'s own narrative, and never treat an absent change-set as a passed task.',\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-task-verified-change-set',\n // v2 (2026-08-19): the evidence subject moved from the retired readiness receipt to the\n // current-horizon requirements the task serves.\n requirementVersion: 2,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n // The accepted current-horizon requirements the dispatched task serves; the change-set itself enters\n // the judgment as the working-subject source (it is not accepted knowledge and cannot be projected).\n subjectRef: 'application-creation:definition-set/requirements-current-horizon',\n minCount: 1,\n maxCount: 1,\n coveragePolicyRef: 'application-creation:evidence-policy/current-horizon-requirements',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-accepted-family-heads',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'A working result was recorded, the verification gate passed, and every changed path outside the declared mutation scope is accounted for.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'The gate passed, but the evidence shows a verification check the reviewer cannot independently confirm, or the result records out-of-scope paths (`outOfScopePaths`) whose authorship is unresolved — the change set cannot tell the run\\'s edits from a parallel session\\'s.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'No change-set was recorded, the run failed, or a required verification check failed.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The change-set evidence is absent, malformed or does not bind the dispatched task.',\n },\n },\n {\n schemaVersion: 1,\n criterionRef: 'application-creation:criterion/build-task-accomplished-in-scope',\n criterionVersion: 1,\n instruction:\n 'Assess whether the attributed change-set actually implements the dispatched task\\'s target and stage (a schema task adds the persisted shape, a ui-behavior task adds field displays, a spec task documents the resource), stays within the task\\'s module/resource/stage, and is cleanly attributable to the run (RUN_EXCLUSIVE / APPEARED_DURING_RUN). Files that were already dirty at the dispatch baseline are review-required and must not be counted against the run. Do not re-decompose the plan, do not author code yourself, and do not reward edits sprawling into unrelated modules.',\n evidenceRequirements: [{\n schemaVersion: 1,\n requirementRef: 'application-creation:evidence-requirement/build-task-serves-requirements',\n requirementVersion: 1,\n kind: MetaWorkflow_EvidenceRequirementKind.MANDATORY,\n subjectRef: 'application-creation:definition-set/requirements-vision-market',\n minCount: 1,\n maxCount: 2,\n coveragePolicyRef: 'application-creation:evidence-policy/all-current-horizon-requirements',\n freshnessPolicyRef: 'application-creation:evidence-policy/current-accepted-family-heads',\n conditionRef: null,\n independencePolicyRef: null,\n diversityPolicyRef: null,\n aggregationPolicyRef: null,\n }],\n verdictGuidance: {\n [MetaWorkflow_EvaluationVerdict.PASS]: 'The change-set advances exactly the dispatched target/stage, inside its scope, with clean attribution.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'The task is advanced but the change-set sprawls beyond its module/resource/stage or its attribution is partly ambiguous.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'The change-set does not advance the dispatched target, or is empty on a task that should have authored files.',\n [MetaWorkflow_EvaluationVerdict.INDETERMINATE]: 'The dispatched task or its change-set cannot be identified from the evidence.',\n },\n },\n ],\n },\n evaluatorBindingPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:evaluator-binding-policy/build-task-dispatch',\n policyVersion: 1,\n admissibleEvaluatorSelectors: [{ evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 }],\n defaultEvaluatorSelector: { evaluatorRef: 'meta-workflow:evaluator/structured-semantic-coherence', evaluatorVersion: 1 },\n outputContractSelector: {\n outputContractRef: 'meta-workflow:output-contract/structured-semantic-evaluation-candidate',\n outputContractVersion: 1,\n },\n fallbackPolicyRef: 'application-creation:evaluator-policy/fail-closed',\n escalationPolicyRef: 'application-creation:evaluator-policy/request-explicit-review',\n maximumAttempts: 2,\n timeoutPolicyRef: 'application-creation:evaluator-policy/bounded-semantic-evaluation',\n budgetPolicyRef: 'application-creation:evaluator-policy/current-work-cycle-budget',\n selectionPolicyRef: 'application-creation:evaluator-policy/scoped-risk-and-evidence',\n },\n decisionPointDefinition: {\n schemaVersion: 1,\n decisionPointRef: 'application-creation:decision-point/build-task-dispatch',\n decisionPointVersion: 1,\n triggerRefs: ['application-creation:trigger/build-task-change-set-recorded'],\n hardFloorRefs: ['application-creation:hard-floor/build-task-verified-change-set'],\n riskPolicyRef: 'application-creation:risk-policy/scoped-application-and-execution-context',\n significancePolicyRef: 'application-creation:significance-policy/application-worktree-change',\n },\n decisionRule: {\n schemaVersion: 1,\n ruleRef: 'application-creation:decision-rule/build-task-dispatch',\n ruleVersion: 1,\n boundaryClass: MetaWorkflow_DecisionRuleBoundaryClass.QUALITY_INTERPRETATION,\n evidenceAggregationRef: 'application-creation:aggregation/worst-build-task-dispatch-verdict',\n resultMappings: [\n { verdict: MetaWorkflow_EvaluationVerdict.PASS, consequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY },\n { verdict: MetaWorkflow_EvaluationVerdict.CONCERN, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.GAP, consequence: MetaWorkflow_DecisionConsequence.REVISE },\n { verdict: MetaWorkflow_EvaluationVerdict.INDETERMINATE, consequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE },\n ],\n hardFloorBindings: [{\n hardFloorRef: 'application-creation:hard-floor/build-task-verified-change-set',\n evidenceRequirementRefs: ['application-creation:evidence-requirement/build-task-verified-change-set'],\n }],\n hardFloorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n hardFloorShortcutAllowed: false,\n unresolvedConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE,\n evaluatorFailureConsequence: MetaWorkflow_DecisionConsequence.BLOCK,\n },\n authorityRequirement: {\n schemaVersion: 1,\n requirementRef: 'application-creation:authority-requirement/build-task-dispatch-result',\n requirementVersion: 1,\n consequenceClassRef: 'application-creation:authority-consequence/accept-build-task-change-set',\n riskClassRef: 'application-creation:risk/application-worktree-horizon-acceptance',\n decisionModePolicyRef: 'application-creation:authority-policy/explicit-operator-confirmation',\n assurancePolicyRef: 'application-creation:authority-policy/local-single-operator',\n channelPolicyRef: 'application-creation:authority-policy/interface-relay',\n principalPolicyRef: null,\n requiredDecisionMode: MetaWorkflow_AuthorityDecisionMode.EXPLICIT_OPERATOR_CONFIRMATION,\n minimumAssurance: MetaWorkflow_AuthorityAssuranceClass.LOCAL_OS_SESSION,\n admittedChannels: [MetaWorkflow_AuthorityInteractionChannel.INTERFACE_RELAY],\n requiredEvidenceRequirementRefs: [\n 'application-creation:evidence-requirement/build-task-verified-change-set',\n 'application-creation:evidence-requirement/build-task-serves-requirements',\n ],\n expiryPolicyRef: 'application-creation:authority-expiry/current-interface-session',\n noncePolicyRef: 'application-creation:authority-nonce/random-per-request',\n hardFloorPosture: MetaWorkflow_HardFloorPosture.NON_WAIVABLE,\n hardFloorOverrideAllowed: false,\n },\n continuationPolicy: {\n schemaVersion: 1,\n policyRef: 'application-creation:continuation-policy/build-task-dispatch',\n policyVersion: 1,\n mappings: [\n { decisionConsequence: MetaWorkflow_DecisionConsequence.CONTINUE, action: MetaWorkflow_ContinuationAction.CONTINUE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REVISE, action: MetaWorkflow_ContinuationAction.REVISE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_EVIDENCE, action: MetaWorkflow_ContinuationAction.REQUEST_EVIDENCE },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.REQUEST_AUTHORITY, action: MetaWorkflow_ContinuationAction.REQUEST_AUTHORITY },\n { decisionConsequence: MetaWorkflow_DecisionConsequence.BLOCK, action: MetaWorkflow_ContinuationAction.BLOCK },\n ],\n maximumRevisionAttempts: 3,\n maximumEvidenceRequests: 2,\n maximumAuthorityReviews: 1,\n fallbackAction: MetaWorkflow_ContinuationAction.BLOCK,\n },\n} satisfies MetaWorkflowEvaluationTreatmentSource;\n"]}
@@ -11,7 +11,7 @@ export declare const playbookDefinition: {
11
11
  readonly ref: "bottom_up.build-scale";
12
12
  readonly version: "0.1.0";
13
13
  readonly phase: "bottom_up";
14
- readonly intent: "Bottom-up build scale — the THIRD and final build-execution playbook, the pivot from dispatching ONE task safely (the single-flight dispatch contract) to running the build at SCALE: parallelism across several coding agents, the concurrency schedule, and interleaving the companion-owned generation steps concurrently with coding runs. Reads the approved build-plan (the ordered coding-agent task graph, each task carrying a target, ONE MetaWorkflow_FunctionalTopic, its skill(s), and prose prerequisite ordering) and the current journey state, and answers the SCALE questions the single-flight dispatch playbook deliberately left open: (1) derive the ready-SET (a wave / frontier of tasks whose prose prerequisites have ALL SUCCEEDED — not merely been attempted); (2) decide the parallelism degree (how many coding agents run at once) and the worktree-isolation model that keeps each concurrent run's change-set cleanly attributable; (3) schedule the waves respecting the DEPENDS_ON ordering the build-plan encodes; (4) interleave the deterministic companion-owned generation steps (labels / i18n, email templates, seeds) concurrently with coding runs at the points their inputs exist — those steps run through their deterministic companion endpoints, NOT the coding-agent single-flight lock, so they genuinely overlap coding runs; (5) reconcile wave completion across the concurrent runs (all tasks in the frontier SUCCEEDED before the next wave opens) and apply onFailure across siblings + downstream. Then advance to the next wave and loop. Each parallel slot INVOKES the single-flight dispatch contract (the build-dispatch playbook, upstream — select-next / context-pack / one ACP prompt turn / change-set capture / verify-outside / record + onFailure); this playbook does NOT re-specify those per-task mechanics and does NOT re-decompose the plan (the build-decompose playbook owns the task graph) and authors no schemas / no code. IMPORTANT HONESTY: the companion runner HARD-ENFORCES single-flight today (a run plan carries at most ONE coding-agent task; a concurrent dispatch is refused; the workspace-mutation lock + the lock-free cursor + the missing run-outcome observation loop all assume one dispatch at a time). So this v1 scale METHOD is the DECLARATIVE TARGET a runner-serializer slice will realize — on the current runner the waves DEGRADE to sequential single-flight dispatch. And even the deterministic companion-generation steps, though they do not take the coding single-flight lock, cannot SAFELY overlap an active coding run today: the coding run's change-set is captured as a whole-worktree time-window diff, so a generation step writing files inside that window is misattributed to the coding run (the same whole-worktree pollution that forbids two concurrent coding agents) — so the generation steps also serialize outside an active coding-capture window today, and genuine concurrency (coding-parallel OR generation-overlap) both arrive only with the git worktree-per-agent isolation runner task. v1 scaffold: a multi-CODING_AGENT run-completion serializer, git worktree-per-agent isolation, a run-outcome reconciler, and a cursor lock are companion-runner mechanism filed as runner tasks, NOT built here; a priority/work-stealing scheduler and cost-optimal packing are a later depth phase.";
14
+ readonly intent: "Bottom-up build scale — the THIRD build-execution playbook: how the build runs at SCALE, as shipped. A run of a build-execution playbook starts a WAVE: up to the application's build parallelism of build-plan tasks at once (`wildo workbench parallelism`, 5 by default; 1 = one task at a time, the single-flight mode), in ONE shared worktree, as a rolling pool that refills each slot with whatever is ready when a run settles. This playbook declares the same CODING_AGENT executor as the build-dispatch playbook and runs through the same runtime branch, so both start the SAME wave; prefer build-dispatch to start a build, and read this one for the scale questions: (1) the ready-SET — tasks whose declared prerequisites have ALL SUCCEEDED, not merely been attempted, resolved by the host from the declared refs and git; (2) the width — the build parallelism, the person's setting, never chosen by the method; (3) the isolation model — none by decision: the runs share the worktree, only a task being built twice at once is prevented, and overlap is RECORDED on each run (`concurrency`, `interferenceSuspected`); (4) the deterministic companion-owned generation steps (labels / i18n, email templates, seeds) — run through their companion endpoints at their input-ready point, inline while live coding runs continue, at most once per wave; (5) the wave's end — bounded at four dispatches per slot per call, it drains its live runs, commits what their own accepts left as ONE change naming every run it carries, re-runs ALONE each completed task whose product a sibling overwrote, and applies keep_and_flag across siblings + dependents. Each slot runs the per-task dispatch contract of the build-dispatch playbook; this playbook does NOT re-specify it, does NOT re-decompose the plan (the build-decompose playbook owns the task graph), and authors no schemas / no code. A priority / work-stealing scheduler, cost-optimal packing and a revert_changeset failure path are later phases.";
15
15
  readonly preconditions: readonly [{
16
16
  readonly kind: "artifact_exists";
17
17
  readonly selector: {
@@ -11,7 +11,7 @@ export const playbookDefinition = {
11
11
  "ref": "bottom_up.build-scale",
12
12
  "version": "0.1.0",
13
13
  "phase": "bottom_up",
14
- "intent": "Bottom-up build scale — the THIRD and final build-execution playbook, the pivot from dispatching ONE task safely (the single-flight dispatch contract) to running the build at SCALE: parallelism across several coding agents, the concurrency schedule, and interleaving the companion-owned generation steps concurrently with coding runs. Reads the approved build-plan (the ordered coding-agent task graph, each task carrying a target, ONE MetaWorkflow_FunctionalTopic, its skill(s), and prose prerequisite ordering) and the current journey state, and answers the SCALE questions the single-flight dispatch playbook deliberately left open: (1) derive the ready-SET (a wave / frontier of tasks whose prose prerequisites have ALL SUCCEEDED — not merely been attempted); (2) decide the parallelism degree (how many coding agents run at once) and the worktree-isolation model that keeps each concurrent run's change-set cleanly attributable; (3) schedule the waves respecting the DEPENDS_ON ordering the build-plan encodes; (4) interleave the deterministic companion-owned generation steps (labels / i18n, email templates, seeds) concurrently with coding runs at the points their inputs exist — those steps run through their deterministic companion endpoints, NOT the coding-agent single-flight lock, so they genuinely overlap coding runs; (5) reconcile wave completion across the concurrent runs (all tasks in the frontier SUCCEEDED before the next wave opens) and apply onFailure across siblings + downstream. Then advance to the next wave and loop. Each parallel slot INVOKES the single-flight dispatch contract (the build-dispatch playbook, upstream — select-next / context-pack / one ACP prompt turn / change-set capture / verify-outside / record + onFailure); this playbook does NOT re-specify those per-task mechanics and does NOT re-decompose the plan (the build-decompose playbook owns the task graph) and authors no schemas / no code. IMPORTANT HONESTY: the companion runner HARD-ENFORCES single-flight today (a run plan carries at most ONE coding-agent task; a concurrent dispatch is refused; the workspace-mutation lock + the lock-free cursor + the missing run-outcome observation loop all assume one dispatch at a time). So this v1 scale METHOD is the DECLARATIVE TARGET a runner-serializer slice will realize — on the current runner the waves DEGRADE to sequential single-flight dispatch. And even the deterministic companion-generation steps, though they do not take the coding single-flight lock, cannot SAFELY overlap an active coding run today: the coding run's change-set is captured as a whole-worktree time-window diff, so a generation step writing files inside that window is misattributed to the coding run (the same whole-worktree pollution that forbids two concurrent coding agents) — so the generation steps also serialize outside an active coding-capture window today, and genuine concurrency (coding-parallel OR generation-overlap) both arrive only with the git worktree-per-agent isolation runner task. v1 scaffold: a multi-CODING_AGENT run-completion serializer, git worktree-per-agent isolation, a run-outcome reconciler, and a cursor lock are companion-runner mechanism filed as runner tasks, NOT built here; a priority/work-stealing scheduler and cost-optimal packing are a later depth phase.",
14
+ "intent": "Bottom-up build scale — the THIRD build-execution playbook: how the build runs at SCALE, as shipped. A run of a build-execution playbook starts a WAVE: up to the application's build parallelism of build-plan tasks at once (`wildo workbench parallelism`, 5 by default; 1 = one task at a time, the single-flight mode), in ONE shared worktree, as a rolling pool that refills each slot with whatever is ready when a run settles. This playbook declares the same CODING_AGENT executor as the build-dispatch playbook and runs through the same runtime branch, so both start the SAME wave; prefer build-dispatch to start a build, and read this one for the scale questions: (1) the ready-SET — tasks whose declared prerequisites have ALL SUCCEEDED, not merely been attempted, resolved by the host from the declared refs and git; (2) the width — the build parallelism, the person's setting, never chosen by the method; (3) the isolation model — none by decision: the runs share the worktree, only a task being built twice at once is prevented, and overlap is RECORDED on each run (`concurrency`, `interferenceSuspected`); (4) the deterministic companion-owned generation steps (labels / i18n, email templates, seeds) — run through their companion endpoints at their input-ready point, inline while live coding runs continue, at most once per wave; (5) the wave's end — bounded at four dispatches per slot per call, it drains its live runs, commits what their own accepts left as ONE change naming every run it carries, re-runs ALONE each completed task whose product a sibling overwrote, and applies keep_and_flag across siblings + dependents. Each slot runs the per-task dispatch contract of the build-dispatch playbook; this playbook does NOT re-specify it, does NOT re-decompose the plan (the build-decompose playbook owns the task graph), and authors no schemas / no code. A priority / work-stealing scheduler, cost-optimal packing and a revert_changeset failure path are later phases.",
15
15
  "preconditions": [
16
16
  { "kind": "artifact_exists", "selector": { "family": "build-plan" } }
17
17
  ],