@wildo-ai/framework-knowledge 1.1.8 → 1.1.9

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 (226) hide show
  1. package/dist/claude-marketplace/plugins/wildo/.claude-plugin/plugin.json +1 -1
  2. package/dist/claude-marketplace/plugins/wildo/references/composites-and-the-loop.md +9 -2
  3. package/dist/claude-marketplace/plugins/wildo/references/creation-state.md +21 -0
  4. package/dist/claude-marketplace/plugins/wildo/references/derived-artifacts.md +121 -0
  5. package/dist/claude-marketplace/plugins/wildo/references/runs-judges-and-questions.md +29 -5
  6. package/dist/claude-marketplace/plugins/wildo/skills/answer/SKILL.md +29 -2
  7. package/dist/claude-marketplace/plugins/wildo/skills/build/SKILL.md +69 -24
  8. package/dist/claude-marketplace/plugins/wildo/skills/doctor/SKILL.md +10 -0
  9. package/dist/claude-marketplace/plugins/wildo/skills/run/SKILL.md +21 -5
  10. package/dist/claude-marketplace/plugins/wildo/skills/start/SKILL.md +31 -5
  11. package/dist/claude-marketplace/plugins/wildo/skills/status/SKILL.md +2 -0
  12. package/dist/claude-marketplace/plugins/wildo/skills/why/SKILL.md +11 -1
  13. package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
  14. package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
  15. package/dist/esm/framework-knowledge.definitions.js +11 -1
  16. package/dist/esm/framework-knowledge.definitions.js.map +1 -1
  17. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +2 -2
  18. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +2 -2
  19. package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -1
  20. package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts +11 -11
  21. package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts.map +1 -1
  22. package/dist/esm/playbooks/bottom_up.build/playbook.definition.js +29 -22
  23. package/dist/esm/playbooks/bottom_up.build/playbook.definition.js.map +1 -1
  24. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +3 -3
  25. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts.map +1 -1
  26. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +59 -10
  27. package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
  28. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +1 -1
  29. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +3 -3
  30. package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
  31. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +1 -1
  32. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +1 -1
  33. package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
  34. package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js +1 -1
  35. package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js.map +1 -1
  36. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +2 -1
  37. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
  38. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +5 -5
  39. package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
  40. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +8 -0
  41. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
  42. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +12 -4
  43. package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
  44. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +25 -27
  45. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
  46. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +85 -43
  47. package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
  48. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts +40 -0
  49. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts.map +1 -0
  50. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js +41 -0
  51. package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js.map +1 -0
  52. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts +199 -0
  53. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts.map +1 -0
  54. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js +201 -0
  55. package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js.map +1 -0
  56. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts +67 -0
  57. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts.map +1 -0
  58. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js +76 -0
  59. package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js.map +1 -0
  60. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +3 -1
  61. package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
  62. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +27 -18
  63. package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
  64. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +11 -1
  65. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -1
  66. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +11 -11
  67. package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -1
  68. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +2 -0
  69. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -1
  70. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +3 -1
  71. package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
  72. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +2 -0
  73. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
  74. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +3 -1
  75. package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
  76. package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts +5 -2
  77. package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts.map +1 -1
  78. package/dist/esm/playbooks/top_down.definition/playbook.definition.js +16 -4
  79. package/dist/esm/playbooks/top_down.definition/playbook.definition.js.map +1 -1
  80. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +7 -3
  81. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
  82. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +36 -2
  83. package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
  84. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts +7 -1
  85. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts.map +1 -1
  86. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js +4 -2
  87. package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js.map +1 -1
  88. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +9 -3
  89. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
  90. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +3 -3
  91. package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
  92. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +35 -2
  93. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
  94. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +30 -17
  95. package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
  96. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
  97. package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +1 -1
  98. package/dist/knowledge/manifest.json +8 -8
  99. package/dist/knowledge/playbooks/bottom_up.assemble-verify/method.md +22 -7
  100. package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +3 -3
  101. package/dist/knowledge/playbooks/bottom_up.build/method.md +17 -15
  102. package/dist/knowledge/playbooks/bottom_up.build/playbook.json +4 -3
  103. package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-protocol.json +1 -1
  104. package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-treatment.json +1 -1
  105. package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +117 -28
  106. package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +4 -4
  107. package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +133 -59
  108. package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +2 -2
  109. package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +169 -276
  110. package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +2 -2
  111. package/dist/knowledge/playbooks/bottom_up.capability-composition/method.md +8 -1
  112. package/dist/knowledge/playbooks/bottom_up.capability-composition/playbook.json +1 -1
  113. package/dist/knowledge/playbooks/bottom_up.conception/method.md +3 -2
  114. package/dist/knowledge/playbooks/bottom_up.conception/playbook.json +2 -2
  115. package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-protocol.json +1 -1
  116. package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-treatment.json +1 -1
  117. package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +22 -6
  118. package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +4 -3
  119. package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +13 -5
  120. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +5 -2
  121. package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +1 -1
  122. package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-protocol.json +1 -1
  123. package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-treatment.json +1 -1
  124. package/dist/knowledge/playbooks/top_down.brand-identity/method.md +71 -37
  125. package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +35 -38
  126. package/dist/knowledge/playbooks/top_down.brand-name-research/method.md +105 -0
  127. package/dist/knowledge/playbooks/top_down.brand-name-research/playbook.json +55 -0
  128. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-protocol.json +1 -0
  129. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-treatment.json +1 -0
  130. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/method.md +78 -0
  131. package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/playbook.json +63 -0
  132. package/dist/knowledge/playbooks/top_down.brand-naming/method.md +56 -0
  133. package/dist/knowledge/playbooks/top_down.brand-naming/playbook.json +65 -0
  134. package/dist/knowledge/playbooks/top_down.business-model/evaluation-protocol.json +1 -1
  135. package/dist/knowledge/playbooks/top_down.business-model/evaluation-treatment.json +1 -1
  136. package/dist/knowledge/playbooks/top_down.business-model/method.md +60 -6
  137. package/dist/knowledge/playbooks/top_down.business-model/playbook.json +15 -10
  138. package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +30 -10
  139. package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +3 -1
  140. package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +4 -1
  141. package/dist/knowledge/playbooks/top_down.definition/method.md +8 -3
  142. package/dist/knowledge/playbooks/top_down.definition/playbook.json +6 -4
  143. package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-protocol.json +1 -1
  144. package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-treatment.json +1 -1
  145. package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +11 -1
  146. package/dist/knowledge/playbooks/top_down.risk-register/method.md +21 -0
  147. package/dist/knowledge/playbooks/top_down.risk-register/playbook.json +8 -2
  148. package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +4 -2
  149. package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +10 -0
  150. package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +40 -17
  151. package/dist/knowledge/references/brand.name-choice.config.md +127 -0
  152. package/dist/knowledge/references/brand.name-screening.config.md +253 -0
  153. package/dist/knowledge/references/build-plan.task-graph.config.md +64 -11
  154. package/dist/knowledge/references/business-model.pricing-plan.config.md +16 -0
  155. package/dist/knowledge/references/business-model.snapshot.config.md +64 -0
  156. package/dist/knowledge/references/business-model.snapshot.validation.md +68 -4
  157. package/dist/knowledge/references/capability-composition.config.md +67 -4
  158. package/dist/knowledge/references/example.data-seeding.minimal.md +29 -1
  159. package/dist/knowledge/references/market.snapshot.validation.md +1 -1
  160. package/dist/knowledge/references/saas.data-seeding.bootstrap-wiring.md +7 -1
  161. package/dist/knowledge/references/saas.data-seeding.definition-input.md +6 -0
  162. package/dist/knowledge/references/saas.models.queue.scheduled-recovery.md +81 -2
  163. package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +10 -0
  164. package/dist/knowledge/references/saas.website.astro.label-loader.md +9 -0
  165. package/dist/knowledge/references/saas.website.factories.define-section.md +4 -0
  166. package/dist/knowledge/references/saas.website.page-manifest.schema.md +12 -3
  167. package/dist/knowledge/references/saas.website.page-sections.component.md +72 -0
  168. package/dist/knowledge/references/saas.website.sections.definition-schema.md +11 -0
  169. package/dist/knowledge/registries/assurance-authority-bases.json +1 -1
  170. package/dist/knowledge/registries/framework-topics.json +38 -1
  171. package/dist/knowledge/registries/playbooks.json +68 -20
  172. package/dist/knowledge/registries/source-tags.json +748 -695
  173. package/dist/knowledge/rules/live-context-door.md +5 -2
  174. package/dist/knowledge/skills/INDEX.md +2 -1
  175. package/dist/knowledge/skills/application-database-migrations/SKILL.md +1 -1
  176. package/dist/knowledge/skills/brand-name-screening/SKILL.md +154 -0
  177. package/dist/knowledge/skills/brand-name-screening/references/framework-brand-name-screening-api.md +394 -0
  178. package/dist/knowledge/skills/brand-name-screening/references/screening-procedure.md +65 -0
  179. package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +5 -2
  180. package/dist/knowledge/skills/config-saas/SKILL.md +31 -4
  181. package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +14 -1
  182. package/dist/knowledge/skills/config-saas/references/framework-background-work-api.md +81 -2
  183. package/dist/knowledge/skills/email-add-template/SKILL.md +1 -1
  184. package/dist/knowledge/skills/i18n-rerun-pipeline/SKILL.md +1 -1
  185. package/dist/knowledge/skills/inbound-channels/SKILL.md +2 -2
  186. package/dist/knowledge/skills/local-environment-bootstrap/SKILL.md +11 -1
  187. package/dist/knowledge/skills/local-environment-bootstrap/references/derived-artifact-currency.md +122 -0
  188. package/dist/knowledge/skills/local-environment-bootstrap/references/framework-upgrade-and-dependency-alignment.md +11 -0
  189. package/dist/knowledge/skills/local-environment-bootstrap/references/wildo-cli-bootstrap-commands.md +9 -2
  190. package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +11 -1
  191. package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +11 -1
  192. package/dist/knowledge/skills/market-message-templates-authoring/references/framework-message-template-api.md +1 -1
  193. package/dist/knowledge/skills/market-snapshot-validation/SKILL.md +1 -1
  194. package/dist/knowledge/skills/market-snapshot-validation/references/framework-snapshot-validation-api.md +1 -1
  195. package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +10 -0
  196. package/dist/knowledge/skills/module-relationships/SKILL.md +6 -4
  197. package/dist/knowledge/skills/seeding-authoring/SKILL.md +51 -3
  198. package/dist/knowledge/skills/seeding-authoring/references/framework-data-seeding-api.md +6 -0
  199. package/dist/knowledge/skills/seeding-operations/references/framework-data-seeding-operations-api.md +7 -1
  200. package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +10 -0
  201. package/dist/knowledge/skills/website-factory-advanced/SKILL.md +4 -0
  202. package/dist/knowledge/skills/website-page-authoring/SKILL.md +84 -3
  203. package/dist/knowledge/skills/website-section-contact/SKILL.md +15 -0
  204. package/dist/knowledge/skills/website-section-contact/references/define-website-section-api.md +15 -0
  205. package/dist/knowledge/skills/website-section-cta/SKILL.md +15 -0
  206. package/dist/knowledge/skills/website-section-cta/references/define-website-section-api.md +15 -0
  207. package/dist/knowledge/skills/website-section-faq/SKILL.md +15 -0
  208. package/dist/knowledge/skills/website-section-faq/references/define-website-section-api.md +15 -0
  209. package/dist/knowledge/skills/website-section-feature-benefit-summary/SKILL.md +15 -0
  210. package/dist/knowledge/skills/website-section-feature-benefit-summary/references/define-website-section-api.md +15 -0
  211. package/dist/knowledge/skills/website-section-feature-detail/SKILL.md +15 -0
  212. package/dist/knowledge/skills/website-section-feature-detail/references/define-website-section-api.md +15 -0
  213. package/dist/knowledge/skills/website-section-footer-cta/SKILL.md +15 -0
  214. package/dist/knowledge/skills/website-section-footer-cta/references/define-website-section-api.md +15 -0
  215. package/dist/knowledge/skills/website-section-hero/SKILL.md +27 -9
  216. package/dist/knowledge/skills/website-section-hero/references/define-website-section-api.md +15 -0
  217. package/dist/knowledge/skills/website-section-pricing/SKILL.md +15 -0
  218. package/dist/knowledge/skills/website-section-pricing/references/define-website-section-api.md +15 -0
  219. package/dist/knowledge/skills/website-section-social-proof/SKILL.md +15 -0
  220. package/dist/knowledge/skills/website-section-social-proof/references/define-website-section-api.md +15 -0
  221. package/dist/knowledge/skills/website-seo-aeo-geo/SKILL.md +1 -1
  222. package/dist/knowledge/skills/website-seo-aeo-geo/references/aeo-api.md +11 -0
  223. package/dist/knowledge/topic-index.json +169 -43
  224. package/dist/tsconfig.build.tsbuildinfo +1 -1
  225. package/dist/tsconfig.tsbuildinfo +1 -1
  226. package/package.json +4 -4
@@ -1,6 +1,6 @@
1
1
  {
2
2
  "name": "wildo",
3
- "version": "1.1.8",
3
+ "version": "1.1.9",
4
4
  "description": "Drive Wildo application creation from Claude Code: run playbooks, follow the companion, answer its questions.",
5
5
  "author": {
6
6
  "name": "Wildo"
@@ -16,11 +16,18 @@ that finished 4 of 10 gets 6 more, not 10 — and a resumed run says so in `resu
16
16
 
17
17
  ## The loop (`wildo creation loop --goal … --iterations <n>`)
18
18
 
19
+ Before its first round it runs the creation preflight (`wildo creation preflight`) and is refused on a
20
+ `FAIL` line — a provider the lane's agents call that is not enabled or has no key, or a billing key the
21
+ backend boot will ask for — before any round is spent. Report those lines to the person; `--skip-preflight`
22
+ is theirs to pass, not yours.
23
+
19
24
  Each round it gates what is eligible, a model chooses lanes (or chooses to stop), and the chosen
20
25
  playbooks run concurrently when their outputs do not overlap. What it will NOT do:
21
26
 
22
- - It never runs a playbook that declares an interview: a model handed no answers can only invent or
23
- omit them. Run those with the person's answers, before or between loops.
27
+ - It runs a playbook that declares an interview only once the dossier answers it. In a QUICK interview it
28
+ first proposes the questions the quick interview skips and records them as assumptions (never a
29
+ regulated-domain question, never one only the person may answer), so such a playbook can run; the queue lists
30
+ them to revisit. Anything else unanswered waits for the person's answers, before or between loops.
24
31
  - One loop per companion. A second is refused, not queued.
25
32
  - It stops for one of four named reasons: nothing eligible, the model chose to stop, the iteration
26
33
  ceiling, or every lane of one round failed. Lanes per round default to 3 and cap at 5. Both limits
@@ -39,10 +39,31 @@ state.
39
39
 
40
40
  ## The build lane (`wildo build next`, `wildo build tasks`)
41
41
 
42
+ The build runs in PARALLEL by default. `wildo build run` starts a WAVE: up to N coding runs at once, N
43
+ being the application's build parallelism (`wildo workbench parallelism`; 5 unless set, `1` means one at
44
+ a time). The runs share ONE worktree and may touch the same files; the lane does not prevent that, it
45
+ repairs it. When the runs have settled it commits what their own accepts left as one change, and re-runs
46
+ ALONE any task whose finished product a sibling overwrote. Each run's record says what it overlapped
47
+ (`concurrency`), whether a failure is suspected to come from a sibling (`interferenceSuspected`), and
48
+ what was done about it (`interference`). One call takes at most four tasks per slot and then returns;
49
+ `wildo build run` again continues from where the build stands, once the running wave has ended — a
50
+ second wave is refused while one runs. `wildo build run --single` and
51
+ `wildo build run <taskRef>` run one task alone.
52
+
42
53
  `plan: null` has two meanings. With `exhausted`, every task landed. With a non-empty `stuckTasks`,
43
54
  nothing ready can run, and each entry's `reason` names what unblocks it — most often a run that wrote
44
55
  its work without committing it, because **a task lands only once its product is committed**.
45
56
 
57
+ "Every task landed" is not "the application builds". When the plan is exhausted, the dispatch and the
58
+ build wave also report an `assembly` verdict: every package's typecheck plus the schema-plan check.
59
+ Report it beside the count. A failing check names the package and what the compiler said; a check that
60
+ could not run says nothing about the application.
61
+
62
+ A landing is derived from committed files, so a task can be landed by something other than its own
63
+ run (a sibling task, the person). `wildo build tasks` lists such a task as **`found`**, never `landed`,
64
+ and the dispatch board names them in `landedBeforeAnyRunTaskRefs`. Report them apart: "92 of 92 landed"
65
+ with 18 found before any run of their own is a different build from 92 that ran.
66
+
46
67
  ## Coherence (`wildo context coherence`)
47
68
 
48
69
  The ONLY surface that answers cross-family questions: what the working tree states with nothing behind
@@ -0,0 +1,121 @@
1
+ # Derived artifacts: finding and regenerating a stale one
2
+
3
+ Read this when `/wildo:doctor` reports a missing generated file, when a process in the person's
4
+ `wildo local dev` output refuses a generated file or says to regenerate it, or when the person asks
5
+ whether what they are running is current.
6
+
7
+ Regenerating is the person's working tree changing, not the stack starting or stopping: say which
8
+ command you are about to run and why, run it from the application root, and report what changed.
9
+ Never edit a generated file, a provider, or `wildo.saas.config.ts` to make a refusal go away.
10
+
11
+ ### Derived artifacts: where they live, how to tell they are current, what regenerates them
12
+
13
+ Much of what your application runs is **derived**: written by a `wildo` command or a dev watcher from
14
+ something you authored. A derived file never fails at the moment it goes stale. It fails later, far
15
+ from its cause, when a process that reads it refuses it — and by then the error reads like a bug in
16
+ your code or in the framework. It almost never is.
17
+
18
+ Four facts govern every row below:
19
+
20
+ - **A derived file is never edited by hand.** Fix the authored source, then regenerate. A hand edit is
21
+ overwritten by the next regeneration and leaves no trace of why it reverted.
22
+ - **Most derived files are regenerated by a COMMAND, not by a watcher.** `wildo local dev` rebuilds
23
+ your packages as you edit them, and when it STARTS it regenerates the provider runtime artifacts if a
24
+ generated module is missing or a reader would refuse one of the JSON artifacts — but it never refreshes the CSP file, the labels or the docs,
25
+ and it does not watch the provider artifacts once running. A framework update can change what a
26
+ reader requires of those files while their inputs stay the same, so they go stale without anything
27
+ you did.
28
+ - **When a reader refuses a derived file, its message names the command that regenerates it.** That
29
+ is the fix. Run it; do not "repair" the reader, the provider, or the authored config to make the
30
+ refusal go away.
31
+ - **Regenerating is safe.** `wildo config sync` never rotates a secret unless you pass
32
+ `--rotate-secrets`; it only adds framework-managed secrets that are missing. Apart from that, the
33
+ one authored file it can change is a backend `package.json` (and the root `pnpm.overrides`), when
34
+ `systemsOfRecord` is declared and the library it needs is not: run `pnpm install` after that.
35
+ Regenerating a current file changes nothing.
36
+
37
+ #### When a running process refuses a generated file
38
+
39
+ 1. **Read the refusal for a command.** The messages in the table below each name one.
40
+ 2. **Date the artifact.** Provider runtime artifacts carry a `generatedAt` field; for anything else use
41
+ the file's modification time. Older than the last change to your `@wildo-ai/*` versions
42
+ (`pnpm-lock.yaml`), to `wildo.saas.config.ts`, or to `wildo.infra.<env>.config.ts`? It is stale.
43
+ 3. **Run the command it names**, from the application root. For the provider runtime artifacts that
44
+ is `wildo -y config sync --local` (add `--env <env>` for one environment). `-y` keeps it from
45
+ stopping at the env-file prompt: it then leaves existing `.env` files alone, which is what you want
46
+ here, and still writes every provider runtime artifact.
47
+ 4. **Let the refused process restart.** Under `wildo local dev` each process is supervised and
48
+ restarts on its own within seconds; otherwise restart that one process. Do not restart the stack.
49
+ 5. **Confirm**: the process logs that it started, and the artifact's `generatedAt` is now.
50
+
51
+ | The refusal says (abbreviated) | Stale artifact | Regenerate with |
52
+ |---|---|---|
53
+ | `refused to serve frontend provider configuration it was handed … declares no publicConfigSchema whose keys can be read … generated before this check existed` | the frontend provider bootstrap: `.wildo-saas/generated/providers/frontend-services.runtime-providers.generated.json` when a website or docs build refuses, `backend-api/src/generated/wildo-provider-runtime.generated.ts` when the backend's `/application-config` refuses | `wildo -y config sync --local` |
54
+ | `generated provider runtime artifact at … does not satisfy the current contract` | a `.wildo-saas/generated/providers/*.runtime-providers.generated.json` file | `wildo -y config sync --local` |
55
+ | `generated before the contract changed. Regenerate it … and restart` · `The artifact is stale for this package` | `backend-api/src/generated/wildo-provider-runtime.generated.ts` | `wildo -y config sync --local` |
56
+ | `runtime artifact lists no facet modules` | the same module, generated before systems of record existed | `wildo -y config sync --local --domain env-files` |
57
+ | `Missing generated provider runtime module` (printed by your backend's own `src/index.ts`) | the same module, absent | `wildo -y config sync --local` |
58
+ | `Missing or invalid companion provider runtime artifact` | `.wildo-saas/generated/providers/companion.runtime-providers.generated.json` | `wildo -y config sync --local` |
59
+ | `detected stale provider topology` · `does not contain a scope for worker/minion` | a minion's or worker's `.wildo-providers.env` or generated module | `wildo -y config sync --local` |
60
+ | browser console: `bundle carries no code for it … regenerate frontend-providers.generated.ts` (a provider silently missing) | `<frontend service>/src/generated/frontend-providers.generated.ts` | `wildo -y config sync --local`, then commit it |
61
+ | `Lockfile drift detected` | `.wildo-saas/wildo-saas.lock.json` | `wildo -y config sync --local`, then commit it |
62
+ | `postgresql_table_schema_mismatch` | the database schema behind your resources | `wildo db generate --name <label>` (see the database-migrations skill) |
63
+ | `Run wildo dev sync-csp and commit the result` | `<frontend service>/src/generated/csp.generated.json` | `wildo dev sync-csp` |
64
+ | `Run wildo config <data-retention · service-consent · subject-data-recipients · document-releases> and commit` | the matching `backend-api/src/*.generated.ts` compliance module | the command it names |
65
+ | `No generated config … Run wildo config sync --domain config` | `.wildo-saas/infrastructure/environments/<env>/generated/config/config.json` | `wildo config sync --local --domain config` |
66
+
67
+ #### Every derived artifact, and how to check it
68
+
69
+ | Artifact | Lives at | Regenerated by | How to tell it is current | In git? |
70
+ |---|---|---|---|---|
71
+ | Provider runtime artifacts | `.wildo-saas/generated/providers/*.runtime-providers.generated.json`; `backend-api/src/generated/wildo-provider-runtime.generated.ts` and the same file in each minion and Node worker; `minions/*/.wildo-providers.env`, `workers/*/.wildo-providers.env` | `wildo -y config sync --local` (no prompt); `wildo local dev` regenerates a missing or refused one when it starts | `wildo local doctor` — the **generated provider-runtime artifact content** line checks the frontend-services, backend and companion JSON files with what their readers apply, and names every one a reader would refuse. It does not read the minion and worker JSON files, the `.ts` modules or the `.wildo-providers.env` files | No — always safe to regenerate |
72
+ | Frontend provider modules | `<frontend service>/src/generated/frontend-providers.generated.ts`, `frontend-provider-service.generated.json` | `wildo -y config sync --local` | Nothing. A stale one drops a provider with a browser-console warning instead of failing | Yes — commit after regenerating |
73
+ | Provider catalogue types | `.wildo-saas/generated/provider-catalog.types.ts` | `wildo -y config sync --local` | Nothing; stale only means stale autocomplete | Yes |
74
+ | Application lockfile | `.wildo-saas/wildo-saas.lock.json` | `wildo -y config sync --local` (providers, infra); module and label commands write their own sections | `wildo lock check` — checks the providers and infra sections only | Yes |
75
+ | Content security policy | `<frontend service>/src/generated/csp.generated.json` | `wildo dev sync-csp` (also `wildo dev start`) — **not** `wildo config sync` | `wildo dev sync-csp --check` (it refreshes the provider artifacts before comparing) | Yes |
76
+ | Environment config and local stack | `.wildo-saas/infrastructure/environments/<env>/generated/config/config.json`, `…/docker-compose/docker-compose.wildo-platform.yml`, `…/docker-compose/.env.wildo-platform` | `wildo -y config sync --local`. `wildo local up` only recreates a MISSING one, never a stale one | `wildo config validate --domain config` checks coherence with your secrets, not currency | No |
77
+ | Per-package `.env` files | `backend-api/.env`, `frontend/.env`, `website/.env`, `technical-doc/.env`, each minion and worker, `.wildo-saas/wildo-dev-companion/.env` | `wildo -y config sync --local --domain env-files` — needs the local platform running (when it is down this phase fails, but the provider artifacts are still written). It asks before overwriting; `-y` SKIPS existing files, `--force` rewrites them | Nothing | No |
78
+ | Application identity | `.wildo-saas/infrastructure/environments/<env>/generated/config/application-runtime-identity.json` | **Not derived** — assigned when the application registered (`wildo local init`) | — | No, and **do not delete it**: only re-registration restores it |
79
+ | Compliance modules | `backend-api/src/{data-retention,service-consent-requirement,subject-data-recipients,governed-document-releases}.generated.ts` | `wildo config data-retention` · `service-consent` · `subject-data-recipients` · `document-releases` | The same command with `--check`, or `wildo config validate --domain <same name>` | Yes |
80
+ | Database migrations | `backend-api/migrations/`, `backend-api/migrations/schema-plan.lock.json` | `wildo db generate --name <label>` | `wildo db diff --check`. It refuses to answer while `backend-api/dist` is older than its sources — let the build catch up first | Yes — **never delete** |
81
+ | Labels and translations | `backend-api/src/engine/i18n/**` | `wildo generate labels`, then `wildo generate translate` (the dev companion must be running) | No command reports it; the lockfile records each unit's status | Yes |
82
+ | Technical documentation | `technical-doc/src/generated/api-reference/**`, `technical-doc/src/generated/consumer-documentation/**` | `wildo docs publish` (the dev companion must be running) | Nothing short of republishing and reading the diff | Yes |
83
+ | Package builds | each package's `dist/` | the dev watchers `wildo local dev` starts | Nothing direct; `wildo db diff` refuses on a stale `backend-api/dist` | No |
84
+ | Config loader cache | `.wildo-saas/dist/config-loader/` | rebuilt on demand | Nothing; delete it when `wildo.saas.config.ts` edits seem ignored | No — always safe to delete |
85
+ | Delivered framework | `.claude/skills/` and the rules delivered beside them under `.claude/`, `.wildo-saas/templates/`, `.wildo-saas/wildo-dev-companion/` | `wildo assets sync` (`wildo update` runs it) | Nothing records which release delivered them; re-run `wildo assets sync` when in doubt | Skills and rules yes; templates and the companion build no |
86
+
87
+ Files your application-creation runs produced — brand assets, personas, charters, specifications —
88
+ are **committed decisions**, not caches. They are never regenerated to fix a refusal.
89
+
90
+ #### What `wildo local doctor` can and cannot tell you
91
+
92
+ - It **fails** when a generated provider runtime module is missing, and names `wildo config sync`.
93
+ - It **fails** when a present provider runtime artifact would be refused by the process that reads
94
+ it (*generated provider-runtime artifact content*), with the reason that reader gives — for the
95
+ frontend-services and backend files, the reader's own refusal message. It applies what the readers
96
+ apply rather than comparing dates, so it catches a file a framework update made stale while every
97
+ input stayed the same. It covers the frontend-services, backend and companion JSON files only.
98
+ - It does not check the other derived artifacts in the table above; use the command in their row.
99
+ - Its **derived-artifact currency** line reads `not probed` in an application installed from
100
+ published packages. That is not a pass: it compares builds against a framework source checkout,
101
+ which your application does not have.
102
+
103
+ #### Regenerate before you debug, after any of these
104
+
105
+ - **A framework update.** `wildo update` ends by regenerating the provider runtime artifacts and the
106
+ CSP files (`wildo dev sync-csp`, for the active environment), after declaring and installing the
107
+ systems-of-record library when `systemsOfRecord` needs it. If the release you moved to predates that
108
+ step, run `wildo -y config sync --local` yourself. If the step fails, its message says why:
109
+ - `Config file not found: …/wildo.infra.<env>.config.ts` — only the CSP half failed: the provider
110
+ runtime artifacts were already regenerated. The active environment has no authored infra config;
111
+ set it up with `wildo setup` (or select an environment that has one), then run `wildo dev sync-csp`.
112
+ - `Cannot produce the frontend provider configuration … its secrets … cannot be read` — nothing was
113
+ produced, and `config sync` stops on the same check. Restore that environment's `secrets.json`:
114
+ the provider configuration is screened against it and is never produced without it.
115
+ - **A change to `providers` or `services` in `wildo.saas.config.ts`**, or adding a frontend service:
116
+ `wildo -y config sync --local`, then `wildo dev sync-csp`.
117
+ - **A change to `wildo.infra.<env>.config.ts`**: `wildo -y config sync --local`, then
118
+ `wildo config sync --local --domain manifest`.
119
+
120
+ Commit the tracked files a regeneration changed in their own commit, so the next reader can tell a
121
+ regeneration from an authored change.
@@ -47,13 +47,37 @@ moved past is refused. Question rounds default to three; once spent, the run pro
47
47
 
48
48
  A playbook that declares an INTERVIEW asks its questions before it runs; they appear in the same queue
49
49
  as interview questions. An answer is matched by the question's ref, and a `choice` question takes one
50
- of its options verbatim. Ask the regulated-domain questions of the vision interview explicitly —
50
+ of its options verbatim. Some `choice` questions have options COMPUTED from what the application has already
51
+ landed rather than written in the catalog: the brand identity's `brand-name` offers the names
52
+ `top_down.brand-naming` proposed and screened. Its options are listed with the question; one may end
53
+ in a qualifier (`[screening-incomplete]`, `[keep-despite-conflict]`) that is part of the answer and
54
+ records how the person chose. Until the naming step has landed a screening, the question has no
55
+ options and cannot be answered yet. Never invent a name for the person, and never present a screened
56
+ name as legally cleared: the screening is a minimal trademark screening, not a clearance opinion. Ask the regulated-domain questions of the vision interview explicitly —
51
57
  children or protected data, financial services, healthcare and life sciences, legal or regulatory
52
58
  decisions, public sector and critical infrastructure — because their answers decide which compliance
53
- playbooks matter later — they are the person's to answer, never derived. Never answer FOR the person:
54
- an answer is either theirs, or one a cited file of the application settles, sent as the agent's with
55
- its source. An answer outside a question's vocabulary is the person's signal to revisit the question,
56
- not a value to coerce.
59
+ playbooks matter later; they are never derived from the application's files. (A quick interview may
60
+ PROPOSE them, as below — a proposal the person keeps is an assumption named to them, never a derivation.) Never answer FOR the
61
+ person: an answer is either theirs, or one a cited file of the application settles, sent as the agent's
62
+ with its source, or an ASSUMPTION (below): a proposal they kept, or one an unattended round recorded for a
63
+ quick interview — never for a regulated-domain question. An answer outside a question's vocabulary is
64
+ the person's signal to revisit the question, not a value to coerce.
65
+
66
+ ## How deep an interview goes, and what happens when the person does not know
67
+
68
+ Each application chooses its interview depth once, with `wildo creation depth simple|detailed`, and
69
+ `wildo creation questions` shows it. A **simple** interview asks only the essential questions — an item
70
+ marked `detail:` is not asked — and the rest are proposed. A **detailed** interview asks everything.
71
+
72
+ A question the person does not know is not a dead end. Unless it is marked `only the person can answer
73
+ it`, `wildo creation propose <playbookRef> --question <ref>` asks the companion for an answer built from
74
+ what the person already said; with no `--question` it proposes everything the depth does not ask. It
75
+ writes nothing. Show each proposal with what it rests on; what the person keeps is sent with
76
+ `wildo creation answer <questionId> --assumed "<value>" --rationale "<why>"` and recorded as ASSUMED —
77
+ the run treats it as a working hypothesis, and the dossier lists it as "Assumed — to revisit" until the
78
+ person answers it themselves. `wildo creation questions` lists assumptions APART from what is waiting:
79
+ nothing waits on them, so never work them as open questions; revisit one only when the person asks. What they change is theirs, sent with `--person`. A regulated-domain
80
+ proposal may be kept the same way, but always name it to the person explicitly first.
57
81
 
58
82
  ## Evidence and spend
59
83
 
@@ -1,7 +1,7 @@
1
1
  ---
2
2
  description: Answer the questions the Wildo dev companion is waiting on — the ones the application itself already answers, from its own configuration and specifications, and the rest by asking the person. Use when the person says "answer the questions", "what is it asking", "it's waiting on me", or a run stopped on a question.
3
3
  argument-hint: [<questionId>]
4
- allowed-tools: Bash(wildo creation questions:*) Bash(wildo creation answer:*) Bash(wildo workbench open:*) Bash(echo:*)
4
+ allowed-tools: Bash(wildo creation questions:*) Bash(wildo creation answer:*) Bash(wildo creation propose:*) Bash(wildo creation depth:*) Bash(wildo workbench open:*) Bash(echo:*)
5
5
  ---
6
6
 
7
7
  # Answer what the companion is waiting on
@@ -19,6 +19,20 @@ ITEM at a time — each answer can change what the next run asks. An item is one
19
19
  round (`kind: clarification`) is one item carrying several questions in `fields`, and it is answered in
20
20
  ONE call covering all of them.
21
21
 
22
+ **Interview items follow the application's interview depth** (the queue's `interviewDepth`), before anything else:
23
+
24
+ - **No depth yet** (`null`) and the queue holds interview items: ask the person once whether they want a
25
+ quick interview (only the essential questions; the rest are proposed for them to review) or a detailed
26
+ one (every question), and record it with `wildo creation depth simple` or `wildo creation depth detailed`.
27
+ Then read the queue again.
28
+ - **Quick** (`simple`): do NOT ask the interview items marked `askedInSimpleInterview: false` one by one.
29
+ Ask the others as below. Then, per playbook, run `wildo creation propose <playbookRef>` ONCE (adding
30
+ `--instance <instanceKey>` when the items carry one): it proposes every question the quick interview leaves open. Show the proposals as ONE list, each with what it rests
31
+ on, naming every regulated-domain proposal to the person explicitly, and ask which to keep. Send each
32
+ kept one with `--assumed` and its `--rationale`; a question the person would rather answer is asked like
33
+ any other and sent with `--person`.
34
+ - **Detailed**: every interview item is asked, as below.
35
+
22
36
  For each item:
23
37
 
24
38
  1. **An item whose `actions` list is empty is not answered here**, and there are two kinds:
@@ -37,6 +51,12 @@ For each item:
37
51
  conversation;
38
52
  - a `confirm`: AskUserQuestion with Yes / No (and "Let the run decide" when `decline` is admitted);
39
53
  - `free_text`: ask in the conversation, offering the deriver's proposal as a default they can accept.
54
+ - **An interview item the person does not know** ("I don't know", "you decide"), when it is not marked
55
+ `only the person can answer it`: run `wildo creation propose <playbookRef> --question <ref>`, show the
56
+ proposal and what it rests on, and ask whether to keep it. Kept, send it with
57
+ `wildo creation answer <questionId> --assumed "<value>" --rationale "<why>"` — it is recorded as an
58
+ assumption to revisit, never as their decision. Changed, it is theirs (`--person`). A regulated-domain
59
+ proposal is always named to them explicitly before it is kept.
40
60
  4. **Send the item in ONE call**, each answer tagged with who gave it:
41
61
 
42
62
  ```
@@ -62,7 +82,14 @@ Rules:
62
82
  `wildo creation answer` refuses an unattributed answer from inside an agent session, because the
63
83
  committed record says who answered and it must be true.
64
84
  - `--decline` is admitted only where the item's `actions` include `decline` (a playbook round). A parked
65
- coding run's question and an interview question are answered or, for a coding run, cancelled.
85
+ coding run's question and an interview question are answered or, for a coding run, cancelled. An
86
+ interview question the person does not know takes `--assumed` with a proposal instead.
87
+ - `--assumed` is only for a value `wildo creation propose` returned and the person let stand. Never send
88
+ your own guess, or the deriver's, as an assumption.
89
+ - The queue's `assumptions` are ANSWERED, not waiting: each is a proposal, kept by the person or recorded by an
90
+ unattended round for a quick interview. Work only the
91
+ `questions`. Revisit an assumption only when the person asks to — answering it (`--person`) records their
92
+ own answer in its place.
66
93
  - If the answer is refused, show the reason and ask again; do not rephrase it into something it was not.
67
94
 
68
95
  ## Read when you need it
@@ -1,38 +1,83 @@
1
1
  ---
2
- description: Dispatch build-plan tasks to coding workers, one or several in a row, committing each finished one before the next. Only the person starts this.
3
- argument-hint: [<taskRef> | <how many>]
2
+ description: Run the build — a parallel wave of build-plan tasks by default, as wide as the application's build parallelism — or one named task, or tasks one at a time. Only the person starts this.
3
+ argument-hint: [<taskRef> [--despite-landed --reason <reason> --note "<why>"] | --single | <how many, one at a time>]
4
4
  disable-model-invocation: true
5
- allowed-tools: Bash(wildo build run:*) Bash(wildo build tasks:*) Bash(wildo build accept:*) Bash(wildo creation feed:*) Bash(wildo creation questions:*) Bash(wildo creation answer:*)
5
+ allowed-tools: Bash(wildo build run:*) Bash(wildo build tasks:*) Bash(wildo build accept:*) Bash(wildo workbench parallelism:*) Bash(wildo creation feed:*) Bash(wildo creation questions:*) Bash(wildo creation answer:*)
6
6
  ---
7
7
 
8
8
  # Build: $ARGUMENTS
9
9
 
10
- The argument is a task ref (run that task), a number (run that many in a row), or nothing (run one).
10
+ The build runs in PARALLEL by default. The lane keeps up to N coding runs going at once in the one
11
+ worktree, where N is the application's build parallelism (5 unless the person set it), and refills a
12
+ slot as soon as a run settles. Do not loop over tasks one by one to "be safe": that is the slow path,
13
+ and the lane already handles runs that touch the same files.
11
14
 
12
- For each task:
15
+ What the argument means:
13
16
 
14
- 1. **Dispatch.** `wildo build run <taskRef>` for a named task, otherwise `wildo build run`. It
15
- answers at once with the task it started; say which, by its objective. Exit `2` means the companion
16
- is not running (tell the person to run `wildo local dev`, and stop); exit `1` names why the task
17
- was refused.
17
+ - **nothing** — run the build as a wave (below);
18
+ - **a task ref** — run that task alone. Followed by `--despite-landed --reason <reason> --note "<why>"`
19
+ it runs a task whose landing probe calls it landed although no run of it produced the product (a
20
+ `found` task in `wildo build tasks`). Pass those flags through exactly as the person gave them; never
21
+ add them yourself;
22
+ - **`--single`** — run the next ready task alone;
23
+ - **a number** — run that many tasks one at a time (`wildo build run --single` each time), committing
24
+ each before the next.
25
+
26
+ ## The wave (no argument)
27
+
28
+ 1. **Say the width.** `wildo workbench parallelism` prints how many tasks run at once. Report it. Never
29
+ change it yourself: each slot is a live agent spending on its own, so the width is the person's call
30
+ (`wildo workbench parallelism <n>`; `1` means one task at a time).
31
+ 2. **Start it.** `wildo build run`. It answers at once: `Started a build wave: up to N tasks at once
32
+ (run <runId>)`. With a parallelism of 1 it answers with the one task it started; follow that one as
33
+ in "One task" below. Exit `2` means the companion is not running (tell the person to run
34
+ `wildo local dev`, and stop). Exit `1` names why nothing started:
35
+ - when every task has landed, the refusal says whether the application ASSEMBLES (each package's
36
+ typecheck). Report that verdict, not "the build is finished": a failing package is work left;
37
+ - when every ready task is stuck, it names the tasks and why. Report them; `/wildo:why <taskRef>`
38
+ explains one.
39
+ - when the creation preflight refuses (`PASS`/`WARN`/`FAIL` lines, or "The creation preflight refused
40
+ this run"), a provider key or scope is missing — for the console's checks, the coding agent's too; for the
41
+ companion's, the playbook lane, the logo step or the expert panel. Tell the person
42
+ each `FAIL` and its remedy, and stop. Never add `--skip-preflight` yourself; that is the person's call.
43
+ 3. **Follow it.** Start `wildo creation feed --follow --exit-on-change --timeout 3600` as a BACKGROUND
44
+ command and wait; start it again after each change until the wave's run completes. The wave stops
45
+ taking tasks when nothing more is ready or it reached its per-call cap, then waits for its runs.
46
+ Do NOT run `wildo build run` again meanwhile: a second wave is refused (exit `1`, "already running")
47
+ until this one has ended, its end-of-wave commit and repair included.
48
+ 4. **Answer what it asks.** An `ASKED` line is a run parked on a question: read it with
49
+ `wildo creation questions` and answer it as `/wildo:answer` does —
50
+ `wildo creation answer <questionId> --revision <revision>` with `--person` for the person's answer,
51
+ or `--derived … --derived-by agent:wildo-deriver` for one the application's own files settle.
52
+ The other runs keep going meanwhile.
53
+ 5. **Report the wave** from `wildo build tasks --json`:
54
+ - what landed, and what is **finished and waiting to be committed** (`stuck.reason` names
55
+ uncommitted work). Under the autonomy posture the loop commits a finished run itself; commit what
56
+ it did not with `wildo build accept <taskRef>`, once the wave's run has completed;
57
+ - each failed run with its failed checks, and `/wildo:why <taskRef>`;
58
+ - runs marked `interferenceSuspected`, or with a `concurrency` entry naming the tasks that overlapped
59
+ them. A run that finished and then lost its product to a sibling is re-run alone by the wave, and
60
+ its `interference` entry says so. Say which, rather than reporting a plain failure;
61
+ - what is left: `wildo build run` again starts the next wave.
62
+
63
+ ## One task (a task ref, `--single`, or each step of a number)
64
+
65
+ 1. **Dispatch.** `wildo build run <taskRef>`, or `wildo build run --single`. It answers at once with
66
+ the task it started; say which, by its objective. Exit codes as above.
18
67
  2. **Follow.** Start `wildo creation feed --follow --exit-on-change --timeout 3600` as a BACKGROUND
19
68
  command and wait. A coding worker takes minutes.
20
69
  3. **Read the outcome** with `wildo build tasks --json` for that task.
21
- - **Finished and waiting to be committed** — the task's `stuck.reason` names uncommitted work:
22
- commit it with `wildo build accept <taskRef>` and report what was committed. The next task
23
- cannot land on top of uncommitted work.
24
- - **It asked a question** — an `ASKED` line for this task: read it with `wildo creation questions`
25
- and answer it as `/wildo:answer` does — `wildo creation answer <questionId> --revision <revision>`
26
- with `--person` for the person's answer, or `--derived … --derived-by agent:wildo-deriver` for one
27
- the application's own files settle — then follow again.
28
- - **It failed**, a check failed, or it wrote outside its scope: STOP the sequence. Report the
29
- error and the failed checks, and suggest `/wildo:why <taskRef>`.
30
- 4. Continue with the next task only when this one committed cleanly and more were asked for.
31
-
32
- Never commit while a dispatch is running: the worker is writing the same tree. Never edit the files
33
- a running dispatch owns. Never run `wildo build rearm` without the person: re-arming re-spends money
34
- on a task that already ran.
70
+ - **Finished and waiting to be committed**: commit it with `wildo build accept <taskRef>` and report
71
+ what was committed. The next task cannot land on top of uncommitted work.
72
+ - **It asked a question**: answer it as in step 4 of the wave, then follow again.
73
+ - **It failed**, a check failed, or it wrote outside its scope: STOP the sequence. Report the error
74
+ and the failed checks, and suggest `/wildo:why <taskRef>`.
75
+ 4. For a number, continue with the next task only when this one committed cleanly.
76
+
77
+ Never commit while a dispatch or a wave is running: the workers are writing the same tree. Never edit
78
+ the files a running dispatch owns. Never run `wildo build rearm` without the person: re-arming
79
+ re-spends money on a task that already ran.
35
80
 
36
81
  ## Read when you need it
37
82
 
38
- - `${CLAUDE_PLUGIN_ROOT}/references/creation-state.md` — the build lane: what `plan: null`, `exhausted` and `stuckTasks` mean
83
+ - `${CLAUDE_PLUGIN_ROOT}/references/creation-state.md` — the build lane: the wave, what `plan: null`, `exhausted` and `stuckTasks` mean
@@ -21,3 +21,13 @@ own wording for the fix; do not invent another.
21
21
  processes they supervise.
22
22
  - Do not alter credentials, provider configuration or secrets to make a check pass.
23
23
  - If everything passes, say so in one line and suggest `/wildo:status`.
24
+ - A pass does not prove a generated file is current. If a finding, or a process in the person's dev
25
+ output, names a generated file or says to regenerate it, read the reference below. Name the stale
26
+ artifact, the command the reference gives for it and the process that will restart afterwards, and
27
+ ask the person before running that command: it changes files in their working tree.
28
+
29
+ ## Read when you need it
30
+
31
+ - `${CLAUDE_PLUGIN_ROOT}/references/derived-artifacts.md` — every generated file in the application:
32
+ where it lives, how to tell it is current, which command regenerates it, and the refusal messages a
33
+ stale one produces
@@ -3,15 +3,21 @@ description: Run one playbook in the dev companion, follow it, handle the questi
3
3
  argument-hint: <playbookRef> [what you want from this run]
4
4
  arguments: [playbook, brief]
5
5
  disable-model-invocation: true
6
- allowed-tools: Bash(wildo creation run:*) Bash(wildo creation feed:*) Bash(wildo creation questions:*) Bash(wildo creation answer:*) Bash(wildo creation why:*) Bash(wildo creation diff:*)
6
+ allowed-tools: Bash(wildo creation run:*) Bash(wildo creation preflight:*) Bash(wildo creation feed:*) Bash(wildo creation questions:*) Bash(wildo creation answer:*) Bash(wildo creation propose:*) Bash(wildo creation depth:*) Bash(wildo creation why:*) Bash(wildo creation diff:*) Bash(wildo creation report:*) Bash(wildo creation reason:*)
7
7
  ---
8
8
 
9
9
  # Run a playbook: $playbook
10
10
 
11
- 1. **Start it.** Run `wildo creation run $playbook`, adding `--brief "$brief"` when a brief was
11
+ 1. **Start it.** If `wildo creation questions` lists `assumptions` for $playbook, name them first: they
12
+ are proposals the person did not decide (kept on review, or recorded unattended for a quick interview), and
13
+ this run will build on them. Revisit any they want
14
+ to (answer it with `--person`). Then run `wildo creation run $playbook`, adding `--brief "$brief"` when a brief was
12
15
  given. Exit `2` means the companion is not running: tell the person to run `wildo local dev` in
13
16
  their own terminal, and stop. Exit `1` names why it was refused; a playbook refused for missing
14
- answers names the questions, so go to step 3.
17
+ answers names the questions, so go to step 3. A refusal printed as `PASS`/`WARN`/`FAIL` lines is the
18
+ creation preflight (`wildo creation preflight` prints the same report): tell the person each `FAIL` line
19
+ and the remedy under it, and stop. Never add `--skip-preflight` yourself; starting past a FAIL is the
20
+ person's decision, and the step that lacks its provider is refused anyway, hours in.
15
21
  2. **Follow it.** Start `wildo creation feed --follow --exit-on-change --timeout 1800` as a
16
22
  BACKGROUND command, so you are told when something happens instead of polling. Wait for it.
17
23
  3. **When it asks** (an `ASKED` line, or `wildo creation questions` lists this run), answer it the way
@@ -22,12 +28,22 @@ allowed-tools: Bash(wildo creation run:*) Bash(wildo creation feed:*) Bash(wildo
22
28
  - what the product should be, a trade-off or a choice is put to the person, and sent as theirs:
23
29
  `--person --answer <ref>=<value>`;
24
30
  - one `wildo creation answer <questionId> --revision <revision>` call per question round, carrying
25
- both groups.
31
+ both groups;
32
+ - INTERVIEW questions follow the application's interview depth as `/wildo:answer` describes (with no depth
33
+ chosen yet, ask quick or detailed and record it with `wildo creation depth simple|detailed`): in a quick
34
+ interview, the questions it skips are proposed together with `wildo creation propose $playbook` and
35
+ reviewed as one list, never asked one by one; a question the person does not know is proposed with
36
+ `--question <ref>`; a kept proposal is sent with `--assumed` and its `--rationale`.
26
37
  Then follow again (step 2).
27
38
  4. **When it finishes**, report in a few lines:
28
39
  - what landed (the families), and `wildo creation diff <runId>` for what it changed;
29
40
  - for a judged run, the criteria that did not pass, by name;
30
- - for a failed run, the error, and `wildo creation why <runId>`.
41
+ - for a failed run, the error, and `wildo creation why <runId>`;
42
+ - if you or the person stepped in during it (restarted the companion, edited or committed a file the run
43
+ wrote, re-armed a task, ran one past its landing, reverted a run), run `wildo creation report`: it lists
44
+ each of those as an intervention, derived. Give each one you were part of its reason with
45
+ `wildo creation reason <id> "<why>"`; the reason is the one thing it cannot derive, and the next run is
46
+ judged against these entries.
31
47
  5. **Do not commit here.** What it wrote is a working edit. Suggest `/wildo:accept` to review and
32
48
  commit it, or `wildo creation revert <runId>` to undo it.
33
49
 
@@ -1,6 +1,6 @@
1
1
  ---
2
2
  description: Begin creating the application with the dev companion — check the stack, then open the vision interview as a conversation. Use in the first session in a new application, or when the person says "let's start", "start the app", or "begin creation".
3
- allowed-tools: Bash(wildo context health:*) Bash(wildo creation feed:*) Bash(wildo creation questions:*) Bash(wildo creation run:*) Bash(wildo creation answer:*) Bash(echo:*)
3
+ allowed-tools: Bash(wildo context health:*) Bash(wildo creation feed:*) Bash(wildo creation questions:*) Bash(wildo creation depth:*) Bash(wildo creation propose:*) Bash(wildo creation run:*) Bash(wildo creation preflight:*) Bash(wildo creation answer:*) Bash(echo:*)
4
4
  ---
5
5
 
6
6
  # Start creating this application
@@ -21,18 +21,44 @@ allowed-tools: Bash(wildo context health:*) Bash(wildo creation feed:*) Bash(wil
21
21
  3. **Otherwise, open the vision interview.** Explain in two sentences what happens: the companion
22
22
  runs playbooks that decide the product, each one asks a few questions, and the answers become the
23
23
  application's specification, reviewed and committed by the person.
24
+ - **First, ask how deep to go**, unless `wildo creation depth` already names a depth. Offer the two,
25
+ in one sentence each: a **quick** interview asks three questions (the kind of application, the
26
+ product in one line, the problem it solves) and proposes the rest for them to review (if creation later
27
+ runs on its own, it records those proposals as assumptions to revisit, never a regulated-domain one); a **detailed**
28
+ interview asks all of them. Record the choice with `wildo creation depth simple` or
29
+ `wildo creation depth detailed` — it is kept for this application's later interviews too.
24
30
  - The vision playbook, `top_down.vision-elicitation`, asks its questions BEFORE it runs, as an
25
- interview. List them with `wildo creation questions` (the `interview` items it asks).
31
+ interview. List them with `wildo creation questions` (the `interview` items it asks). In a quick
32
+ interview, ask only the items NOT marked `detail:`; in a detailed one, ask them all.
26
33
  - Put each one to the person in plain words, as a conversation, not as a form, and send their answer
27
34
  with `wildo creation answer <questionId> --person "<their answer>"` (a `choice` takes one of its
28
- options verbatim). Every vision question is the person's to answer: what the product is, who it is
29
- for and the regulated-domain questions are decisions, never facts to derive.
35
+ options verbatim). Never answer from the application's files here: a vision question is a decision,
36
+ not a fact to derive.
37
+ - **When the person does not know** ("I don't know", "you decide", "no idea") and the item is not
38
+ marked `only the person can answer it`, propose instead of pressing them: run
39
+ `wildo creation propose top_down.vision-elicitation --question <ref>`, show the proposal and what it
40
+ rests on, and ask whether to keep it. Kept as it is, send it as an assumption —
41
+ `wildo creation answer <questionId> --assumed "<value>" --rationale "<why>"` (the command
42
+ `wildo creation propose` prints) — never with `--person`, because they did not decide it. Changed,
43
+ it is theirs: send it with `--person`. The kind of application is the one question only they can
44
+ answer; describe the options again and let them choose.
45
+ - **In a quick interview, after the essential questions**, run `wildo creation propose top_down.vision-elicitation`
46
+ with no `--question`: it proposes every remaining question at once. Show them as ONE review list —
47
+ question, proposed answer, what it rests on — and ask the person to change any they disagree with.
48
+ **Name every regulated-domain proposal explicitly** (children's data, financial services, health,
49
+ legal or compliance decisions, public sector): those answers decide which compliance work matters
50
+ later, so the person must see each one, not skim past it. Then send each: kept ones with `--assumed`,
51
+ changed ones with `--person`. Anything the proposal could not cover, ask.
30
52
  - When none of its questions is left, run it with `wildo creation run top_down.vision-elicitation`
31
53
  and follow it with `wildo creation feed --follow --exit-on-change --timeout 600`, started as a
32
54
  background command, so you are told when it moves. If it stops on a question round, answer it as
33
55
  `/wildo:answer` does.
56
+ - If the run is refused with `PASS`/`WARN`/`FAIL` lines, that is the creation preflight
57
+ (`wildo creation preflight` prints the same report): a new application often has no provider keys
58
+ yet. Tell the person each `FAIL` line and the remedy under it, and stop. Never add `--skip-preflight`
59
+ yourself; starting past a FAIL is the person's decision.
34
60
  4. End by saying what landed and suggesting `/wildo:next`.
35
61
 
36
62
  ## Read when you need it
37
63
 
38
- - `${CLAUDE_PLUGIN_ROOT}/references/runs-judges-and-questions.md` — the interview, and the regulated-domain questions to ask
64
+ - `${CLAUDE_PLUGIN_ROOT}/references/runs-judges-and-questions.md` — the interview, its depth, proposed answers, and the regulated-domain questions
@@ -25,6 +25,8 @@ reached, `1` means it answered with a refusal (its reason is printed).
25
25
  should run `wildo local dev` in a terminal of their own. Do not start it yourself.
26
26
  - Otherwise write ONE screen, in this order:
27
27
  1. **Asked of you** — each waiting question, in the person's words, with its question id.
28
+ The queue's `assumptions` are NOT waiting — each is a proposal, kept by the person or recorded by an
29
+ unattended round for a quick interview; mention how many, never list them as asked of you.
28
30
  2. **What happened** — the `SINCE` lines, newest first; a failed run with the error it hit, and
29
31
  for a judged run the criteria that did not pass.
30
32
  3. **What could come next** — the `SUGGESTION` lines.
@@ -27,7 +27,17 @@ scope). Then name ONE remedy with its command:
27
27
  - waiting on another task → that task first;
28
28
  - a failed check or error the code must fix → what to change, and then `/wildo:build <taskRef>`;
29
29
  - a task the loop guard holds after its cause was fixed → `wildo build rearm <taskRef> --reason …
30
- --note …`, which the person runs, because re-arming spends money again.
30
+ --note …`, which the person runs, because re-arming spends money again;
31
+ - a completed run whose product is missing while concurrent runs changed the same file ("suspected
32
+ interference") → nothing, when the build wave says it re-runs it alone; when its re-runs are spent,
33
+ the re-arm above with `--reason operator-judgement`, then `/wildo:build <taskRef>`. It is suspected,
34
+ not proven: if the task fails again when run alone, the cause is the task's own.
35
+ - a task listed as `found` (its record carries `landedBeforeAnyRun`): its landing probe finds the
36
+ product, but no run of the task produced it. Read the file the record names. If a sibling task or the
37
+ person wrote the product, it is real: nothing to do. If what was found is not the product, the
38
+ remedy is `/wildo:build <taskRef> --despite-landed --reason <reason> --note "<why>"` (the reasons are
39
+ the re-arm reasons), which only the person starts, because it spends money on a run the probe says
40
+ is done.
31
41
 
32
42
  If the records do not say why, say that plainly rather than guessing.
33
43