@wildo-ai/framework-knowledge 1.1.2 → 1.1.4

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 (289) hide show
  1. package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
  2. package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
  3. package/dist/esm/framework-knowledge.definitions.js +351 -18
  4. package/dist/esm/framework-knowledge.definitions.js.map +1 -1
  5. package/dist/esm/framework-knowledge.loader.d.ts.map +1 -1
  6. package/dist/esm/framework-knowledge.schemas.d.ts +1 -2
  7. package/dist/esm/framework-knowledge.schemas.d.ts.map +1 -1
  8. package/dist/esm/framework-knowledge.schemas.js.map +1 -1
  9. package/dist/esm/index.d.ts.map +1 -1
  10. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +3 -4
  11. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts.map +1 -1
  12. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +4 -4
  13. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -1
  14. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +3 -4
  15. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts.map +1 -1
  16. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +4 -4
  17. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
  18. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +0 -1
  19. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts.map +1 -1
  20. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +0 -1
  21. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
  22. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +0 -1
  23. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts.map +1 -1
  24. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +0 -1
  25. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
  26. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +1 -2
  27. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
  28. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +1 -2
  29. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
  30. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +2 -3
  31. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
  32. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +3 -3
  33. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
  34. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts +1 -2
  35. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts.map +1 -1
  36. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js +1 -2
  37. package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js.map +1 -1
  38. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts +0 -1
  39. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.d.ts.map +1 -1
  40. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.js +0 -1
  41. package/dist/esm/playbooks/refinement.compliance-document-candidate/playbook.definition.js.map +1 -1
  42. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts +0 -1
  43. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts.map +1 -1
  44. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js +0 -1
  45. package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js.map +1 -1
  46. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +0 -1
  47. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
  48. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +0 -1
  49. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
  50. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +0 -1
  51. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
  52. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +0 -1
  53. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
  54. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts +0 -1
  55. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.d.ts.map +1 -1
  56. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js +0 -1
  57. package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js.map +1 -1
  58. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +0 -2
  59. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -1
  60. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +2 -2
  61. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -1
  62. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +0 -1
  63. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -1
  64. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +0 -1
  65. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
  66. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts +0 -1
  67. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts.map +1 -1
  68. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js +0 -1
  69. package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js.map +1 -1
  70. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +0 -1
  71. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
  72. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +0 -1
  73. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
  74. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts +0 -1
  75. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts.map +1 -1
  76. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js +0 -1
  77. package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js.map +1 -1
  78. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts +0 -2
  79. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.d.ts.map +1 -1
  80. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js +9 -4
  81. package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js.map +1 -1
  82. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.d.ts +0 -1
  83. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.d.ts.map +1 -1
  84. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.js +0 -1
  85. package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.js.map +1 -1
  86. package/dist/esm/playbooks/top_down.market-research/playbook.definition.d.ts +0 -1
  87. package/dist/esm/playbooks/top_down.market-research/playbook.definition.d.ts.map +1 -1
  88. package/dist/esm/playbooks/top_down.market-research/playbook.definition.js +0 -1
  89. package/dist/esm/playbooks/top_down.market-research/playbook.definition.js.map +1 -1
  90. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts +0 -1
  91. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts.map +1 -1
  92. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js +0 -1
  93. package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js.map +1 -1
  94. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +0 -1
  95. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
  96. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +0 -1
  97. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
  98. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts +0 -1
  99. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts.map +1 -1
  100. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js +0 -1
  101. package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js.map +1 -1
  102. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +0 -1
  103. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
  104. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +0 -1
  105. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
  106. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts +0 -1
  107. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts.map +1 -1
  108. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js +0 -1
  109. package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js.map +1 -1
  110. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +0 -1
  111. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
  112. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +0 -1
  113. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
  114. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
  115. package/dist/knowledge/manifest.json +8 -9
  116. package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +13 -70
  117. package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +11 -19
  118. package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +5 -88
  119. package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +15 -8
  120. package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +4 -5
  121. package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +15 -8
  122. package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +4 -0
  123. package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +8 -7
  124. package/dist/knowledge/playbooks/bottom_up.foundation/method.md +22 -49
  125. package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +8 -17
  126. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +15 -780
  127. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +11 -11
  128. package/dist/knowledge/playbooks/refinement.document-facts/method.md +20 -141
  129. package/dist/knowledge/playbooks/refinement.document-facts/playbook.json +15 -10
  130. package/dist/knowledge/playbooks/top_down.brand-identity/method.md +3 -2
  131. package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +16 -11
  132. package/dist/knowledge/playbooks/top_down.business-model/playbook.json +14 -6
  133. package/dist/knowledge/playbooks/top_down.capability-map/method.md +4 -2
  134. package/dist/knowledge/playbooks/top_down.capability-map/playbook.json +16 -7
  135. package/dist/knowledge/playbooks/top_down.compliance-posture/method.md +4 -21
  136. package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +65 -16
  137. package/dist/knowledge/playbooks/{top_down.market-snapshot-produce → top_down.market-analysis}/evaluation-protocol.json +1 -1
  138. package/dist/knowledge/playbooks/{top_down.market-snapshot-produce → top_down.market-analysis}/evaluation-treatment.json +1 -1
  139. package/dist/knowledge/playbooks/top_down.market-analysis/method.md +165 -51
  140. package/dist/knowledge/playbooks/top_down.market-analysis/playbook.json +43 -23
  141. package/dist/knowledge/playbooks/top_down.phase-gate/method.md +4 -8
  142. package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +7 -9
  143. package/dist/knowledge/playbooks/top_down.requirements-definition/method.md +7 -9
  144. package/dist/knowledge/playbooks/top_down.requirements-definition/playbook.json +15 -7
  145. package/dist/knowledge/playbooks/top_down.scope-roadmap/method.md +3 -3
  146. package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +16 -11
  147. package/dist/knowledge/playbooks/top_down.value-proposition/method.md +4 -2
  148. package/dist/knowledge/playbooks/top_down.value-proposition/playbook.json +15 -7
  149. package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +2 -2
  150. package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +16 -11
  151. package/dist/knowledge/references/build-plan.task-graph.config.md +1 -45
  152. package/dist/knowledge/references/companion.technical-doc.service.md +2 -102
  153. package/dist/knowledge/references/example.config.app-shell.full.md +5 -0
  154. package/dist/knowledge/references/example.module.companion-exports.full.md +0 -1
  155. package/dist/knowledge/references/example.provider.backend-module-shape.md +0 -7
  156. package/dist/knowledge/references/example.resource.add-resource.module-factory-map.md +1 -0
  157. package/dist/knowledge/references/platform.config.saas.md +0 -51
  158. package/dist/knowledge/references/presets.models.surface-policy.md +10 -19
  159. package/dist/knowledge/references/saas.external-data.admin-endpoints.md +48 -0
  160. package/dist/knowledge/references/saas.frontend.app-level-component.configuration.md +11 -31
  161. package/dist/knowledge/references/saas.frontend.app-level-component.vocabulary.md +1 -0
  162. package/dist/knowledge/references/saas.frontend.composite-view.authoring.md +0 -45
  163. package/dist/knowledge/references/saas.frontend.resource-operation-frontend-config.md +0 -198
  164. package/dist/knowledge/references/saas.models.data-mode-read-list.md +0 -164
  165. package/dist/knowledge/references/saas.models.engine-capabilities.md +6 -26
  166. package/dist/knowledge/references/saas.models.http-api-binding.md +29 -3
  167. package/dist/knowledge/references/saas.models.provider-capabilities.md +3 -4
  168. package/dist/knowledge/references/saas.models.resource-config.builder-parameters.md +2 -4
  169. package/dist/knowledge/references/saas.models.resource-config.resource-configuration.md +0 -2
  170. package/dist/knowledge/references/saas.models.resource-config.resources-registry.md +0 -14
  171. package/dist/knowledge/references/saas.specifications.application-document-fact-specification.contract.md +31 -11
  172. package/dist/knowledge/references/saas.specifications.assurance-document-blueprint.contract.md +2 -32
  173. package/dist/knowledge/references/saas.specifications.assurance-program.contract.md +6 -29
  174. package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +0 -56
  175. package/dist/knowledge/references/saas.specifications.resource-spec-config.md +0 -22
  176. package/dist/knowledge/references/zod.decorators.chainable-runtime.md +0 -26
  177. package/dist/knowledge/references/zod.decorators.decorator-vocabulary.md +0 -45
  178. package/dist/knowledge/references/zod.decorators.display-edit-modes.md +1 -7
  179. package/dist/knowledge/references/zod.decorators.field-spec-params.md +5 -31
  180. package/dist/knowledge/references/zod.decorators.per-primitive-ui.md +1 -44
  181. package/dist/knowledge/references/zod.decorators.primitive-ui.md +0 -3
  182. package/dist/knowledge/references/zod.decorators.schema-metadata.md +0 -1
  183. package/dist/knowledge/references/zod.decorators.shared-structural-params.md +0 -15
  184. package/dist/knowledge/registries/assurance-authority-bases.json +2 -3
  185. package/dist/knowledge/registries/framework-topics.json +11 -146
  186. package/dist/knowledge/registries/playbooks.json +18 -154
  187. package/dist/knowledge/registries/source-tags.json +630 -883
  188. package/dist/knowledge/skills/INDEX.md +3 -4
  189. package/dist/knowledge/skills/brand-logo-authoring/SKILL.md +1 -2
  190. package/dist/knowledge/skills/compliance-document-authoring/SKILL.md +2 -16
  191. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-governance.md +9 -31
  192. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +74 -252
  193. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-service-terms.md +8 -26
  194. package/dist/knowledge/skills/compliance-document-authoring/references/framework-application-document-fact-specification-contract.md +53 -97
  195. package/dist/knowledge/skills/compliance-document-authoring/references/framework-assurance-document-blueprint-contract.md +21 -84
  196. package/dist/knowledge/skills/config-app-shell/SKILL.md +9 -31
  197. package/dist/knowledge/skills/config-app-shell/references/framework-app-shell-api.md +12 -31
  198. package/dist/knowledge/skills/config-design-system/SKILL.md +1 -23
  199. package/dist/knowledge/skills/config-design-system/references/framework-surface-policy-api.md +10 -19
  200. package/dist/knowledge/skills/config-navigation/SKILL.md +2 -75
  201. package/dist/knowledge/skills/config-saas/SKILL.md +2 -19
  202. package/dist/knowledge/skills/config-saas/references/framework-provider-capabilities-api.md +9 -30
  203. package/dist/knowledge/skills/config-saas/references/framework-wildo-saas-config-api.md +0 -51
  204. package/dist/knowledge/skills/configure-billing/references/example-backend-provider-module-shape.md +0 -7
  205. package/dist/knowledge/skills/flows-actors-a2a-exposure/SKILL.md +1 -2
  206. package/dist/knowledge/skills/flows-actors-a2a-exposure/references/framework-flows-actors-a2a-contract.md +3 -4
  207. package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +0 -56
  208. package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +0 -56
  209. package/dist/knowledge/skills/module-companion-exports/SKILL.md +0 -1
  210. package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +0 -56
  211. package/dist/knowledge/skills/resource-add-field/SKILL.md +3 -3
  212. package/dist/knowledge/skills/resource-add-field/references/framework-field-cross-layer-api.md +0 -213
  213. package/dist/knowledge/skills/resource-add-resource/SKILL.md +1 -2
  214. package/dist/knowledge/skills/resource-add-resource/references/framework-new-resource-core-config-api.md +2 -4
  215. package/dist/knowledge/skills/resource-config-wiring/SKILL.md +0 -15
  216. package/dist/knowledge/skills/resource-config-wiring/references/framework-saas-models-resource-config-api.md +2 -224
  217. package/dist/knowledge/skills/resource-custom-view/references/custom-view-contracts.md +0 -198
  218. package/dist/knowledge/skills/resource-external-data/SKILL.md +2 -0
  219. package/dist/knowledge/skills/resource-external-data/references/framework-http-api-binding-api.md +29 -3
  220. package/dist/knowledge/skills/resource-external-data/references/framework-pipeline-admin-endpoints-api.md +70 -0
  221. package/dist/knowledge/skills/resource-mcp-tool-exposure/SKILL.md +1 -22
  222. package/dist/knowledge/skills/resource-rag-source-fields/references/framework-embeddings-capability-api.md +8 -28
  223. package/dist/knowledge/skills/resource-schema-authoring/SKILL.md +0 -1
  224. package/dist/knowledge/skills/resource-schema-authoring/references/decorator-layer-map.md +0 -17
  225. package/dist/knowledge/skills/resource-schema-authoring/references/framework-decorator-vocabulary-api.md +0 -46
  226. package/dist/knowledge/skills/resource-schema-authoring/references/framework-shared-structural-params-api.md +0 -15
  227. package/dist/knowledge/skills/resource-schema-authoring/references/framework-zod-lifecycle-and-chainable-api.md +0 -26
  228. package/dist/knowledge/skills/resource-ui-behavior/references/framework-display-edit-modes-api.md +1 -7
  229. package/dist/knowledge/skills/resource-ui-behavior/references/framework-frontend-resource-ui-contracts-api.md +0 -198
  230. package/dist/knowledge/skills/resource-ui-behavior/references/framework-per-primitive-ui-api.md +1 -44
  231. package/dist/knowledge/skills/resource-ui-behavior/references/framework-primitive-ui-api.md +0 -3
  232. package/dist/knowledge/skills/spec-companion-exports/SKILL.md +0 -1
  233. package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +0 -56
  234. package/dist/knowledge/skills/spec-resource-update/references/framework-field-spec-params-api.md +5 -31
  235. package/dist/knowledge/skills/spec-resource-update/references/framework-spec-resource-contracts-api.md +0 -22
  236. package/dist/knowledge/skills/views-composite-authoring/references/framework-composite-view-contracts-api.md +0 -45
  237. package/dist/knowledge/topic-index.json +220 -725
  238. package/dist/tsconfig.build.tsbuildinfo +1 -1
  239. package/dist/tsconfig.tsbuildinfo +1 -1
  240. package/package.json +4 -4
  241. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +0 -1
  242. package/dist/knowledge/playbooks/bottom_up.assemble-verify/method.md +0 -51
  243. package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +0 -43
  244. package/dist/knowledge/playbooks/bottom_up.placement-plan/method.md +0 -185
  245. package/dist/knowledge/playbooks/bottom_up.placement-plan/playbook.json +0 -64
  246. package/dist/knowledge/playbooks/top_down.compliance-analysis/method.md +0 -41
  247. package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +0 -100
  248. package/dist/knowledge/playbooks/top_down.compliance-conception/method.md +0 -117
  249. package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +0 -86
  250. package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/method.md +0 -61
  251. package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/playbook.json +0 -41
  252. package/dist/knowledge/playbooks/top_down.compliance-research/method.md +0 -76
  253. package/dist/knowledge/playbooks/top_down.compliance-research/playbook.json +0 -42
  254. package/dist/knowledge/playbooks/top_down.market-evidence-adequacy/method.md +0 -56
  255. package/dist/knowledge/playbooks/top_down.market-evidence-adequacy/playbook.json +0 -42
  256. package/dist/knowledge/playbooks/top_down.market-research/method.md +0 -68
  257. package/dist/knowledge/playbooks/top_down.market-research/playbook.json +0 -44
  258. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/method.md +0 -239
  259. package/dist/knowledge/playbooks/top_down.market-snapshot-produce/playbook.json +0 -67
  260. package/dist/knowledge/references/placement-plan.config.md +0 -330
  261. package/dist/knowledge/references/saas.frontend.display-layout.reading-measure.md +0 -34
  262. package/dist/knowledge/references/saas.frontend.navigation.operation-override.md +0 -45
  263. package/dist/knowledge/references/saas.frontend.public-shell.identity-mode.md +0 -65
  264. package/dist/knowledge/references/saas.frontend.settings-hub.engine-destinations.md +0 -58
  265. package/dist/knowledge/references/saas.frontend.settings-hub.placement.md +0 -118
  266. package/dist/knowledge/references/saas.models.file-upload-grant.md +0 -179
  267. package/dist/knowledge/references/saas.models.navigation.surface-vocabulary.md +0 -124
  268. package/dist/knowledge/references/saas.models.navigation.transition-vocabulary.md +0 -99
  269. package/dist/knowledge/references/saas.models.navigation.zone-declaration.md +0 -127
  270. package/dist/knowledge/references/saas.models.resource-config.operation-variant-client-timeout.md +0 -42
  271. package/dist/knowledge/references/saas.specifications.application-authored-document-fact-specification.contract.md +0 -29
  272. package/dist/knowledge/references/zod.decorators.data-categories.md +0 -197
  273. package/dist/knowledge/rules/resource-schema-awareness.md +0 -77
  274. package/dist/knowledge/skills/config-app-shell/references/framework-public-shell-identity-api.md +0 -124
  275. package/dist/knowledge/skills/config-design-system/references/loading-placeholder-authoring.md +0 -47
  276. package/dist/knowledge/skills/config-navigation/references/framework-content-width-api.md +0 -98
  277. package/dist/knowledge/skills/config-navigation/references/framework-navigation-operation-override-api.md +0 -54
  278. package/dist/knowledge/skills/config-navigation/references/framework-navigation-vocabulary-api.md +0 -232
  279. package/dist/knowledge/skills/config-navigation/references/framework-navigation-zone-declaration-api.md +0 -149
  280. package/dist/knowledge/skills/config-navigation/references/how-navigation-resolves.md +0 -114
  281. package/dist/knowledge/skills/config-navigation/references/navigation-configuration-map.md +0 -133
  282. package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +0 -111
  283. package/dist/knowledge/skills/resource-config-wiring/references/framework-personal-data-declaration-api.md +0 -622
  284. package/dist/knowledge/skills/resource-mcp-tool-exposure/references/framework-file-upload-grant-contract.md +0 -192
  285. package/dist/knowledge/skills/resource-schema-authoring/references/framework-personal-data-category-api.md +0 -245
  286. package/dist/knowledge/skills/settings-placement-authoring/SKILL.md +0 -134
  287. package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-destinations-catalog.md +0 -65
  288. package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-placement-api.md +0 -127
  289. /package/dist/knowledge/playbooks/{top_down.market-snapshot-produce → top_down.market-analysis}/structured-artifact-action.json +0 -0
@@ -1 +1 @@
1
- {"version":3,"file":"framework-knowledge.loader.d.ts","sourceRoot":"","sources":["../../../src/framework-knowledge.loader.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EACV,yCAAyC,EAEzC,sDAAsD,EACtD,0BAA0B,EAC1B,8BAA8B,EAC9B,0BAA0B,EAE1B,uCAAuC,EACvC,oCAAoC,EACpC,6BAA6B,EAC7B,uBAAuB,EACvB,4BAA4B,EAC5B,iCAAiC,EAClC,MAAM,kCAAkC,CAAC;AAC1C,OAAO,EAAwC,8BAA8B,EAAE,MAAM,kCAAkC,CAAC;AAoExH,wBAAgB,kCAAkC,CAAC,YAAY,EAAE,MAAM,GAAG,MAAM,CAE/E;AAED,wBAAgB,qCAAqC,IAAI,8BAA8B,CAAC,0BAA0B,CAAC,CAalH;AAED,wBAAgB,6BAA6B,IAAI,0BAA0B,CAE1E;AAED,wBAAgB,gCAAgC,IAAI,oCAAoC,EAAE,CAEzF;AAED,wBAAgB,+BAA+B,IAAI,4BAA4B,CAE9E;AAED,wBAAgB,4BAA4B,IAAI,iCAAiC,EAAE,CAElF;AAED,wBAAgB,0BAA0B,CAAC,OAAO,EAAE,MAAM,GAAG,uBAAuB,GAAG,IAAI,CAyB1F;AAED,wBAAgB,6BAA6B,CAAC,aAAa,SAAS,8BAA8B,EAChG,YAAY,EAAE,aAAa,GAC1B,6BAA6B,CAAC,aAAa,CAAC,CAE9C;AAED;;;GAGG;AACH,wBAAgB,+BAA+B,IAAI,uCAAuC,EAAE,CAK3F;AAED;;;;;;;;;GASG;AACH,wBAAgB,6BAA6B,CAAC,GAAG,EAAE,MAAM,GAAG,0BAA0B,GAAG,IAAI,CAmD5F;AAED,4EAA4E;AAC5E,wBAAgB,6CAA6C,IAAI,sDAAsD,EAAE,CAGxH;AAED;;;;;;GAMG;AACH,wBAAgB,4CAA4C,CAAC,GAAG,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,MAAM,GAAG,yCAAyC,GAAG,IAAI,CA0B5I;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,wBAAgB,sDAAsD,CACpE,GAAG,EAAE,MAAM,EACX,OAAO,CAAC,EAAE,MAAM,GACf,8BAA8B,CAAC,OAAO,CAAC,GAAG,IAAI,CAWhD;AAED;;;;;GAKG;AACH;;;;;;;GAOG;AACH,MAAM,WAAW,8BAA8B;IAC7C,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;CAC1B;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,oCAAoC,IAAI,8BAA8B,EAAE,CAsBvF;AAED,wBAAgB,gCAAgC,IAAI,MAAM,GAAG,IAAI,CAQhE"}
1
+ {"version":3,"file":"framework-knowledge.loader.d.ts","sourceRoot":"","sources":["../../src/framework-knowledge.loader.ts"],"names":[],"mappings":"AAKA,OAAO,KAAK,EACV,yCAAyC,EAEzC,sDAAsD,EACtD,0BAA0B,EAC1B,8BAA8B,EAC9B,0BAA0B,EAE1B,uCAAuC,EACvC,oCAAoC,EACpC,6BAA6B,EAC7B,uBAAuB,EACvB,4BAA4B,EAC5B,iCAAiC,EAClC,MAAM,kCAAkC,CAAC;AAC1C,OAAO,EAAwC,8BAA8B,EAAE,MAAM,kCAAkC,CAAC;AAoExH,wBAAgB,kCAAkC,CAAC,YAAY,EAAE,MAAM,GAAG,MAAM,CAE/E;AAED,wBAAgB,qCAAqC,IAAI,8BAA8B,CAAC,0BAA0B,CAAC,CAalH;AAED,wBAAgB,6BAA6B,IAAI,0BAA0B,CAE1E;AAED,wBAAgB,gCAAgC,IAAI,oCAAoC,EAAE,CAEzF;AAED,wBAAgB,+BAA+B,IAAI,4BAA4B,CAE9E;AAED,wBAAgB,4BAA4B,IAAI,iCAAiC,EAAE,CAElF;AAED,wBAAgB,0BAA0B,CAAC,OAAO,EAAE,MAAM,GAAG,uBAAuB,GAAG,IAAI,CAyB1F;AAED,wBAAgB,6BAA6B,CAAC,aAAa,SAAS,8BAA8B,EAChG,YAAY,EAAE,aAAa,GAC1B,6BAA6B,CAAC,aAAa,CAAC,CAE9C;AAED;;;GAGG;AACH,wBAAgB,+BAA+B,IAAI,uCAAuC,EAAE,CAK3F;AAED;;;;;;;;;GASG;AACH,wBAAgB,6BAA6B,CAAC,GAAG,EAAE,MAAM,GAAG,0BAA0B,GAAG,IAAI,CAmD5F;AAED,4EAA4E;AAC5E,wBAAgB,6CAA6C,IAAI,sDAAsD,EAAE,CAGxH;AAED;;;;;;GAMG;AACH,wBAAgB,4CAA4C,CAAC,GAAG,EAAE,MAAM,EAAE,OAAO,CAAC,EAAE,MAAM,GAAG,yCAAyC,GAAG,IAAI,CA0B5I;AAED;;;;;;;;;;;;;;;;;GAiBG;AACH,wBAAgB,sDAAsD,CACpE,GAAG,EAAE,MAAM,EACX,OAAO,CAAC,EAAE,MAAM,GACf,8BAA8B,CAAC,OAAO,CAAC,GAAG,IAAI,CAWhD;AAED;;;;;GAKG;AACH;;;;;;;GAOG;AACH,MAAM,WAAW,8BAA8B;IAC7C,QAAQ,CAAC,IAAI,EAAE,MAAM,CAAC;IACtB,QAAQ,CAAC,OAAO,EAAE,MAAM,CAAC;CAC1B;AAED;;;;;;;;;;;;;;GAcG;AACH,wBAAgB,oCAAoC,IAAI,8BAA8B,EAAE,CAsBvF;AAED,wBAAgB,gCAAgC,IAAI,MAAM,GAAG,IAAI,CAQhE"}
@@ -116,7 +116,7 @@ export interface FrameworkKnowledgeSourceTagRegistryEntry {
116
116
  /**
117
117
  * One compiled meta-workflow playbook, as listed in the `playbooks` registry.
118
118
  *
119
- * Enum-backed playbook fields (`phase`, `executor`, `functionalTopics`) are
119
+ * Enum-backed playbook fields (`phase`, `executor`) are
120
120
  * surfaced as plain strings here: this package has zero dependencies by
121
121
  * design, so it cannot import the `MetaWorkflow_*` enums from
122
122
  * `@wildo-ai/saas-specifications`. Consumers that need the typed contract must parse
@@ -131,7 +131,6 @@ export interface FrameworkKnowledgePlaybookRegistryEntry {
131
131
  /** Absent when the playbook runs no single tier — see `MetaWorkflow_Executor` (#115). */
132
132
  executor?: string;
133
133
  intent: string;
134
- functionalTopics: string[];
135
134
  /** App-knowledge skill ids the playbook's method delegates the technical HOW to. */
136
135
  skillRefs: string[];
137
136
  /** Payload-relative path of the compiled `playbook.json`. */
@@ -1 +1 @@
1
- {"version":3,"file":"framework-knowledge.schemas.d.ts","sourceRoot":"","sources":["../../../src/framework-knowledge.schemas.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,oCAAoC,MAAM,CAAC;AAExD,oBAAY,8BAA8B;IACxC,WAAW,gBAAgB;IAC3B,gBAAgB,qBAAqB;IACrC,SAAS,cAAc;IACvB,yBAAyB,8BAA8B;CACxD;AAED,oBAAY,qCAAqC;IAC/C,SAAS,cAAc;IACvB,UAAU,eAAe;CAC1B;AAED;;;;GAIG;AACH,oBAAY,sCAAsC;IAChD,gCAAgC,qCAAqC;CACtE;AAED;;;;;;;GAOG;AACH,MAAM,WAAW,kCAAkC;IACjD,cAAc,EAAE,MAAM,CAAC;IACvB,mBAAmB,EAAE,MAAM,CAAC;IAC5B,mBAAmB,EAAE,MAAM,CAAC;IAC5B,eAAe,EAAE,MAAM,CAAC;IACxB,6FAA6F;IAC7F,kBAAkB,EAAE,MAAM,CAAC;IAC3B,2DAA2D;IAC3D,2GAA2G;IAC3G,gCAAgC,EAAE,MAAM,CAAC;IACzC;;;;;;;;;;OAUG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;CAC1B;AAED,MAAM,WAAW,oCAAoC;IACnD,YAAY,EAAE,8BAA8B,CAAC;IAC7C,QAAQ,EAAE,MAAM,CAAC;IACjB,WAAW,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,0BAA0B;IACzC,eAAe,EAAE,MAAM,CAAC;IACxB,gBAAgB,EAAE,MAAM,CAAC;IACzB,gBAAgB,EAAE,MAAM,CAAC;IACzB,WAAW,EAAE,MAAM,CAAC;IACpB,WAAW,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,MAAM,CAAC;IACnB,kBAAkB,EAAE,MAAM,CAAC;IAC3B,OAAO,EAAE,kCAAkC,CAAC;IAC5C,UAAU,EAAE,oCAAoC,EAAE,CAAC;CACpD;AAED,MAAM,WAAW,iCAAiC;IAChD,IAAI,EAAE,qCAAqC,CAAC;IAC5C,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,iCAAiC;IAChD,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,gBAAgB,EAAE,iCAAiC,EAAE,CAAC;IACtD,cAAc,EAAE,MAAM,EAAE,CAAC;IACzB,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,YAAY,EAAE,8BAA8B,EAAE,CAAC;CAChD;AAED,MAAM,WAAW,4BAA4B;IAC3C,MAAM,EAAE,iCAAiC,EAAE,CAAC;CAC7C;AAED,MAAM,WAAW,uBAAuB;IACtC,KAAK,EAAE,iCAAiC,CAAC;IACzC,gBAAgB,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACzC,YAAY,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CACtC;AAED,MAAM,WAAW,oCAAoC;IACnD,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,iBAAiB,CAAC,EAAE,MAAM,CAAC;IAC3B,oBAAoB,EAAE,MAAM,CAAC;CAC9B;AAED,MAAM,WAAW,wCAAwC;IACvD,iBAAiB,EAAE,MAAM,CAAC;IAC1B,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,WAAW,EAAE,MAAM,CAAC;IACpB,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,gBAAgB,EAAE,iCAAiC,EAAE,CAAC;CACvD;AAED;;;;;;;;;;GAUG;AACH,MAAM,WAAW,uCAAuC;IACtD,GAAG,EAAE,MAAM,CAAC;IACZ,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,yFAAyF;IACzF,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;IACf,gBAAgB,EAAE,MAAM,EAAE,CAAC;IAC3B,oFAAoF;IACpF,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,6DAA6D;IAC7D,gBAAgB,EAAE,MAAM,CAAC;IACzB,yDAAyD;IACzD,cAAc,EAAE,MAAM,CAAC;IACvB,wEAAwE;IACxE,YAAY,EAAE,sCAAsC,CAAC;IACrD,kBAAkB,CAAC,EAAE;QACnB,WAAW,EAAE,MAAM,CAAC;QACpB,eAAe,EAAE,MAAM,CAAC;QACxB,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;IACF,mBAAmB,CAAC,EAAE;QACpB,aAAa,EAAE,MAAM,CAAC;QACtB,iBAAiB,EAAE,MAAM,CAAC;QAC1B,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;IACF,wBAAwB,CAAC,EAAE;QACzB,aAAa,EAAE,MAAM,CAAC;QACtB,iBAAiB,EAAE,MAAM,CAAC;QAC1B,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;CACH;AAED;;;;;;;;GAQG;AACH,MAAM,WAAW,sDAAsD;IACrE,GAAG,EAAE,MAAM,CAAC;IACZ,OAAO,EAAE,MAAM,CAAC;IAChB,iBAAiB,EAAE,MAAM,CAAC;IAC1B,QAAQ,EAAE,MAAM,CAAC;IACjB;;;;;;;;;;OAUG;IACH,gCAAgC,CAAC,EAAE,MAAM,CAAC;CAC3C;AAED,iHAAiH;AACjH,MAAM,WAAW,yCAAyC;IACxD,KAAK,EAAE,sDAAsD,CAAC;IAC9D,KAAK,EAAE,OAAO,CAAC;IACf,KAAK,EAAE,UAAU,CAAC;CACnB;AAED,8EAA8E;AAC9E,MAAM,WAAW,8BAA8B,CAAC,MAAM;IACpD,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,UAAU,CAAC;CACnB;AAED;;GAEG;AACH,MAAM,WAAW,0BAA0B;IACzC,KAAK,EAAE,uCAAuC,CAAC;IAC/C;;;;;;OAMG;IACH,QAAQ,EAAE,OAAO,CAAC;IAClB,uEAAuE;IACvE,aAAa,EAAE,UAAU,CAAC;IAC1B,+EAA+E;IAC/E,cAAc,EAAE,MAAM,CAAC;IACvB,mEAAmE;IACnE,WAAW,EAAE,UAAU,CAAC;IACxB,4FAA4F;IAC5F,kBAAkB,EAAE;QAClB,KAAK,EAAE,OAAO,CAAC;QACf,KAAK,EAAE,UAAU,CAAC;KACnB,GAAG,IAAI,CAAC;IACT,6FAA6F;IAC7F,mBAAmB,EAAE;QACnB,KAAK,EAAE,OAAO,CAAC;QACf,KAAK,EAAE,UAAU,CAAC;KACnB,GAAG,IAAI,CAAC;IACT,uFAAuF;IACvF,wBAAwB,EAAE;QACxB,KAAK,EAAE,OAAO,CAAC;QACf,KAAK,EAAE,UAAU,CAAC;KACnB,GAAG,IAAI,CAAC;CACV;AAED,MAAM,WAAW,8BAA8B,CAAC,KAAK,SAAS,8BAA8B,EAAE,MAAM;IAClG,IAAI,EAAE,KAAK,CAAC;IACZ,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IACnC,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CACjC;AAED,MAAM,MAAM,mCAAmC,GAAG,8BAA8B,CAC9E,8BAA8B,CAAC,WAAW,EAC1C,wCAAwC,CACzC,CAAC;AAEF,MAAM,MAAM,+BAA+B,GAAG,8BAA8B,CAC1E,8BAA8B,CAAC,gBAAgB,EAC/C,oCAAoC,CACrC,CAAC;AAEF,MAAM,MAAM,kCAAkC,GAAG,8BAA8B,CAC7E,8BAA8B,CAAC,SAAS,EACxC,uCAAuC,CACxC,CAAC;AAEF,MAAM,MAAM,iDAAiD,GAAG,8BAA8B,CAC5F,8BAA8B,CAAC,yBAAyB,EACxD,sDAAsD,CACvD,CAAC;AAEF,MAAM,WAAW,6BAA6B;IAC5C,CAAC,8BAA8B,CAAC,WAAW,CAAC,EAAE,mCAAmC,CAAC;IAClF,CAAC,8BAA8B,CAAC,gBAAgB,CAAC,EAAE,+BAA+B,CAAC;IACnF,CAAC,8BAA8B,CAAC,SAAS,CAAC,EAAE,kCAAkC,CAAC;IAC/E,CAAC,8BAA8B,CAAC,yBAAyB,CAAC,EAAE,iDAAiD,CAAC;CAC/G;AAED,MAAM,MAAM,0BAA0B,GAAG,6BAA6B,CAAC,8BAA8B,CAAC,CAAC"}
1
+ {"version":3,"file":"framework-knowledge.schemas.d.ts","sourceRoot":"","sources":["../../src/framework-knowledge.schemas.ts"],"names":[],"mappings":"AAAA,eAAO,MAAM,oCAAoC,MAAM,CAAC;AAExD,oBAAY,8BAA8B;IACxC,WAAW,gBAAgB;IAC3B,gBAAgB,qBAAqB;IACrC,SAAS,cAAc;IACvB,yBAAyB,8BAA8B;CACxD;AAED,oBAAY,qCAAqC;IAC/C,SAAS,cAAc;IACvB,UAAU,eAAe;CAC1B;AAED;;;;GAIG;AACH,oBAAY,sCAAsC;IAChD,gCAAgC,qCAAqC;CACtE;AAED;;;;;;;GAOG;AACH,MAAM,WAAW,kCAAkC;IACjD,cAAc,EAAE,MAAM,CAAC;IACvB,mBAAmB,EAAE,MAAM,CAAC;IAC5B,mBAAmB,EAAE,MAAM,CAAC;IAC5B,eAAe,EAAE,MAAM,CAAC;IACxB,6FAA6F;IAC7F,kBAAkB,EAAE,MAAM,CAAC;IAC3B,2DAA2D;IAC3D,2GAA2G;IAC3G,gCAAgC,EAAE,MAAM,CAAC;IACzC;;;;;;;;;;OAUG;IACH,cAAc,CAAC,EAAE,MAAM,CAAC;IACxB;;;;;;OAMG;IACH,eAAe,CAAC,EAAE,MAAM,CAAC;CAC1B;AAED,MAAM,WAAW,oCAAoC;IACnD,YAAY,EAAE,8BAA8B,CAAC;IAC7C,QAAQ,EAAE,MAAM,CAAC;IACjB,WAAW,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,MAAM,CAAC;CACpB;AAED,MAAM,WAAW,0BAA0B;IACzC,eAAe,EAAE,MAAM,CAAC;IACxB,gBAAgB,EAAE,MAAM,CAAC;IACzB,gBAAgB,EAAE,MAAM,CAAC;IACzB,WAAW,EAAE,MAAM,CAAC;IACpB,WAAW,EAAE,MAAM,CAAC;IACpB,UAAU,EAAE,MAAM,CAAC;IACnB,kBAAkB,EAAE,MAAM,CAAC;IAC3B,OAAO,EAAE,kCAAkC,CAAC;IAC5C,UAAU,EAAE,oCAAoC,EAAE,CAAC;CACpD;AAED,MAAM,WAAW,iCAAiC;IAChD,IAAI,EAAE,qCAAqC,CAAC;IAC5C,OAAO,EAAE,MAAM,CAAC;IAChB,QAAQ,EAAE,MAAM,CAAC;IACjB,SAAS,CAAC,EAAE,MAAM,CAAC;IACnB,OAAO,CAAC,EAAE,MAAM,CAAC;CAClB;AAED,MAAM,WAAW,iCAAiC;IAChD,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,IAAI,EAAE,MAAM,EAAE,CAAC;IACf,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,gBAAgB,EAAE,iCAAiC,EAAE,CAAC;IACtD,cAAc,EAAE,MAAM,EAAE,CAAC;IACzB,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,YAAY,EAAE,8BAA8B,EAAE,CAAC;CAChD;AAED,MAAM,WAAW,4BAA4B;IAC3C,MAAM,EAAE,iCAAiC,EAAE,CAAC;CAC7C;AAED,MAAM,WAAW,uBAAuB;IACtC,KAAK,EAAE,iCAAiC,CAAC;IACzC,gBAAgB,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;IACzC,YAAY,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CACtC;AAED,MAAM,WAAW,oCAAoC;IACnD,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,UAAU,EAAE,MAAM,EAAE,CAAC;IACrB,iBAAiB,CAAC,EAAE,MAAM,CAAC;IAC3B,oBAAoB,EAAE,MAAM,CAAC;CAC9B;AAED,MAAM,WAAW,wCAAwC;IACvD,iBAAiB,EAAE,MAAM,CAAC;IAC1B,aAAa,CAAC,EAAE,MAAM,CAAC;IACvB,WAAW,EAAE,MAAM,CAAC;IACpB,MAAM,EAAE,MAAM,EAAE,CAAC;IACjB,gBAAgB,EAAE,iCAAiC,EAAE,CAAC;CACvD;AAED;;;;;;;;;;GAUG;AACH,MAAM,WAAW,uCAAuC;IACtD,GAAG,EAAE,MAAM,CAAC;IACZ,OAAO,EAAE,MAAM,CAAC;IAChB,KAAK,EAAE,MAAM,CAAC;IACd,yFAAyF;IACzF,QAAQ,CAAC,EAAE,MAAM,CAAC;IAClB,MAAM,EAAE,MAAM,CAAC;IACf,oFAAoF;IACpF,SAAS,EAAE,MAAM,EAAE,CAAC;IACpB,6DAA6D;IAC7D,gBAAgB,EAAE,MAAM,CAAC;IACzB,yDAAyD;IACzD,cAAc,EAAE,MAAM,CAAC;IACvB,wEAAwE;IACxE,YAAY,EAAE,sCAAsC,CAAC;IACrD,kBAAkB,CAAC,EAAE;QACnB,WAAW,EAAE,MAAM,CAAC;QACpB,eAAe,EAAE,MAAM,CAAC;QACxB,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;IACF,mBAAmB,CAAC,EAAE;QACpB,aAAa,EAAE,MAAM,CAAC;QACtB,iBAAiB,EAAE,MAAM,CAAC;QAC1B,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;IACF,wBAAwB,CAAC,EAAE;QACzB,aAAa,EAAE,MAAM,CAAC;QACtB,iBAAiB,EAAE,MAAM,CAAC;QAC1B,QAAQ,EAAE,MAAM,CAAC;KAClB,CAAC;CACH;AAED;;;;;;;;GAQG;AACH,MAAM,WAAW,sDAAsD;IACrE,GAAG,EAAE,MAAM,CAAC;IACZ,OAAO,EAAE,MAAM,CAAC;IAChB,iBAAiB,EAAE,MAAM,CAAC;IAC1B,QAAQ,EAAE,MAAM,CAAC;IACjB;;;;;;;;;;OAUG;IACH,gCAAgC,CAAC,EAAE,MAAM,CAAC;CAC3C;AAED,iHAAiH;AACjH,MAAM,WAAW,yCAAyC;IACxD,KAAK,EAAE,sDAAsD,CAAC;IAC9D,KAAK,EAAE,OAAO,CAAC;IACf,KAAK,EAAE,UAAU,CAAC;CACnB;AAED,8EAA8E;AAC9E,MAAM,WAAW,8BAA8B,CAAC,MAAM;IACpD,KAAK,EAAE,MAAM,CAAC;IACd,KAAK,EAAE,UAAU,CAAC;CACnB;AAED;;GAEG;AACH,MAAM,WAAW,0BAA0B;IACzC,KAAK,EAAE,uCAAuC,CAAC;IAC/C;;;;;;OAMG;IACH,QAAQ,EAAE,OAAO,CAAC;IAClB,uEAAuE;IACvE,aAAa,EAAE,UAAU,CAAC;IAC1B,+EAA+E;IAC/E,cAAc,EAAE,MAAM,CAAC;IACvB,mEAAmE;IACnE,WAAW,EAAE,UAAU,CAAC;IACxB,4FAA4F;IAC5F,kBAAkB,EAAE;QAClB,KAAK,EAAE,OAAO,CAAC;QACf,KAAK,EAAE,UAAU,CAAC;KACnB,GAAG,IAAI,CAAC;IACT,6FAA6F;IAC7F,mBAAmB,EAAE;QACnB,KAAK,EAAE,OAAO,CAAC;QACf,KAAK,EAAE,UAAU,CAAC;KACnB,GAAG,IAAI,CAAC;IACT,uFAAuF;IACvF,wBAAwB,EAAE;QACxB,KAAK,EAAE,OAAO,CAAC;QACf,KAAK,EAAE,UAAU,CAAC;KACnB,GAAG,IAAI,CAAC;CACV;AAED,MAAM,WAAW,8BAA8B,CAAC,KAAK,SAAS,8BAA8B,EAAE,MAAM;IAClG,IAAI,EAAE,KAAK,CAAC;IACZ,QAAQ,CAAC,EAAE,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,CAAC;IACnC,OAAO,EAAE,MAAM,CAAC,MAAM,EAAE,MAAM,CAAC,CAAC;CACjC;AAED,MAAM,MAAM,mCAAmC,GAAG,8BAA8B,CAC9E,8BAA8B,CAAC,WAAW,EAC1C,wCAAwC,CACzC,CAAC;AAEF,MAAM,MAAM,+BAA+B,GAAG,8BAA8B,CAC1E,8BAA8B,CAAC,gBAAgB,EAC/C,oCAAoC,CACrC,CAAC;AAEF,MAAM,MAAM,kCAAkC,GAAG,8BAA8B,CAC7E,8BAA8B,CAAC,SAAS,EACxC,uCAAuC,CACxC,CAAC;AAEF,MAAM,MAAM,iDAAiD,GAAG,8BAA8B,CAC5F,8BAA8B,CAAC,yBAAyB,EACxD,sDAAsD,CACvD,CAAC;AAEF,MAAM,WAAW,6BAA6B;IAC5C,CAAC,8BAA8B,CAAC,WAAW,CAAC,EAAE,mCAAmC,CAAC;IAClF,CAAC,8BAA8B,CAAC,gBAAgB,CAAC,EAAE,+BAA+B,CAAC;IACnF,CAAC,8BAA8B,CAAC,SAAS,CAAC,EAAE,kCAAkC,CAAC;IAC/E,CAAC,8BAA8B,CAAC,yBAAyB,CAAC,EAAE,iDAAiD,CAAC;CAC/G;AAED,MAAM,MAAM,0BAA0B,GAAG,6BAA6B,CAAC,8BAA8B,CAAC,CAAC"}
@@ -1 +1 @@
1
- {"version":3,"file":"framework-knowledge.schemas.js","sourceRoot":"","sources":["../../../src/framework-knowledge.schemas.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,oCAAoC,GAAG,GAAG,CAAC;AAExD,MAAM,CAAN,IAAY,8BAKX;AALD,WAAY,8BAA8B;IACxC,6DAA2B,CAAA;IAC3B,uEAAqC,CAAA;IACrC,yDAAuB,CAAA;IACvB,yFAAuD,CAAA;AACzD,CAAC,EALW,8BAA8B,KAA9B,8BAA8B,QAKzC;AAED,MAAM,CAAN,IAAY,qCAGX;AAHD,WAAY,qCAAqC;IAC/C,gEAAuB,CAAA;IACvB,kEAAyB,CAAA;AAC3B,CAAC,EAHW,qCAAqC,KAArC,qCAAqC,QAGhD;AAED;;;;GAIG;AACH,MAAM,CAAN,IAAY,sCAEX;AAFD,WAAY,sCAAsC;IAChD,+GAAqE,CAAA;AACvE,CAAC,EAFW,sCAAsC,KAAtC,sCAAsC,QAEjD","sourcesContent":["export const FRAMEWORK_KNOWLEDGE_ARTIFACT_VERSION = '3';\n\nexport enum FrameworkKnowledgeRegistryName {\n SOURCE_TAGS = 'source-tags',\n FRAMEWORK_TOPICS = 'framework-topics',\n PLAYBOOKS = 'playbooks',\n ASSURANCE_AUTHORITY_BASES = 'assurance-authority-bases',\n}\n\nexport enum FrameworkKnowledgeSourceReferenceKind {\n FULL_FILE = 'full-file',\n PART_RANGE = 'part-range',\n}\n\n/**\n * The JSON-v1 authoring format was retired (and its member deleted) at the\n * first-activation hard cut; every authored playbook is an effect-free native\n * TypeScript declaration.\n */\nexport enum FrameworkKnowledgePlaybookSourceFormat {\n EFFECT_FREE_TYPESCRIPT_MODULE_V1 = 'EFFECT_FREE_TYPESCRIPT_MODULE_V1',\n}\n\n/**\n * Directory/file inventory of the compiled payload, mirrored 1:1 by the\n * generator-local `FrameworkKnowledgeManifestShape` in\n * `wildo-cli/src/services/framework/framework-knowledge-generation.service.ts`.\n * The two shapes are deliberately duplicated (the audit/generator must stay\n * buildless w.r.t. this package) — extending one WITHOUT the other silently\n * ships a payload the typed loader cannot see. Keep them in lockstep.\n */\nexport interface FrameworkKnowledgePayloadInventory {\n topicIndexPath: string;\n registriesDirectory: string;\n referencesDirectory: string;\n skillsDirectory: string;\n /** Compiled meta-workflow playbooks home (`playbooks/<ref>/playbook.json` + `method.md`). */\n playbooksDirectory: string;\n /** Compiled application-creation transition route home. */\n /** Compiled, portable assurance-authority bases; published bytes never contain repository source paths. */\n assuranceAuthorityBasesDirectory: string;\n /**\n * Compiled ALWAYS-ON rules home (`rules/*.md`), installed into an application's `.claude/rules/`.\n *\n * Distinct from a skill: a skill is reached when the router matches a request description, which\n * requires the agent to already suspect the topic. A rule is policy that must be present when the\n * agent opens a matching file, without being asked for.\n *\n * OPTIONAL, unlike its siblings: it was introduced by issue #98 after the channel had been\n * documented and never built, so a payload generated before that carries none. A required field\n * would make every previously generated payload unloadable to fix a delivery gap.\n */\n rulesDirectory?: string;\n /**\n * Compiled skills router (`skills/INDEX.md`), rendered from the authored\n * `src/skills/INDEX.md` — the single router truth. Absent when the authored\n * catalog file does not exist (audit Rule 8 warns on that state). It is\n * deliberately NOT attached to any topic entry: the catalog is cross-topic\n * and `getFrameworkKnowledgeTopic` would misfile it.\n */\n skillsIndexPath?: string;\n}\n\nexport interface FrameworkKnowledgeRegistryDescriptor {\n registryName: FrameworkKnowledgeRegistryName;\n filePath: string;\n description: string;\n entryCount: number;\n}\n\nexport interface FrameworkKnowledgeManifest {\n artifactVersion: string;\n frameworkVersion: string;\n generatorVersion: string;\n generatedAt: string;\n packageName: string;\n topicCount: number;\n referenceFileCount: number;\n payload: FrameworkKnowledgePayloadInventory;\n registries: FrameworkKnowledgeRegistryDescriptor[];\n}\n\nexport interface FrameworkKnowledgeSourceReference {\n kind: FrameworkKnowledgeSourceReferenceKind;\n tagName: string;\n filePath: string;\n startLine?: number;\n endLine?: number;\n}\n\nexport interface FrameworkKnowledgeTopicIndexEntry {\n topicId: string;\n title: string;\n tags: string[];\n facets: string[];\n categories: string[];\n sourceReferences: FrameworkKnowledgeSourceReference[];\n referenceFiles: string[];\n skillFiles: string[];\n registryKeys: FrameworkKnowledgeRegistryName[];\n}\n\nexport interface FrameworkKnowledgeTopicIndex {\n topics: FrameworkKnowledgeTopicIndexEntry[];\n}\n\nexport interface FrameworkKnowledgeTopic {\n entry: FrameworkKnowledgeTopicIndexEntry;\n referencesByFile: Record<string, string>;\n skillsByFile: Record<string, string>;\n}\n\nexport interface FrameworkKnowledgeTopicRegistryEntry {\n topicId: string;\n title: string;\n categories: string[];\n referenceFilePath?: string;\n sourceReferenceCount: number;\n}\n\nexport interface FrameworkKnowledgeSourceTagRegistryEntry {\n referenceFilePath: string;\n skillFilePath?: string;\n extractedAt: string;\n facets: string[];\n sourceReferences: FrameworkKnowledgeSourceReference[];\n}\n\n/**\n * One compiled meta-workflow playbook, as listed in the `playbooks` registry.\n *\n * Enum-backed playbook fields (`phase`, `executor`, `functionalTopics`) are\n * surfaced as plain strings here: this package has zero dependencies by\n * design, so it cannot import the `MetaWorkflow_*` enums from\n * `@wildo-ai/saas-specifications`. Consumers that need the typed contract must parse\n * the playbook JSON (see {@link FrameworkKnowledgePlaybook.playbook}) with\n * `MetaWorkflowPlaybookSchema` at their own seam — the generator has already\n * validated it, so the parse is a type-recovery step, not a trust boundary.\n */\nexport interface FrameworkKnowledgePlaybookRegistryEntry {\n ref: string;\n version: string;\n phase: string;\n /** Absent when the playbook runs no single tier — see `MetaWorkflow_Executor` (#115). */\n executor?: string;\n intent: string;\n functionalTopics: string[];\n /** App-knowledge skill ids the playbook's method delegates the technical HOW to. */\n skillRefs: string[];\n /** Payload-relative path of the compiled `playbook.json`. */\n playbookFilePath: string;\n /** Payload-relative path of the rendered `method.md`. */\n methodFilePath: string;\n /** Canonical structured authoring format used to compile this entry. */\n sourceFormat: FrameworkKnowledgePlaybookSourceFormat;\n evaluationProtocol?: {\n protocolRef: string;\n protocolVersion: number;\n filePath: string;\n };\n evaluationTreatment?: {\n definitionRef: string;\n definitionVersion: number;\n filePath: string;\n };\n structuredArtifactAction?: {\n definitionRef: string;\n definitionVersion: number;\n filePath: string;\n };\n}\n\n/**\n * Zero-dependency registry identity for one compiled assurance-authority basis.\n *\n * `ref@version` IS the identity: `version` is the declared compatibility generation. The three\n * content digests this carried (basis, source revision, artifact bytes) were removed 2026-08-27 —\n * they compared the compiled payload against a registry that ships in the same payload, and the\n * basis digest additionally forced every consuming application to re-accept its controls on any\n * engine byte movement (`.claude/rules/one-source-of-truth.md`).\n */\nexport interface FrameworkKnowledgeAssuranceAuthorityBasisRegistryEntry {\n ref: string;\n version: number;\n sourceRevisionRef: string;\n filePath: string;\n /**\n * The rights-classified WILDO-objective → external-source mapping DERIVED from this basis (#266).\n *\n * Beside the basis rather than in its own channel because it is a projection of exactly these\n * bytes: derived in the same pass, from the same value, so it cannot describe a different basis\n * than the one it ships with. A separate channel would be free to disagree, and a mapping is read\n * precisely by people who cannot check it.\n *\n * OPTIONAL for the same reason `rulesDirectory` is: a payload generated before this existed carries\n * none, and a required field would make every one of them unloadable to fix a delivery gap.\n */\n externalFrameworkMappingFilePath?: string;\n}\n\n/** Portable authority-basis bytes; consumers recover the typed assurance contract at their semantic boundary. */\nexport interface FrameworkKnowledgeAssuranceAuthorityBasis {\n entry: FrameworkKnowledgeAssuranceAuthorityBasisRegistryEntry;\n basis: unknown;\n bytes: Uint8Array;\n}\n\n/** Exact JSON artifact bytes plus their parsed zero-dependency projection. */\nexport interface FrameworkKnowledgeJsonArtifact<TValue> {\n value: TValue;\n bytes: Uint8Array;\n}\n\n/**\n * Hydrated playbook returned by `getFrameworkKnowledgePlaybook(ref)`.\n */\nexport interface FrameworkKnowledgePlaybook {\n entry: FrameworkKnowledgePlaybookRegistryEntry;\n /**\n * Parsed compiled `playbook.json` — schema-valid `MetaWorkflowPlaybook`\n * content (with `method.guidance` inlined from the rendered `method.md`).\n * Typed `unknown` because this package cannot depend on\n * `@wildo-ai/saas-specifications`; parse with `MetaWorkflowPlaybookSchema` to\n * recover the typed contract.\n */\n playbook: unknown;\n /** Exact compiled `playbook.json` bytes used for source provenance. */\n playbookBytes: Uint8Array;\n /** Rendered `method.md` prose (same content as `playbook.method.guidance`). */\n methodMarkdown: string;\n /** Exact rendered `method.md` bytes used for source provenance. */\n methodBytes: Uint8Array;\n /** Exact compiled protocol bytes and parsed value, absent for contained JSON-v1 entries. */\n evaluationProtocol: {\n value: unknown;\n bytes: Uint8Array;\n } | null;\n /** Exact compiled treatment bytes and parsed value, absent for contained JSON-v1 entries. */\n evaluationTreatment: {\n value: unknown;\n bytes: Uint8Array;\n } | null;\n /** Exact compiled structured-artifact Action bytes, when the playbook declares one. */\n structuredArtifactAction: {\n value: unknown;\n bytes: Uint8Array;\n } | null;\n}\n\nexport interface FrameworkKnowledgeRegistryBase<TName extends FrameworkKnowledgeRegistryName, TEntry> {\n name: TName;\n metadata?: Record<string, unknown>;\n entries: Record<string, TEntry>;\n}\n\nexport type FrameworkKnowledgeSourceTagRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.SOURCE_TAGS,\n FrameworkKnowledgeSourceTagRegistryEntry\n>;\n\nexport type FrameworkKnowledgeTopicRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.FRAMEWORK_TOPICS,\n FrameworkKnowledgeTopicRegistryEntry\n>;\n\nexport type FrameworkKnowledgePlaybookRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.PLAYBOOKS,\n FrameworkKnowledgePlaybookRegistryEntry\n>;\n\nexport type FrameworkKnowledgeAssuranceAuthorityBasisRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.ASSURANCE_AUTHORITY_BASES,\n FrameworkKnowledgeAssuranceAuthorityBasisRegistryEntry\n>;\n\nexport interface FrameworkKnowledgeRegistryMap {\n [FrameworkKnowledgeRegistryName.SOURCE_TAGS]: FrameworkKnowledgeSourceTagRegistry;\n [FrameworkKnowledgeRegistryName.FRAMEWORK_TOPICS]: FrameworkKnowledgeTopicRegistry;\n [FrameworkKnowledgeRegistryName.PLAYBOOKS]: FrameworkKnowledgePlaybookRegistry;\n [FrameworkKnowledgeRegistryName.ASSURANCE_AUTHORITY_BASES]: FrameworkKnowledgeAssuranceAuthorityBasisRegistry;\n}\n\nexport type FrameworkKnowledgeRegistry = FrameworkKnowledgeRegistryMap[FrameworkKnowledgeRegistryName];\n"]}
1
+ {"version":3,"file":"framework-knowledge.schemas.js","sourceRoot":"","sources":["../../src/framework-knowledge.schemas.ts"],"names":[],"mappings":"AAAA,MAAM,CAAC,MAAM,oCAAoC,GAAG,GAAG,CAAC;AAExD,MAAM,CAAN,IAAY,8BAKX;AALD,WAAY,8BAA8B;IACxC,6DAA2B,CAAA;IAC3B,uEAAqC,CAAA;IACrC,yDAAuB,CAAA;IACvB,yFAAuD,CAAA;AACzD,CAAC,EALW,8BAA8B,KAA9B,8BAA8B,QAKzC;AAED,MAAM,CAAN,IAAY,qCAGX;AAHD,WAAY,qCAAqC;IAC/C,gEAAuB,CAAA;IACvB,kEAAyB,CAAA;AAC3B,CAAC,EAHW,qCAAqC,KAArC,qCAAqC,QAGhD;AAED;;;;GAIG;AACH,MAAM,CAAN,IAAY,sCAEX;AAFD,WAAY,sCAAsC;IAChD,+GAAqE,CAAA;AACvE,CAAC,EAFW,sCAAsC,KAAtC,sCAAsC,QAEjD","sourcesContent":["export const FRAMEWORK_KNOWLEDGE_ARTIFACT_VERSION = '3';\n\nexport enum FrameworkKnowledgeRegistryName {\n SOURCE_TAGS = 'source-tags',\n FRAMEWORK_TOPICS = 'framework-topics',\n PLAYBOOKS = 'playbooks',\n ASSURANCE_AUTHORITY_BASES = 'assurance-authority-bases',\n}\n\nexport enum FrameworkKnowledgeSourceReferenceKind {\n FULL_FILE = 'full-file',\n PART_RANGE = 'part-range',\n}\n\n/**\n * The JSON-v1 authoring format was retired (and its member deleted) at the\n * first-activation hard cut; every authored playbook is an effect-free native\n * TypeScript declaration.\n */\nexport enum FrameworkKnowledgePlaybookSourceFormat {\n EFFECT_FREE_TYPESCRIPT_MODULE_V1 = 'EFFECT_FREE_TYPESCRIPT_MODULE_V1',\n}\n\n/**\n * Directory/file inventory of the compiled payload, mirrored 1:1 by the\n * generator-local `FrameworkKnowledgeManifestShape` in\n * `wildo-cli/src/services/framework/framework-knowledge-generation.service.ts`.\n * The two shapes are deliberately duplicated (the audit/generator must stay\n * buildless w.r.t. this package) — extending one WITHOUT the other silently\n * ships a payload the typed loader cannot see. Keep them in lockstep.\n */\nexport interface FrameworkKnowledgePayloadInventory {\n topicIndexPath: string;\n registriesDirectory: string;\n referencesDirectory: string;\n skillsDirectory: string;\n /** Compiled meta-workflow playbooks home (`playbooks/<ref>/playbook.json` + `method.md`). */\n playbooksDirectory: string;\n /** Compiled application-creation transition route home. */\n /** Compiled, portable assurance-authority bases; published bytes never contain repository source paths. */\n assuranceAuthorityBasesDirectory: string;\n /**\n * Compiled ALWAYS-ON rules home (`rules/*.md`), installed into an application's `.claude/rules/`.\n *\n * Distinct from a skill: a skill is reached when the router matches a request description, which\n * requires the agent to already suspect the topic. A rule is policy that must be present when the\n * agent opens a matching file, without being asked for.\n *\n * OPTIONAL, unlike its siblings: it was introduced by issue #98 after the channel had been\n * documented and never built, so a payload generated before that carries none. A required field\n * would make every previously generated payload unloadable to fix a delivery gap.\n */\n rulesDirectory?: string;\n /**\n * Compiled skills router (`skills/INDEX.md`), rendered from the authored\n * `src/skills/INDEX.md` — the single router truth. Absent when the authored\n * catalog file does not exist (audit Rule 8 warns on that state). It is\n * deliberately NOT attached to any topic entry: the catalog is cross-topic\n * and `getFrameworkKnowledgeTopic` would misfile it.\n */\n skillsIndexPath?: string;\n}\n\nexport interface FrameworkKnowledgeRegistryDescriptor {\n registryName: FrameworkKnowledgeRegistryName;\n filePath: string;\n description: string;\n entryCount: number;\n}\n\nexport interface FrameworkKnowledgeManifest {\n artifactVersion: string;\n frameworkVersion: string;\n generatorVersion: string;\n generatedAt: string;\n packageName: string;\n topicCount: number;\n referenceFileCount: number;\n payload: FrameworkKnowledgePayloadInventory;\n registries: FrameworkKnowledgeRegistryDescriptor[];\n}\n\nexport interface FrameworkKnowledgeSourceReference {\n kind: FrameworkKnowledgeSourceReferenceKind;\n tagName: string;\n filePath: string;\n startLine?: number;\n endLine?: number;\n}\n\nexport interface FrameworkKnowledgeTopicIndexEntry {\n topicId: string;\n title: string;\n tags: string[];\n facets: string[];\n categories: string[];\n sourceReferences: FrameworkKnowledgeSourceReference[];\n referenceFiles: string[];\n skillFiles: string[];\n registryKeys: FrameworkKnowledgeRegistryName[];\n}\n\nexport interface FrameworkKnowledgeTopicIndex {\n topics: FrameworkKnowledgeTopicIndexEntry[];\n}\n\nexport interface FrameworkKnowledgeTopic {\n entry: FrameworkKnowledgeTopicIndexEntry;\n referencesByFile: Record<string, string>;\n skillsByFile: Record<string, string>;\n}\n\nexport interface FrameworkKnowledgeTopicRegistryEntry {\n topicId: string;\n title: string;\n categories: string[];\n referenceFilePath?: string;\n sourceReferenceCount: number;\n}\n\nexport interface FrameworkKnowledgeSourceTagRegistryEntry {\n referenceFilePath: string;\n skillFilePath?: string;\n extractedAt: string;\n facets: string[];\n sourceReferences: FrameworkKnowledgeSourceReference[];\n}\n\n/**\n * One compiled meta-workflow playbook, as listed in the `playbooks` registry.\n *\n * Enum-backed playbook fields (`phase`, `executor`) are\n * surfaced as plain strings here: this package has zero dependencies by\n * design, so it cannot import the `MetaWorkflow_*` enums from\n * `@wildo-ai/saas-specifications`. Consumers that need the typed contract must parse\n * the playbook JSON (see {@link FrameworkKnowledgePlaybook.playbook}) with\n * `MetaWorkflowPlaybookSchema` at their own seam — the generator has already\n * validated it, so the parse is a type-recovery step, not a trust boundary.\n */\nexport interface FrameworkKnowledgePlaybookRegistryEntry {\n ref: string;\n version: string;\n phase: string;\n /** Absent when the playbook runs no single tier — see `MetaWorkflow_Executor` (#115). */\n executor?: string;\n intent: string;\n /** App-knowledge skill ids the playbook's method delegates the technical HOW to. */\n skillRefs: string[];\n /** Payload-relative path of the compiled `playbook.json`. */\n playbookFilePath: string;\n /** Payload-relative path of the rendered `method.md`. */\n methodFilePath: string;\n /** Canonical structured authoring format used to compile this entry. */\n sourceFormat: FrameworkKnowledgePlaybookSourceFormat;\n evaluationProtocol?: {\n protocolRef: string;\n protocolVersion: number;\n filePath: string;\n };\n evaluationTreatment?: {\n definitionRef: string;\n definitionVersion: number;\n filePath: string;\n };\n structuredArtifactAction?: {\n definitionRef: string;\n definitionVersion: number;\n filePath: string;\n };\n}\n\n/**\n * Zero-dependency registry identity for one compiled assurance-authority basis.\n *\n * `ref@version` IS the identity: `version` is the declared compatibility generation. The three\n * content digests this carried (basis, source revision, artifact bytes) were removed 2026-08-27 —\n * they compared the compiled payload against a registry that ships in the same payload, and the\n * basis digest additionally forced every consuming application to re-accept its controls on any\n * engine byte movement (`.claude/rules/one-source-of-truth.md`).\n */\nexport interface FrameworkKnowledgeAssuranceAuthorityBasisRegistryEntry {\n ref: string;\n version: number;\n sourceRevisionRef: string;\n filePath: string;\n /**\n * The rights-classified WILDO-objective → external-source mapping DERIVED from this basis (#266).\n *\n * Beside the basis rather than in its own channel because it is a projection of exactly these\n * bytes: derived in the same pass, from the same value, so it cannot describe a different basis\n * than the one it ships with. A separate channel would be free to disagree, and a mapping is read\n * precisely by people who cannot check it.\n *\n * OPTIONAL for the same reason `rulesDirectory` is: a payload generated before this existed carries\n * none, and a required field would make every one of them unloadable to fix a delivery gap.\n */\n externalFrameworkMappingFilePath?: string;\n}\n\n/** Portable authority-basis bytes; consumers recover the typed assurance contract at their semantic boundary. */\nexport interface FrameworkKnowledgeAssuranceAuthorityBasis {\n entry: FrameworkKnowledgeAssuranceAuthorityBasisRegistryEntry;\n basis: unknown;\n bytes: Uint8Array;\n}\n\n/** Exact JSON artifact bytes plus their parsed zero-dependency projection. */\nexport interface FrameworkKnowledgeJsonArtifact<TValue> {\n value: TValue;\n bytes: Uint8Array;\n}\n\n/**\n * Hydrated playbook returned by `getFrameworkKnowledgePlaybook(ref)`.\n */\nexport interface FrameworkKnowledgePlaybook {\n entry: FrameworkKnowledgePlaybookRegistryEntry;\n /**\n * Parsed compiled `playbook.json` — schema-valid `MetaWorkflowPlaybook`\n * content (with `method.guidance` inlined from the rendered `method.md`).\n * Typed `unknown` because this package cannot depend on\n * `@wildo-ai/saas-specifications`; parse with `MetaWorkflowPlaybookSchema` to\n * recover the typed contract.\n */\n playbook: unknown;\n /** Exact compiled `playbook.json` bytes used for source provenance. */\n playbookBytes: Uint8Array;\n /** Rendered `method.md` prose (same content as `playbook.method.guidance`). */\n methodMarkdown: string;\n /** Exact rendered `method.md` bytes used for source provenance. */\n methodBytes: Uint8Array;\n /** Exact compiled protocol bytes and parsed value, absent for contained JSON-v1 entries. */\n evaluationProtocol: {\n value: unknown;\n bytes: Uint8Array;\n } | null;\n /** Exact compiled treatment bytes and parsed value, absent for contained JSON-v1 entries. */\n evaluationTreatment: {\n value: unknown;\n bytes: Uint8Array;\n } | null;\n /** Exact compiled structured-artifact Action bytes, when the playbook declares one. */\n structuredArtifactAction: {\n value: unknown;\n bytes: Uint8Array;\n } | null;\n}\n\nexport interface FrameworkKnowledgeRegistryBase<TName extends FrameworkKnowledgeRegistryName, TEntry> {\n name: TName;\n metadata?: Record<string, unknown>;\n entries: Record<string, TEntry>;\n}\n\nexport type FrameworkKnowledgeSourceTagRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.SOURCE_TAGS,\n FrameworkKnowledgeSourceTagRegistryEntry\n>;\n\nexport type FrameworkKnowledgeTopicRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.FRAMEWORK_TOPICS,\n FrameworkKnowledgeTopicRegistryEntry\n>;\n\nexport type FrameworkKnowledgePlaybookRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.PLAYBOOKS,\n FrameworkKnowledgePlaybookRegistryEntry\n>;\n\nexport type FrameworkKnowledgeAssuranceAuthorityBasisRegistry = FrameworkKnowledgeRegistryBase<\n FrameworkKnowledgeRegistryName.ASSURANCE_AUTHORITY_BASES,\n FrameworkKnowledgeAssuranceAuthorityBasisRegistryEntry\n>;\n\nexport interface FrameworkKnowledgeRegistryMap {\n [FrameworkKnowledgeRegistryName.SOURCE_TAGS]: FrameworkKnowledgeSourceTagRegistry;\n [FrameworkKnowledgeRegistryName.FRAMEWORK_TOPICS]: FrameworkKnowledgeTopicRegistry;\n [FrameworkKnowledgeRegistryName.PLAYBOOKS]: FrameworkKnowledgePlaybookRegistry;\n [FrameworkKnowledgeRegistryName.ASSURANCE_AUTHORITY_BASES]: FrameworkKnowledgeAssuranceAuthorityBasisRegistry;\n}\n\nexport type FrameworkKnowledgeRegistry = FrameworkKnowledgeRegistryMap[FrameworkKnowledgeRegistryName];\n"]}
@@ -1 +1 @@
1
- {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,kCAAkC,CAAC;AACjD,cAAc,sCAAsC,CAAC;AACrD,cAAc,iCAAiC,CAAC"}
1
+ {"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../../src/index.ts"],"names":[],"mappings":"AAAA,cAAc,kCAAkC,CAAC;AACjD,cAAc,sCAAsC,CAAC;AACrD,cAAc,iCAAiC,CAAC"}
@@ -18,10 +18,9 @@
18
18
  */
19
19
  export declare const playbookDefinition: {
20
20
  readonly ref: "bottom_up.assemble-verify";
21
- readonly version: "0.2.0";
21
+ readonly version: "0.3.0";
22
22
  readonly phase: "bottom_up";
23
- readonly intent: "Bottom-up assemble & verify — the FINAL bottom-up step and the capstone of the build: the pivot from having BUILT the application (the decompose / dispatch / scale loop authored its modules, resources, config and integrations) to answering ONE mechanical question — does the built application ASSEMBLE? It runs the deterministic verification set over the application's four workspace packages (specifications, shared-lib, backend-api, frontend) OUTSIDE any coding agent, and reports a per-check outcome. It fixes NOTHING: a failure is surfaced for a refinement re-dispatch, which is a different playbook's job, and it authors no schemas and writes no code. Deliberately DISTINCT from the refinement phase's coverage audit, which also binds topic 7 but asks a SEMANTIC question (does the built app match the intent — specs diffed against introspected reality). This playbook never diffs intent against reality; if you are judging coverage you are in the refinement lane. Scope honesty for v0.2: the check set is the whole-application TYPECHECK across the four packages — the question 'does it compile as one program', which no per-task check can answer because the dispatch lane typechecks only the package a task mutated. A boot probe, the whole test suite, `wildo config validate` and OpenAPI/docs regeneration are NOT in this set: each needs a running stack or a companion affordance that does not exist, and declaring them here without running them is exactly what made the deleted version of this playbook inert.";
24
- readonly functionalTopics: readonly ["assemble_verify_and_iterate"];
23
+ readonly intent: "Bottom-up assemble & verify — the FINAL bottom-up step and the capstone of the build: the pivot from having BUILT the application (the decompose / dispatch / scale loop authored its modules, resources, config and integrations) to answering ONE mechanical question — does the built application ASSEMBLE? It runs the deterministic verification set over the application's four workspace packages (specifications, shared-lib, backend-api, frontend) OUTSIDE any coding agent, and reports a per-check outcome. It fixes NOTHING: a failure is surfaced for a refinement re-dispatch, which is a different playbook's job, and it authors no schemas and writes no code. Deliberately DISTINCT from the refinement phase's coverage audit, which also binds topic 7 but asks a SEMANTIC question (does the built app match the intent — specs diffed against introspected reality). This playbook never diffs intent against reality; if you are judging coverage you are in the refinement lane. Scope honesty for v0.3: the check set is the whole-application TYPECHECK across the four packages — the question 'does it compile as one program', which no per-task check can answer because the dispatch lane typechecks only the package a task mutated — PLUS the schema-plan drift gate (`check:schema-plan-in-sync`), which asks whether the modelled resources have migrations behind them. The second is not a variant of the first: on a PostgreSQL-backed application a table exists only because a migration built it, so a resource whose migration was never generated compiles green in all four packages and then refuses to boot on `postgresql_table_schema_mismatch` — invisible to a typecheck, because no type in the program knows whether a table exists. It is safe on MongoDB applications and on unbuilt trees because it resolves three outcomes (not adopted / could-not-ask / decided) rather than reading an exit code. A boot probe, the whole test suite, `wildo config validate` and OpenAPI/docs regeneration are NOT in this set: each needs a running stack or a companion affordance that does not exist, and declaring them here without running them is exactly what made the deleted version of this playbook inert.";
25
24
  readonly preconditions: readonly [{
26
25
  readonly kind: "artifact_exists";
27
26
  readonly selector: {
@@ -33,7 +32,7 @@ export declare const playbookDefinition: {
33
32
  }];
34
33
  readonly outputs: readonly [];
35
34
  readonly method: {
36
- readonly skillRefs: readonly ["journey-status", "journey-report", "journey-approve"];
35
+ readonly skillRefs: readonly ["journey-status", "journey-report", "journey-approve", "application-database-migrations"];
37
36
  };
38
37
  readonly executor: "deterministic_cli";
39
38
  readonly approval: "approve_result";
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.assemble-verify/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;;CAoCrB,CAAC"}
1
+ {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.assemble-verify/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;CAoCrB,CAAC"}
@@ -18,10 +18,9 @@
18
18
  */
19
19
  export const playbookDefinition = {
20
20
  "ref": "bottom_up.assemble-verify",
21
- "version": "0.2.0",
21
+ "version": "0.3.0",
22
22
  "phase": "bottom_up",
23
- "intent": "Bottom-up assemble & verify — the FINAL bottom-up step and the capstone of the build: the pivot from having BUILT the application (the decompose / dispatch / scale loop authored its modules, resources, config and integrations) to answering ONE mechanical question — does the built application ASSEMBLE? It runs the deterministic verification set over the application's four workspace packages (specifications, shared-lib, backend-api, frontend) OUTSIDE any coding agent, and reports a per-check outcome. It fixes NOTHING: a failure is surfaced for a refinement re-dispatch, which is a different playbook's job, and it authors no schemas and writes no code. Deliberately DISTINCT from the refinement phase's coverage audit, which also binds topic 7 but asks a SEMANTIC question (does the built app match the intent — specs diffed against introspected reality). This playbook never diffs intent against reality; if you are judging coverage you are in the refinement lane. Scope honesty for v0.2: the check set is the whole-application TYPECHECK across the four packages — the question 'does it compile as one program', which no per-task check can answer because the dispatch lane typechecks only the package a task mutated. A boot probe, the whole test suite, `wildo config validate` and OpenAPI/docs regeneration are NOT in this set: each needs a running stack or a companion affordance that does not exist, and declaring them here without running them is exactly what made the deleted version of this playbook inert.",
24
- "functionalTopics": ["assemble_verify_and_iterate"],
23
+ "intent": "Bottom-up assemble & verify — the FINAL bottom-up step and the capstone of the build: the pivot from having BUILT the application (the decompose / dispatch / scale loop authored its modules, resources, config and integrations) to answering ONE mechanical question — does the built application ASSEMBLE? It runs the deterministic verification set over the application's four workspace packages (specifications, shared-lib, backend-api, frontend) OUTSIDE any coding agent, and reports a per-check outcome. It fixes NOTHING: a failure is surfaced for a refinement re-dispatch, which is a different playbook's job, and it authors no schemas and writes no code. Deliberately DISTINCT from the refinement phase's coverage audit, which also binds topic 7 but asks a SEMANTIC question (does the built app match the intent — specs diffed against introspected reality). This playbook never diffs intent against reality; if you are judging coverage you are in the refinement lane. Scope honesty for v0.3: the check set is the whole-application TYPECHECK across the four packages — the question 'does it compile as one program', which no per-task check can answer because the dispatch lane typechecks only the package a task mutated — PLUS the schema-plan drift gate (`check:schema-plan-in-sync`), which asks whether the modelled resources have migrations behind them. The second is not a variant of the first: on a PostgreSQL-backed application a table exists only because a migration built it, so a resource whose migration was never generated compiles green in all four packages and then refuses to boot on `postgresql_table_schema_mismatch` — invisible to a typecheck, because no type in the program knows whether a table exists. It is safe on MongoDB applications and on unbuilt trees because it resolves three outcomes (not adopted / could-not-ask / decided) rather than reading an exit code. A boot probe, the whole test suite, `wildo config validate` and OpenAPI/docs regeneration are NOT in this set: each needs a running stack or a companion affordance that does not exist, and declaring them here without running them is exactly what made the deleted version of this playbook inert.",
25
24
  "preconditions": [
26
25
  { "kind": "artifact_exists", "selector": { "family": "build-plan" } }
27
26
  ],
@@ -33,7 +32,8 @@ export const playbookDefinition = {
33
32
  "skillRefs": [
34
33
  "journey-status",
35
34
  "journey-report",
36
- "journey-approve"
35
+ "journey-approve",
36
+ "application-database-migrations"
37
37
  ]
38
38
  },
39
39
  "executor": "deterministic_cli",
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.assemble-verify/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,2BAA2B;IAClC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,8+CAA8+C;IACx/C,kBAAkB,EAAE,CAAC,6BAA6B,CAAC;IACnD,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;YACX,gBAAgB;YAChB,gBAAgB;YAChB,iBAAiB;SAClB;KACF;IACD,UAAU,EAAE,mBAAmB;IAC/B,UAAU,EAAE,gBAAgB;IAC5B;;;;;;;OAOG;IACH,QAAQ,EAAE;QACR,SAAS,EAAE,EAAE;QACb,eAAe,EAAE,OAAO;KACzB;IACD,WAAW,EAAE,eAAe;CACpB,CAAC","sourcesContent":["/**\n * Canonical native declaration for topic 7 — the app-wide assemble/verify step.\n *\n * REBUILT rather than restored (issue #147). A playbook of this ref existed from\n * 2026-07-10 and was deleted on 2026-08-25 with the app-creation digest\n * demolition; the question it asked went with it, even though answering \"does\n * the built application assemble?\" needs no digests. Restoring it verbatim was\n * rejected: it declared the retired `COMPOSITE` executor, depended on two\n * families the demolition removed (`foundation-manifest`, `build-verification`),\n * and its method was explicit that NONE of its checks were actually run by the\n * runner — `// TODO CLI COMMAND:` placeholders and \"companion affordances that\n * do not exist yet\".\n *\n * What is different now is that the checks RUN. `DETERMINISTIC_CLI` is honoured\n * by the runtime as of #147, and the check refs below resolve through the same\n * closed `APPLICATION_CODING_TASK_VERIFICATION_CATALOG` a coding task uses, so\n * an unknown ref is refused rather than silently skipped.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.assemble-verify\",\n \"version\": \"0.2.0\",\n \"phase\": \"bottom_up\",\n \"intent\": \"Bottom-up assemble & verify — the FINAL bottom-up step and the capstone of the build: the pivot from having BUILT the application (the decompose / dispatch / scale loop authored its modules, resources, config and integrations) to answering ONE mechanical question — does the built application ASSEMBLE? It runs the deterministic verification set over the application's four workspace packages (specifications, shared-lib, backend-api, frontend) OUTSIDE any coding agent, and reports a per-check outcome. It fixes NOTHING: a failure is surfaced for a refinement re-dispatch, which is a different playbook's job, and it authors no schemas and writes no code. Deliberately DISTINCT from the refinement phase's coverage audit, which also binds topic 7 but asks a SEMANTIC question (does the built app match the intent — specs diffed against introspected reality). This playbook never diffs intent against reality; if you are judging coverage you are in the refinement lane. Scope honesty for v0.2: the check set is the whole-application TYPECHECK across the four packages — the question 'does it compile as one program', which no per-task check can answer because the dispatch lane typechecks only the package a task mutated. A boot probe, the whole test suite, `wildo config validate` and OpenAPI/docs regeneration are NOT in this set: each needs a running stack or a companion affordance that does not exist, and declaring them here without running them is exactly what made the deleted version of this playbook inert.\",\n \"functionalTopics\": [\"assemble_verify_and_iterate\"],\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 \"journey-status\",\n \"journey-report\",\n \"journey-approve\"\n ]\n },\n \"executor\": \"deterministic_cli\",\n \"approval\": \"approve_result\",\n /*\n * Token and model-call ceilings are OMITTED, not zeroed.\n *\n * Every field here is optional, and this tier makes no model calls at all — it runs typechecks in\n * a subprocess. Declaring `maxModelCalls: 0` is rejected by the schema (positive only), and\n * declaring `1` to satisfy it would state a ceiling nobody chose for a resource that is never\n * consumed. What IS bounded is wall-clock and how many times the step may run.\n */\n \"budget\": {\n \"maxRuns\": 40,\n \"maxDurationMs\": 3600000\n },\n \"onFailure\": \"keep_and_flag\",\n} as const;\n"]}
1
+ {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.assemble-verify/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;;;;;;;;;;GAiBG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,2BAA2B;IAClC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,uoEAAuoE;IACjpE,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;YACX,gBAAgB;YAChB,gBAAgB;YAChB,iBAAiB;YACjB,iCAAiC;SAClC;KACF;IACD,UAAU,EAAE,mBAAmB;IAC/B,UAAU,EAAE,gBAAgB;IAC5B;;;;;;;OAOG;IACH,QAAQ,EAAE;QACR,SAAS,EAAE,EAAE;QACb,eAAe,EAAE,OAAO;KACzB;IACD,WAAW,EAAE,eAAe;CACpB,CAAC","sourcesContent":["/**\n * Canonical native declaration for topic 7 — the app-wide assemble/verify step.\n *\n * REBUILT rather than restored (issue #147). A playbook of this ref existed from\n * 2026-07-10 and was deleted on 2026-08-25 with the app-creation digest\n * demolition; the question it asked went with it, even though answering \"does\n * the built application assemble?\" needs no digests. Restoring it verbatim was\n * rejected: it declared the retired `COMPOSITE` executor, depended on two\n * families the demolition removed (`foundation-manifest`, `build-verification`),\n * and its method was explicit that NONE of its checks were actually run by the\n * runner — `// TODO CLI COMMAND:` placeholders and \"companion affordances that\n * do not exist yet\".\n *\n * What is different now is that the checks RUN. `DETERMINISTIC_CLI` is honoured\n * by the runtime as of #147, and the check refs below resolve through the same\n * closed `APPLICATION_CODING_TASK_VERIFICATION_CATALOG` a coding task uses, so\n * an unknown ref is refused rather than silently skipped.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.assemble-verify\",\n \"version\": \"0.3.0\",\n \"phase\": \"bottom_up\",\n \"intent\": \"Bottom-up assemble & verify — the FINAL bottom-up step and the capstone of the build: the pivot from having BUILT the application (the decompose / dispatch / scale loop authored its modules, resources, config and integrations) to answering ONE mechanical question — does the built application ASSEMBLE? It runs the deterministic verification set over the application's four workspace packages (specifications, shared-lib, backend-api, frontend) OUTSIDE any coding agent, and reports a per-check outcome. It fixes NOTHING: a failure is surfaced for a refinement re-dispatch, which is a different playbook's job, and it authors no schemas and writes no code. Deliberately DISTINCT from the refinement phase's coverage audit, which also binds topic 7 but asks a SEMANTIC question (does the built app match the intent — specs diffed against introspected reality). This playbook never diffs intent against reality; if you are judging coverage you are in the refinement lane. Scope honesty for v0.3: the check set is the whole-application TYPECHECK across the four packages — the question 'does it compile as one program', which no per-task check can answer because the dispatch lane typechecks only the package a task mutated — PLUS the schema-plan drift gate (`check:schema-plan-in-sync`), which asks whether the modelled resources have migrations behind them. The second is not a variant of the first: on a PostgreSQL-backed application a table exists only because a migration built it, so a resource whose migration was never generated compiles green in all four packages and then refuses to boot on `postgresql_table_schema_mismatch` — invisible to a typecheck, because no type in the program knows whether a table exists. It is safe on MongoDB applications and on unbuilt trees because it resolves three outcomes (not adopted / could-not-ask / decided) rather than reading an exit code. A boot probe, the whole test suite, `wildo config validate` and OpenAPI/docs regeneration are NOT in this set: each needs a running stack or a companion affordance that does not exist, and declaring them here without running them is exactly what made the deleted version of this playbook inert.\",\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 \"journey-status\",\n \"journey-report\",\n \"journey-approve\",\n \"application-database-migrations\"\n ]\n },\n \"executor\": \"deterministic_cli\",\n \"approval\": \"approve_result\",\n /*\n * Token and model-call ceilings are OMITTED, not zeroed.\n *\n * Every field here is optional, and this tier makes no model calls at all — it runs typechecks in\n * a subprocess. Declaring `maxModelCalls: 0` is rejected by the schema (positive only), and\n * declaring `1` to satisfy it would state a ceiling nobody chose for a resource that is never\n * consumed. What IS bounded is wall-clock and how many times the step may run.\n */\n \"budget\": {\n \"maxRuns\": 40,\n \"maxDurationMs\": 3600000\n },\n \"onFailure\": \"keep_and_flag\",\n} as const;\n"]}
@@ -9,10 +9,9 @@
9
9
  */
10
10
  export declare const playbookDefinition: {
11
11
  readonly ref: "bottom_up.build-decompose";
12
- readonly version: "0.2.0";
12
+ readonly version: "0.2.1";
13
13
  readonly phase: "bottom_up";
14
14
  readonly 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 (labels / i18n, email templates, seeds) 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. v1 scaffold methodology — a typed build-task-graph contract, a dependency-DAG solver, and a collection validator are a later depth phase, not here.";
15
- readonly functionalTopics: readonly [];
16
15
  readonly preconditions: readonly [{
17
16
  readonly kind: "artifact_exists";
18
17
  readonly selector: {
@@ -36,12 +35,12 @@ export declare const playbookDefinition: {
36
35
  readonly outputs: readonly [{
37
36
  readonly family: "build-plan";
38
37
  readonly schemaRef: "saas-specifications:BuildPlanTaskGraph";
39
- readonly 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), 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 prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (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), 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 (prerequisite cycles are a hard floor; a resource stage without its predecessor stage is an authoring warning); 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.";
38
+ readonly 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), 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 prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (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), 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. 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.";
40
39
  }];
41
40
  readonly method: {
42
41
  readonly "//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.";
43
42
  readonly contextSources: readonly ["workspace_truth", "skill_catalog"];
44
- readonly skillRefs: readonly ["journey-status", "resource-add-module", "resource-add-resource", "resource-schema-authoring", "resource-config-wiring", "resource-ui-behavior", "spec-resource-update", "module-relationships", "module-registration"];
43
+ readonly skillRefs: readonly ["journey-status", "resource-add-module", "resource-add-resource", "resource-schema-authoring", "resource-config-wiring", "resource-ui-behavior", "spec-resource-update", "module-relationships", "module-registration", "application-database-migrations"];
45
44
  };
46
45
  readonly executor: "companion_agent";
47
46
  readonly approval: "approve_result";
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-decompose/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA8CrB,CAAC"}
1
+ {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.build-decompose/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CA8CrB,CAAC"}
@@ -9,10 +9,9 @@
9
9
  */
10
10
  export const playbookDefinition = {
11
11
  "ref": "bottom_up.build-decompose",
12
- "version": "0.2.0",
12
+ "version": "0.2.1",
13
13
  "phase": "bottom_up",
14
14
  "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 (labels / i18n, email templates, seeds) 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. v1 scaffold methodology — a typed build-task-graph contract, a dependency-DAG solver, and a collection validator are a later depth phase, not here.",
15
- "functionalTopics": [],
16
15
  "preconditions": [
17
16
  { "kind": "artifact_exists", "selector": { "family": "domain-plan" } }
18
17
  ],
@@ -28,7 +27,7 @@ export const playbookDefinition = {
28
27
  {
29
28
  "family": "build-plan",
30
29
  "schemaRef": "saas-specifications:BuildPlanTaskGraph",
31
- "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), 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 prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (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), 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 (prerequisite cycles are a hard floor; a resource stage without its predecessor stage is an authoring warning); 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."
30
+ "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), 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 prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (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), 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. 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."
32
31
  }
33
32
  ],
34
33
  "method": {
@@ -43,7 +42,8 @@ export const playbookDefinition = {
43
42
  "resource-ui-behavior",
44
43
  "spec-resource-update",
45
44
  "module-relationships",
46
- "module-registration"
45
+ "module-registration",
46
+ "application-database-migrations"
47
47
  ]
48
48
  },
49
49
  "executor": "companion_agent",
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-decompose/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,2BAA2B;IAClC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,qvDAAqvD;IAC/vD,kBAAkB,EAAE,EAAE;IACtB,eAAe,EAAE;QACf,EAAE,MAAM,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,aAAa,EAAE,EAAE;KACvE;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;KACnV;IACD,SAAS,EAAE;QACT;YACE,QAAQ,EAAE,YAAY;YACtB,WAAW,EAAE,wCAAwC;YACrD,aAAa,EAAE,6iFAA6iF;SAC7jF;KACF;IACD,QAAQ,EAAE;QACR,kBAAkB,EAAE,gfAAgf;QACpgB,gBAAgB,EAAE,CAAC,iBAAiB,EAAE,eAAe,CAAC;QACtD,WAAW,EAAE;YACX,gBAAgB;YAChB,qBAAqB;YACrB,uBAAuB;YACvB,2BAA2B;YAC3B,wBAAwB;YACxB,sBAAsB;YACtB,sBAAsB;YACtB,sBAAsB;YACtB,qBAAqB;SACtB;KACF;IACD,UAAU,EAAE,iBAAiB;IAC7B,UAAU,EAAE,gBAAgB;IAC5B,QAAQ,EAAE;QACR,SAAS,EAAE,CAAC;KACb;IACD,WAAW,EAAE,eAAe;CACpB,CAAC","sourcesContent":["/**\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. This source\n * intentionally omits the superseded per-playbook evaluation-treatment object;\n * generation records that absence rather than fabricating legacy judge behavior.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-decompose\",\n \"version\": \"0.2.0\",\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 (labels / i18n, email templates, seeds) 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. v1 scaffold methodology — a typed build-task-graph contract, a dependency-DAG solver, and a collection validator are a later depth phase, not here.\",\n \"functionalTopics\": [],\n \"preconditions\": [\n { \"kind\": \"artifact_exists\", \"selector\": { \"family\": \"domain-plan\" } }\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 ],\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), 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 prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (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), 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 (prerequisite cycles are a hard floor; a resource stage without its predecessor stage is an authoring warning); 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.\",\n \"contextSources\": [\"workspace_truth\", \"skill_catalog\"],\n \"skillRefs\": [\n \"journey-status\",\n \"resource-add-module\",\n \"resource-add-resource\",\n \"resource-schema-authoring\",\n \"resource-config-wiring\",\n \"resource-ui-behavior\",\n \"spec-resource-update\",\n \"module-relationships\",\n \"module-registration\"\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"]}
1
+ {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.build-decompose/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,2BAA2B;IAClC,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,qvDAAqvD;IAC/vD,eAAe,EAAE;QACf,EAAE,MAAM,EAAE,iBAAiB,EAAE,UAAU,EAAE,EAAE,QAAQ,EAAE,aAAa,EAAE,EAAE;KACvE;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;KACnV;IACD,SAAS,EAAE;QACT;YACE,QAAQ,EAAE,YAAY;YACtB,WAAW,EAAE,wCAAwC;YACrD,aAAa,EAAE,+5FAA+5F;SAC/6F;KACF;IACD,QAAQ,EAAE;QACR,kBAAkB,EAAE,gfAAgf;QACpgB,gBAAgB,EAAE,CAAC,iBAAiB,EAAE,eAAe,CAAC;QACtD,WAAW,EAAE;YACX,gBAAgB;YAChB,qBAAqB;YACrB,uBAAuB;YACvB,2BAA2B;YAC3B,wBAAwB;YACxB,sBAAsB;YACtB,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","sourcesContent":["/**\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. This source\n * intentionally omits the superseded per-playbook evaluation-treatment object;\n * generation records that absence rather than fabricating legacy judge behavior.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-decompose\",\n \"version\": \"0.2.1\",\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 (labels / i18n, email templates, seeds) 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. v1 scaffold methodology — a typed build-task-graph contract, a dependency-DAG solver, and a collection validator are a later depth phase, not here.\",\n \"preconditions\": [\n { \"kind\": \"artifact_exists\", \"selector\": { \"family\": \"domain-plan\" } }\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 ],\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), 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 prose prerequisite references, NOT a solved DAG). The ordering respects two axes: (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), 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. 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.\",\n \"contextSources\": [\"workspace_truth\", \"skill_catalog\"],\n \"skillRefs\": [\n \"journey-status\",\n \"resource-add-module\",\n \"resource-add-resource\",\n \"resource-schema-authoring\",\n \"resource-config-wiring\",\n \"resource-ui-behavior\",\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"]}
@@ -15,7 +15,6 @@ export declare const playbookDefinition: {
15
15
  readonly version: "0.1.0";
16
16
  readonly phase: "bottom_up";
17
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).";
18
- readonly functionalTopics: readonly [];
19
18
  readonly preconditions: readonly [{
20
19
  readonly kind: "artifact_exists";
21
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;;;;;;;;GAQG;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;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAuCrB,CAAC;AAEX;;;;;;;;GAQG;AACH,eAAO,MAAM,yBAAyB;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;CAsKW,CAAC"}
@@ -15,7 +15,6 @@ export const playbookDefinition = {
15
15
  "version": "0.1.0",
16
16
  "phase": "bottom_up",
17
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).",
18
- "functionalTopics": [],
19
18
  "preconditions": [
20
19
  { "kind": "artifact_exists", "selector": { "family": "build-plan" } }
21
20
  ],
@@ -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,kBAAkB,EAAE,EAAE;IACtB,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;YACX,gBAAgB;YAChB,iBAAiB;YACjB,aAAa;YACb,gBAAgB;SACjB;KACF;IACD,UAAU,EAAE,cAAc;IAC1B,UAAU,EAAE,gBAAgB;IAC5B,mFAAmF;IACnF,gFAAgF;IAChF,2EAA2E;IAC3E,mFAAmF;IACnF,qFAAqF;IACrF,6EAA6E;IAC7E,gFAAgF;IAChF,oFAAoF;IACpF,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;;;;;;;;GAQG;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,uWAAuW;gBACzW,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,2HAA2H;oBAClK,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,yGAAyG;oBACnJ,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,yHAAyH;oBAC/J,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';\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 \"functionalTopics\": [],\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 \"journey-status\",\n \"journey-approve\",\n \"journey-run\",\n \"journey-report\"\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); the four explicit ceilings below are the WORKING-episode safety\n // envelope the host turns into the Driver's per-episode resource authority\n // (`createApplicationPlaybookWorkingCeiling` refuses a working episode without all\n // four). Found by the Block-4 integration proof: the playbook had been promoted to a\n // working episode without them, so its live admission failed at `prepare()`.\n // Sized as stops against loops, not as cost control: three iterations, each ONE\n // structured-semantic evaluation; a coding run is not a model call of this ceiling.\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, mutation-scope assessment\n * and verification gate), never from model output; the criteria below are the\n * reviewer pass OVER that floor. 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, the mutation-scope assessment allowed every attributed path, and every required verification check succeeded. 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 change-set stayed inside the declared mutation scope and the verification gate passed.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'The gate passed, but the evidence shows a verification check the reviewer cannot independently confirm.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'No change-set was recorded, the run failed, a path escaped the mutation scope, 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,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;YACX,gBAAgB;YAChB,iBAAiB;YACjB,aAAa;YACb,gBAAgB;SACjB;KACF;IACD,UAAU,EAAE,cAAc;IAC1B,UAAU,EAAE,gBAAgB;IAC5B,mFAAmF;IACnF,gFAAgF;IAChF,2EAA2E;IAC3E,mFAAmF;IACnF,qFAAqF;IACrF,6EAA6E;IAC7E,gFAAgF;IAChF,oFAAoF;IACpF,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;;;;;;;;GAQG;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,uWAAuW;gBACzW,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,2HAA2H;oBAClK,CAAC,8BAA8B,CAAC,OAAO,CAAC,EAAE,yGAAyG;oBACnJ,CAAC,8BAA8B,CAAC,GAAG,CAAC,EAAE,yHAAyH;oBAC/J,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';\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 \"journey-status\",\n \"journey-approve\",\n \"journey-run\",\n \"journey-report\"\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); the four explicit ceilings below are the WORKING-episode safety\n // envelope the host turns into the Driver's per-episode resource authority\n // (`createApplicationPlaybookWorkingCeiling` refuses a working episode without all\n // four). Found by the Block-4 integration proof: the playbook had been promoted to a\n // working episode without them, so its live admission failed at `prepare()`.\n // Sized as stops against loops, not as cost control: three iterations, each ONE\n // structured-semantic evaluation; a coding run is not a model call of this ceiling.\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, mutation-scope assessment\n * and verification gate), never from model output; the criteria below are the\n * reviewer pass OVER that floor. 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, the mutation-scope assessment allowed every attributed path, and every required verification check succeeded. 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 change-set stayed inside the declared mutation scope and the verification gate passed.',\n [MetaWorkflow_EvaluationVerdict.CONCERN]: 'The gate passed, but the evidence shows a verification check the reviewer cannot independently confirm.',\n [MetaWorkflow_EvaluationVerdict.GAP]: 'No change-set was recorded, the run failed, a path escaped the mutation scope, 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"]}
@@ -12,7 +12,6 @@ export declare const playbookDefinition: {
12
12
  readonly version: "0.1.0";
13
13
  readonly phase: "bottom_up";
14
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.";
15
- readonly functionalTopics: readonly [];
16
15
  readonly preconditions: readonly [{
17
16
  readonly kind: "artifact_exists";
18
17
  readonly selector: {
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-scale/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;;CA4BrB,CAAC"}
1
+ {"version":3,"file":"playbook.definition.d.ts","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.build-scale/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,eAAO,MAAM,kBAAkB;;;;;;;;;;;;;;;;;;;;;;;;CA2BrB,CAAC"}
@@ -12,7 +12,6 @@ export const playbookDefinition = {
12
12
  "version": "0.1.0",
13
13
  "phase": "bottom_up",
14
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.",
15
- "functionalTopics": [],
16
15
  "preconditions": [
17
16
  { "kind": "artifact_exists", "selector": { "family": "build-plan" } }
18
17
  ],
@@ -1 +1 @@
1
- {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../../src/playbooks/bottom_up.build-scale/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,uBAAuB;IAC9B,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,uvGAAuvG;IACjwG,kBAAkB,EAAE,EAAE;IACtB,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;YACX,gBAAgB;YAChB,iBAAiB;YACjB,aAAa;YACb,gBAAgB;SACjB;KACF;IACD,UAAU,EAAE,cAAc;IAC1B,UAAU,EAAE,gBAAgB;IAC5B,QAAQ,EAAE;QACR,SAAS,EAAE,EAAE;KACd;IACD,WAAW,EAAE,eAAe;CACpB,CAAC","sourcesContent":["/**\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. This source\n * intentionally omits the superseded per-playbook evaluation-treatment object;\n * generation records that absence rather than fabricating legacy judge behavior.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-scale\",\n \"version\": \"0.1.0\",\n \"phase\": \"bottom_up\",\n \"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.\",\n \"functionalTopics\": [],\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 \"journey-status\",\n \"journey-approve\",\n \"journey-run\",\n \"journey-report\"\n ]\n },\n \"executor\": \"coding_agent\",\n \"approval\": \"approve_before\",\n \"budget\": {\n \"maxRuns\": 30\n },\n \"onFailure\": \"keep_and_flag\"\n} as const;\n"]}
1
+ {"version":3,"file":"playbook.definition.js","sourceRoot":"","sources":["../../../../src/playbooks/bottom_up.build-scale/playbook.definition.ts"],"names":[],"mappings":"AAAA;;;;;;;;GAQG;AACH,MAAM,CAAC,MAAM,kBAAkB,GAC/B;IACE,KAAK,EAAE,uBAAuB;IAC9B,SAAS,EAAE,OAAO;IAClB,OAAO,EAAE,WAAW;IACpB,QAAQ,EAAE,uvGAAuvG;IACjwG,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;YACX,gBAAgB;YAChB,iBAAiB;YACjB,aAAa;YACb,gBAAgB;SACjB;KACF;IACD,UAAU,EAAE,cAAc;IAC1B,UAAU,EAAE,gBAAgB;IAC5B,QAAQ,EAAE;QACR,SAAS,EAAE,EAAE;KACd;IACD,WAAW,EAAE,eAAe;CACpB,CAAC","sourcesContent":["/**\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. This source\n * intentionally omits the superseded per-playbook evaluation-treatment object;\n * generation records that absence rather than fabricating legacy judge behavior.\n */\nexport const playbookDefinition =\n{\n \"ref\": \"bottom_up.build-scale\",\n \"version\": \"0.1.0\",\n \"phase\": \"bottom_up\",\n \"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.\",\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 \"journey-status\",\n \"journey-approve\",\n \"journey-run\",\n \"journey-report\"\n ]\n },\n \"executor\": \"coding_agent\",\n \"approval\": \"approve_before\",\n \"budget\": {\n \"maxRuns\": 30\n },\n \"onFailure\": \"keep_and_flag\"\n} as const;\n"]}