@wildo-ai/framework-knowledge 1.1.5 → 1.1.7
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.
- package/dist/claude-marketplace/.claude-plugin/marketplace.json +14 -0
- package/dist/claude-marketplace/plugins/wildo/.claude-plugin/plugin.json +8 -0
- package/dist/claude-marketplace/plugins/wildo/agents/wildo-deriver.md +41 -0
- package/dist/claude-marketplace/plugins/wildo/hooks/hooks.json +18 -0
- package/dist/claude-marketplace/plugins/wildo/monitors/monitors.json +8 -0
- package/dist/claude-marketplace/plugins/wildo/references/acceptance.md +38 -0
- package/dist/{knowledge/skills/journey-run/references/framework-playbook-approval-policy.md → claude-marketplace/plugins/wildo/references/approval-and-failure-policy.md} +10 -8
- package/dist/claude-marketplace/plugins/wildo/references/composites-and-the-loop.md +29 -0
- package/dist/claude-marketplace/plugins/wildo/references/creation-state.md +61 -0
- package/dist/{knowledge/skills/journey-run → claude-marketplace/plugins/wildo}/references/expert-personas-and-deliberations.md +8 -8
- package/dist/claude-marketplace/plugins/wildo/references/runs-judges-and-questions.md +67 -0
- package/dist/claude-marketplace/plugins/wildo/skills/accept/SKILL.md +43 -0
- package/dist/claude-marketplace/plugins/wildo/skills/answer/SKILL.md +70 -0
- package/dist/claude-marketplace/plugins/wildo/skills/build/SKILL.md +38 -0
- package/dist/claude-marketplace/plugins/wildo/skills/doctor/SKILL.md +23 -0
- package/dist/claude-marketplace/plugins/wildo/skills/next/SKILL.md +39 -0
- package/dist/claude-marketplace/plugins/wildo/skills/run/SKILL.md +39 -0
- package/dist/claude-marketplace/plugins/wildo/skills/start/SKILL.md +38 -0
- package/dist/claude-marketplace/plugins/wildo/skills/status/SKILL.md +38 -0
- package/dist/claude-marketplace/plugins/wildo/skills/why/SKILL.md +37 -0
- package/dist/esm/framework-knowledge.definitions.d.ts +1 -1
- package/dist/esm/framework-knowledge.definitions.d.ts.map +1 -1
- package/dist/esm/framework-knowledge.definitions.js +321 -11
- package/dist/esm/framework-knowledge.definitions.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +0 -3
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts +12 -2
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.js +33 -2
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts +8 -5
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js +55 -10
- package/dist/esm/playbooks/bottom_up.build-decompose/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js +1 -6
- package/dist/esm/playbooks/bottom_up.build-dispatch/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js +1 -6
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.capability-composition/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.capability-composition/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.capability-composition/playbook.definition.js +0 -1
- package/dist/esm/playbooks/bottom_up.capability-composition/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.d.ts +2 -2
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js +13 -4
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.documentation-plan/playbook.definition.d.ts +10 -3
- package/dist/esm/playbooks/bottom_up.documentation-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.documentation-plan/playbook.definition.js +7 -3
- package/dist/esm/playbooks/bottom_up.documentation-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js +8 -3
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.js +0 -1
- package/dist/esm/playbooks/bottom_up.experience-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +7 -3
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +9 -4
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.integration-plan/playbook.definition.d.ts +3 -2
- package/dist/esm/playbooks/bottom_up.integration-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.integration-plan/playbook.definition.js +4 -3
- package/dist/esm/playbooks/bottom_up.integration-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.maturity-reading/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.maturity-reading/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.maturity-reading/playbook.definition.js +1 -3
- package/dist/esm/playbooks/bottom_up.maturity-reading/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js +0 -1
- package/dist/esm/playbooks/bottom_up.placement-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.d.ts +10 -3
- package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.js +8 -3
- package/dist/esm/playbooks/bottom_up.website-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/cross_cutting.application-creation/playbook.definition.d.ts +12 -5
- package/dist/esm/playbooks/cross_cutting.application-creation/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/cross_cutting.application-creation/playbook.definition.js +33 -5
- package/dist/esm/playbooks/cross_cutting.application-creation/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/cross_cutting.compliance/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/cross_cutting.compliance/playbook.definition.js +1 -1
- package/dist/esm/playbooks/cross_cutting.compliance/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/cross_cutting.feature-development/playbook.definition.d.ts +59 -0
- package/dist/esm/playbooks/cross_cutting.feature-development/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/cross_cutting.feature-development/playbook.definition.js +72 -0
- package/dist/esm/playbooks/cross_cutting.feature-development/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/cross_cutting.refinement/playbook.definition.d.ts +66 -0
- package/dist/esm/playbooks/cross_cutting.refinement/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/cross_cutting.refinement/playbook.definition.js +115 -0
- package/dist/esm/playbooks/cross_cutting.refinement/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/refinement.document-facts/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js +1 -1
- package/dist/esm/playbooks/refinement.document-facts/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/refinement.feature-contribution/playbook.definition.d.ts +50 -0
- package/dist/esm/playbooks/refinement.feature-contribution/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/refinement.feature-contribution/playbook.definition.js +54 -0
- package/dist/esm/playbooks/refinement.feature-contribution/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.capability-map/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.compliance-evidence-adequacy/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.compliance-research/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts +36 -17
- package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.definition/playbook.definition.js +67 -17
- package/dist/esm/playbooks/top_down.definition/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.expert-personas/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.feature-drafts/playbook.definition.d.ts +45 -0
- package/dist/esm/playbooks/top_down.feature-drafts/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.feature-drafts/playbook.definition.js +46 -0
- package/dist/esm/playbooks/top_down.feature-drafts/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.market-analysis/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.market-evidence-adequacy/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.market-research/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.market-research/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js +0 -1
- package/dist/esm/playbooks/top_down.market-snapshot-produce/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.requirements-definition/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +1 -1
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js +0 -1
- package/dist/esm/playbooks/top_down.value-proposition/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +1 -1
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js +11 -3
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.js.map +1 -1
- package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/authority-basis.json +1 -1
- package/dist/knowledge/assurance-authority-bases/wildo-safe-baseline-v1/external-framework-mapping.json +1 -1
- package/dist/knowledge/manifest.json +8 -8
- package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +0 -3
- package/dist/knowledge/playbooks/bottom_up.build/method.md +4 -2
- package/dist/knowledge/playbooks/bottom_up.build/playbook.json +31 -7
- package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.build-decompose/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.build-decompose/method.md +134 -26
- package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +7 -4
- package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +84 -29
- package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +2 -7
- package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +12 -23
- package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +2 -7
- package/dist/knowledge/playbooks/bottom_up.capability-composition/method.md +12 -14
- package/dist/knowledge/playbooks/bottom_up.capability-composition/playbook.json +1 -2
- package/dist/knowledge/playbooks/bottom_up.conception/method.md +20 -2
- package/dist/knowledge/playbooks/bottom_up.conception/playbook.json +15 -7
- package/dist/knowledge/playbooks/bottom_up.documentation-plan/method.md +8 -6
- package/dist/knowledge/playbooks/bottom_up.documentation-plan/playbook.json +11 -4
- package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +2 -4
- package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +3 -4
- package/dist/knowledge/playbooks/bottom_up.experience-plan/method.md +18 -2
- package/dist/knowledge/playbooks/bottom_up.experience-plan/playbook.json +1 -2
- package/dist/knowledge/playbooks/bottom_up.foundation/method.md +2 -4
- package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +8 -5
- package/dist/knowledge/playbooks/bottom_up.integration-plan/method.md +16 -2
- package/dist/knowledge/playbooks/bottom_up.integration-plan/playbook.json +3 -3
- package/dist/knowledge/playbooks/bottom_up.maturity-reading/playbook.json +1 -3
- package/dist/knowledge/playbooks/bottom_up.placement-plan/playbook.json +1 -2
- package/dist/knowledge/playbooks/bottom_up.website-plan/method.md +8 -7
- package/dist/knowledge/playbooks/bottom_up.website-plan/playbook.json +11 -4
- package/dist/knowledge/playbooks/cross_cutting.application-creation/playbook.json +27 -5
- package/dist/knowledge/playbooks/cross_cutting.compliance/playbook.json +1 -4
- package/dist/knowledge/playbooks/cross_cutting.feature-development/method.md +42 -0
- package/dist/knowledge/playbooks/cross_cutting.feature-development/playbook.json +73 -0
- package/dist/knowledge/playbooks/cross_cutting.refinement/method.md +46 -0
- package/dist/knowledge/playbooks/cross_cutting.refinement/playbook.json +108 -0
- package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +112 -21
- package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +1 -1
- package/dist/knowledge/playbooks/refinement.document-facts/method.md +7 -2
- package/dist/knowledge/playbooks/refinement.document-facts/playbook.json +2 -4
- package/dist/knowledge/playbooks/refinement.feature-contribution/method.md +48 -0
- package/dist/knowledge/playbooks/refinement.feature-contribution/playbook.json +66 -0
- package/dist/knowledge/playbooks/refinement.governance-document-candidate/method.md +6 -0
- package/dist/knowledge/playbooks/refinement.governance-document-candidate/playbook.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/method.md +0 -4
- package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +1 -2
- package/dist/knowledge/playbooks/top_down.business-model/playbook.json +1 -3
- package/dist/knowledge/playbooks/top_down.capability-map/method.md +2 -4
- package/dist/knowledge/playbooks/top_down.capability-map/playbook.json +1 -2
- package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +1 -3
- package/dist/knowledge/playbooks/top_down.compliance-conception/method.md +5 -3
- package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +2 -4
- package/dist/knowledge/playbooks/top_down.compliance-evidence-adequacy/playbook.json +1 -3
- package/dist/knowledge/playbooks/top_down.compliance-posture/method.md +0 -4
- package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +2 -4
- package/dist/knowledge/playbooks/top_down.compliance-research/playbook.json +1 -3
- package/dist/knowledge/playbooks/top_down.definition/method.md +7 -4
- package/dist/knowledge/playbooks/top_down.definition/playbook.json +52 -7
- package/dist/knowledge/playbooks/top_down.expert-personas/method.md +1 -1
- package/dist/knowledge/playbooks/top_down.expert-personas/playbook.json +2 -4
- package/dist/knowledge/playbooks/top_down.feature-drafts/method.md +72 -0
- package/dist/knowledge/playbooks/top_down.feature-drafts/playbook.json +57 -0
- package/dist/knowledge/playbooks/top_down.market-analysis/playbook.json +0 -1
- package/dist/knowledge/playbooks/top_down.market-evidence-adequacy/playbook.json +0 -1
- package/dist/knowledge/playbooks/top_down.market-research/playbook.json +0 -1
- package/dist/knowledge/playbooks/top_down.market-snapshot-produce/method.md +2 -4
- package/dist/knowledge/playbooks/top_down.market-snapshot-produce/playbook.json +1 -2
- package/dist/knowledge/playbooks/top_down.phase-gate/method.md +1 -1
- package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +2 -6
- package/dist/knowledge/playbooks/top_down.requirements-definition/method.md +17 -1
- package/dist/knowledge/playbooks/top_down.requirements-definition/playbook.json +2 -5
- package/dist/knowledge/playbooks/top_down.risk-register/playbook.json +1 -3
- package/dist/knowledge/playbooks/top_down.scope-roadmap/method.md +15 -7
- package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +2 -4
- package/dist/knowledge/playbooks/top_down.value-proposition/method.md +2 -4
- package/dist/knowledge/playbooks/top_down.value-proposition/playbook.json +1 -2
- package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +7 -3
- package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +12 -5
- package/dist/knowledge/references/backend.inbound-channels.handler-definition.md +212 -0
- package/dist/knowledge/references/backend.inbound-handlers.agents.md +45 -0
- package/dist/knowledge/references/backend.inbound-handlers.definition.md +218 -0
- package/dist/knowledge/references/build-plan.task-graph.config.md +71 -6
- package/dist/knowledge/references/capability-composition.config.md +20 -1
- package/dist/knowledge/references/cli.market.generate-command.md +18 -2
- package/dist/knowledge/references/engine.client-bundle.allow-list.md +7 -22
- package/dist/knowledge/references/engine.saas-technical-doc.provider-component.slot.md +83 -0
- package/dist/knowledge/references/example.authorization.service-provider-organization-wide-access.md +12 -0
- package/dist/knowledge/references/example.backend.addon-wiring.module.md +5 -0
- package/dist/knowledge/references/example.backend.custom-operation.create-postfix.md +7 -3
- package/dist/knowledge/references/example.config.app-shell.command-menu-items.md +7 -0
- package/dist/knowledge/references/example.config.app-shell.full.md +11 -0
- package/dist/knowledge/references/example.config.backend.billing-enable.md +14 -0
- package/dist/knowledge/references/example.config.backend.inbound-email.md +14 -0
- package/dist/knowledge/references/example.config.backend.required-floors.md +7 -0
- package/dist/knowledge/references/example.config.navigation.full.md +45 -2
- package/dist/knowledge/references/example.config.provider-usage-pricing.md +36 -0
- package/dist/knowledge/references/example.config.provider.backend-scope-billing.md +5 -3
- package/dist/knowledge/references/example.config.provider.backend-scope-inbound-email.md +16 -0
- package/dist/knowledge/references/example.flows-actors.autonomous-agent.md +23 -0
- package/dist/knowledge/references/example.flows-actors.autonomous-agent.reviewed-write.md +36 -0
- package/dist/knowledge/references/example.flows-actors.chat-assistant.md +26 -3
- package/dist/knowledge/references/example.flows-actors.llm-agent-one-shot.md +1 -1
- package/dist/knowledge/references/example.inbound.application-endpoint-handler.md +72 -0
- package/dist/knowledge/references/example.inbound.email-channel-handler.md +47 -0
- package/dist/knowledge/references/example.inbound.email-to-todo.md +150 -0
- package/dist/knowledge/references/example.infra.environment-config.local.md +14 -30
- package/dist/knowledge/references/example.layout-3d.own-layout.md +16 -0
- package/dist/knowledge/references/example.layout-3d.registration.md +15 -0
- package/dist/knowledge/references/example.module.companion-exports.full.md +8 -13
- package/dist/knowledge/references/example.module.relationships.discriminator.md +2 -2
- package/dist/knowledge/references/example.organizations.serves-as-provider.md +12 -0
- package/dist/knowledge/references/example.provider.address-lookup.adapter.md +64 -0
- package/dist/knowledge/references/example.provider.backend-module-shape.md +3 -0
- package/dist/knowledge/references/example.provider.frontend-app.module.md +9 -0
- package/dist/knowledge/references/example.provider.frontend-facet.package-module.md +85 -0
- package/dist/knowledge/references/example.provider.frontend-file-picker.contribution.md +14 -13
- package/dist/knowledge/references/example.provider.frontend-file-picker.module.md +18 -0
- package/dist/knowledge/references/example.provider.operation.backend-typed-client.md +11 -11
- package/dist/knowledge/references/example.rate-limit.resource-operation-surface.md +5 -0
- package/dist/knowledge/references/example.resource.add-resource.module-factory-map.md +2 -0
- package/dist/knowledge/references/example.resource.retention-binding.closure-event.md +21 -0
- package/dist/knowledge/references/example.resource.ui-behavior.enum-badge.md +1 -2
- package/dist/knowledge/references/example.resource.ui-behavior.operation-icon.md +24 -6
- package/dist/knowledge/references/example.resource.ui-behavior.surface-decision.md +36 -25
- package/dist/knowledge/references/example.resource.work-unit.declaration.md +13 -0
- package/dist/knowledge/references/example.spec.composite-view.workspace.md +0 -12
- package/dist/knowledge/references/example.views.app-level.composite-views-config.md +1 -1
- package/dist/knowledge/references/example.views.chart-view.resource-owned.md +27 -0
- package/dist/knowledge/references/example.views.composite-view.workspace.md +4 -1
- package/dist/knowledge/references/example.website.page.manifest.md +30 -0
- package/dist/knowledge/references/experience-plan.config.md +11 -4
- package/dist/knowledge/references/external-connectors.app.frontend-provider-module.md +20 -0
- package/dist/knowledge/references/external-connectors.backend.provider-augmentation.md +75 -0
- package/dist/knowledge/references/external-connectors.frontend-provider-component-declaration.md +85 -0
- package/dist/knowledge/references/external-connectors.frontend-provider-consent-classification.md +52 -0
- package/dist/knowledge/references/external-connectors.models.connection-rate-budgets.md +113 -0
- package/dist/knowledge/references/external-connectors.models.file-storage-adapter.md +165 -0
- package/dist/knowledge/references/external-connectors.models.oauth2-audiences.md +133 -0
- package/dist/knowledge/references/external-connectors.models.oauth2-incremental-consent.md +44 -0
- package/dist/knowledge/references/external-connectors.models.rest-operation-contract.md +21 -0
- package/dist/knowledge/references/external-connectors.provider-component-load-state.md +45 -0
- package/dist/knowledge/references/external-connectors.provider-component-loader-contribution.md +32 -0
- package/dist/knowledge/references/external-connectors.provider-component-registry.md +190 -0
- package/dist/knowledge/references/external-connectors.techdoc.frontend-provider-module.md +91 -0
- package/dist/knowledge/references/external-connectors.website.frontend-provider-module.md +91 -0
- package/dist/knowledge/references/integration-plan.config.md +34 -2
- package/dist/knowledge/references/market.alternative.config.md +1 -1
- package/dist/knowledge/references/market.buying-journey.config.md +1 -1
- package/dist/knowledge/references/market.category.config.md +1 -1
- package/dist/knowledge/references/market.channel.config.md +1 -1
- package/dist/knowledge/references/market.feature-benefit.config.md +1 -1
- package/dist/knowledge/references/market.gain.config.md +1 -1
- package/dist/knowledge/references/market.icp.config.md +1 -1
- package/dist/knowledge/references/market.job.config.md +1 -1
- package/dist/knowledge/references/market.message-template.config.md +1 -1
- package/dist/knowledge/references/market.objection.config.md +1 -1
- package/dist/knowledge/references/market.pain.config.md +1 -1
- package/dist/knowledge/references/market.persona.config.md +1 -1
- package/dist/knowledge/references/market.positioning.config.md +1 -1
- package/dist/knowledge/references/market.proof.config.md +1 -1
- package/dist/knowledge/references/market.references.weighted-edges.md +7 -0
- package/dist/knowledge/references/market.tone-of-voice.config.md +1 -1
- package/dist/knowledge/references/market.trigger.config.md +1 -1
- package/dist/knowledge/references/placement-plan.config.md +7 -1
- package/dist/knowledge/references/platform.config.backing-services.md +15 -15
- package/dist/knowledge/references/platform.config.infra-provider-resolution.md +57 -57
- package/dist/knowledge/references/presets.3d.focal-plane-settings.md +45 -0
- package/dist/knowledge/references/presets.3d.frame-style-overrides.md +134 -0
- package/dist/knowledge/references/presets.3d.layout-contract.md +235 -0
- package/dist/knowledge/references/presets.3d.register-layout.md +100 -0
- package/dist/knowledge/references/presets.models.labelling.sections.md +5 -0
- package/dist/knowledge/references/presets.models.shell-region.md +47 -0
- package/dist/knowledge/references/requirements.functional-requirement.config.md +8 -0
- package/dist/knowledge/references/saas.backend.actor-execution-decision-record.md +41 -0
- package/dist/knowledge/references/saas.backend.application-initialization.assembly.md +1 -1
- package/dist/knowledge/references/saas.backend.authorization.role-ceiling.md +7 -6
- package/dist/knowledge/references/saas.backend.compliance.governed-documents-pdf-template.md +370 -0
- package/dist/knowledge/references/saas.backend.custom-operation.transactional-core.md +7 -0
- package/dist/knowledge/references/saas.backend.domain-module.md +93 -15
- package/dist/knowledge/references/saas.backend.flows-actors.autonomous-agent-declaration.md +66 -0
- package/dist/knowledge/references/saas.backend.flows-actors.autonomous-agent-schedule.md +31 -0
- package/dist/knowledge/references/saas.backend.flows-actors.function-tool.md +200 -0
- package/dist/knowledge/references/saas.backend.flows-actors.resource-write-tool.md +2 -0
- package/dist/knowledge/references/saas.backend.pdf-template.collection-definition.md +73 -0
- package/dist/knowledge/references/saas.backend.providers.connection-target-credential-resolution.md +33 -9
- package/dist/knowledge/references/saas.backend.submission-challenge.md +118 -0
- package/dist/knowledge/references/saas.backend.system-access-service.md +98 -0
- package/dist/knowledge/references/saas.backend.system-of-record-action-runner.md +73 -0
- package/dist/knowledge/references/saas.config.providers.augmentations.md +61 -0
- package/dist/knowledge/references/saas.config.providers.packages.md +59 -0
- package/dist/knowledge/references/saas.config.providers.shared-connections.md +84 -0
- package/dist/knowledge/references/saas.external-data.admin-endpoints.md +56 -2
- package/dist/knowledge/references/saas.frontend.app-level-component.configuration.md +2 -2
- package/dist/knowledge/references/saas.frontend.app-shell.building-blocks.md +253 -0
- package/dist/knowledge/references/saas.frontend.billing-context.md +25 -2
- package/dist/knowledge/references/saas.frontend.chart-view.resource-chart-data.md +92 -0
- package/dist/knowledge/references/saas.frontend.consent-based-provider-activation.md +22 -0
- package/dist/knowledge/references/saas.frontend.form-field-address.lookup-slot.md +74 -0
- package/dist/knowledge/references/saas.frontend.linked-conversations-embed.md +60 -0
- package/dist/knowledge/references/saas.frontend.navigation.operation-override.md +7 -5
- package/dist/knowledge/references/saas.frontend.notifications.publish-badge-count.md +60 -0
- package/dist/knowledge/references/saas.frontend.providers.execute-operation.md +17 -2
- package/dist/knowledge/references/saas.frontend.related-resource-embeds.md +49 -0
- package/dist/knowledge/references/saas.frontend.related-resource-sections.md +8 -1
- package/dist/knowledge/references/saas.frontend.resource-layout-templates.md +9 -0
- package/dist/knowledge/references/saas.frontend.resource-operation-frontend-config.md +100 -5
- package/dist/knowledge/references/saas.frontend.resource-ui-behavior-config.md +25 -1
- package/dist/knowledge/references/saas.frontend.settings-hub.engine-destinations.md +61 -0
- package/dist/knowledge/references/saas.market.generation-agent.md +0 -1
- package/dist/knowledge/references/saas.models.agent-work-capture-settings.md +34 -0
- package/dist/knowledge/references/saas.models.agent-work-decision-surface.md +45 -0
- package/dist/knowledge/references/saas.models.agent-work-decision-vocabulary.md +107 -0
- package/dist/knowledge/references/saas.models.agent-work-output-review.md +36 -0
- package/dist/knowledge/references/saas.models.agent-work-override-rate.md +50 -0
- package/dist/knowledge/references/saas.models.agent-work-review-config.md +24 -0
- package/dist/knowledge/references/saas.models.audit-trails.actor-attribution.md +97 -0
- package/dist/knowledge/references/saas.models.audit.trail-config.md +15 -9
- package/dist/knowledge/references/saas.models.auth.service-provider-client-authentication.md +169 -0
- package/dist/knowledge/references/saas.models.authorization.administrative-continuity-codes.md +8 -0
- package/dist/knowledge/references/saas.models.billing.catalog-vocabularies.md +54 -1
- package/dist/knowledge/references/saas.models.billing.referral-program.md +47 -0
- package/dist/knowledge/references/saas.models.config.organization-types.md +74 -0
- package/dist/knowledge/references/saas.models.config.tenant-teardown.md +31 -14
- package/dist/knowledge/references/saas.models.conversation-threads.md +242 -0
- package/dist/knowledge/references/saas.models.data-mode-read-list.md +4 -4
- package/dist/knowledge/references/saas.models.engine-capabilities.md +12 -0
- package/dist/knowledge/references/saas.models.engine-capabilities.required-provider-floor.md +5 -1
- package/dist/knowledge/references/saas.models.evaluation-dataset-export.md +39 -0
- package/dist/knowledge/references/saas.models.evaluation-export-authorization.md +38 -0
- package/dist/knowledge/references/saas.models.external-data-pipeline.md +667 -6
- package/dist/knowledge/references/saas.models.flows-actors.autonomous-agents-vocabulary.md +98 -0
- package/dist/knowledge/references/saas.models.flows-actors.human-decision-vocabulary.md +52 -0
- package/dist/knowledge/references/saas.models.flows-actors.review-calendar.md +42 -0
- package/dist/knowledge/references/saas.models.flows-actors.review-deadline-vocabulary.md +84 -0
- package/dist/knowledge/references/saas.models.flows-actors.review-deadlines-declaration.md +69 -0
- package/dist/knowledge/references/saas.models.frontend-provider-public-config-contract.md +72 -0
- package/dist/knowledge/references/saas.models.http-api-binding.md +812 -29
- package/dist/knowledge/references/saas.models.http-api-binding.rest-write-operations.md +81 -0
- package/dist/knowledge/references/saas.models.human-decision-review-marker.md +20 -0
- package/dist/knowledge/references/saas.models.inbound-channels.md +277 -0
- package/dist/knowledge/references/saas.models.inbound-email-domains.md +101 -0
- package/dist/knowledge/references/saas.models.inbound-email.md +111 -0
- package/dist/knowledge/references/saas.models.model-cost-accounting-config.md +28 -0
- package/dist/knowledge/references/saas.models.model-cost-summary.md +87 -0
- package/dist/knowledge/references/saas.models.navigation.layout.md +11 -7
- package/dist/knowledge/references/saas.models.navigation.surface-vocabulary.md +32 -23
- package/dist/knowledge/references/saas.models.navigation.transition-vocabulary.md +8 -4
- package/dist/knowledge/references/saas.models.navigation.zone-declaration.md +22 -20
- package/dist/knowledge/references/saas.models.notifications.badge-vocabularies.md +14 -0
- package/dist/knowledge/references/saas.models.notifications.targets.md +20 -12
- package/dist/knowledge/references/saas.models.notifications.user-notification-definition.md +61 -34
- package/dist/knowledge/references/saas.models.organization-unit-narrowing-containment.md +9 -0
- package/dist/knowledge/references/saas.models.organizations.service-provider-activity-feed.md +121 -0
- package/dist/knowledge/references/saas.models.organizations.service-provider-capability-grants.md +152 -0
- package/dist/knowledge/references/saas.models.organizations.service-provider-client-controls.md +49 -0
- package/dist/knowledge/references/saas.models.organizations.service-provider-relationships.md +567 -0
- package/dist/knowledge/references/saas.models.privacy.legal-holds.md +172 -0
- package/dist/knowledge/references/saas.models.privacy.provider-capability-disclosure.md +104 -0
- package/dist/knowledge/references/saas.models.privacy.retention-binding.md +103 -0
- package/dist/knowledge/references/saas.models.privacy.retention-enforcement-record.md +120 -0
- package/dist/knowledge/references/saas.models.privacy.retention-schedule.md +147 -0
- package/dist/knowledge/references/saas.models.privacy.statutory-retention-ground.md +50 -0
- package/dist/knowledge/references/saas.models.privacy.subject-data-recipients.md +388 -0
- package/dist/knowledge/references/saas.models.provider-address-lookup-contract.md +139 -0
- package/dist/knowledge/references/saas.models.provider-address-lookup-declaration.md +61 -0
- package/dist/knowledge/references/saas.models.provider-capabilities.md +34 -0
- package/dist/knowledge/references/saas.models.provider-credential-identity.md +67 -0
- package/dist/knowledge/references/saas.models.provider-usage-pricing-authority.md +139 -0
- package/dist/knowledge/references/saas.models.providers.browser-operation-policy.md +61 -0
- package/dist/knowledge/references/saas.models.providers.compliance-choice.md +98 -13
- package/dist/knowledge/references/saas.models.providers.scope-reauthorization.md +57 -0
- package/dist/knowledge/references/saas.models.resource-config.builder-parameters.md +122 -28
- package/dist/knowledge/references/saas.models.resource-config.operation-submission-challenge.md +54 -0
- package/dist/knowledge/references/saas.models.resource-config.resource-configuration.md +6 -0
- package/dist/knowledge/references/saas.models.resource-config.resources-registry.md +8 -0
- package/dist/knowledge/references/saas.models.resource-config.retention-policy.md +82 -0
- package/dist/knowledge/references/saas.models.system-of-record-actions.md +226 -0
- package/dist/knowledge/references/saas.models.system-of-record-error-codes.md +461 -0
- package/dist/knowledge/references/saas.models.systems-of-record.facet-augmentation.md +63 -0
- package/dist/knowledge/references/saas.models.systems-of-record.md +242 -7
- package/dist/knowledge/references/saas.models.work-attribution-vocabulary.md +109 -0
- package/dist/knowledge/references/saas.models.work-unit-ref.md +28 -0
- package/dist/knowledge/references/saas.public-runtime.contract.md +75 -7
- package/dist/knowledge/references/saas.specifications.assurance-document-blueprint.contract.md +20 -0
- package/dist/knowledge/references/saas.specifications.assurance-program.contract.md +106 -13
- package/dist/knowledge/references/saas.specifications.catalogs.schema-org.catalog-spec-shared.md +14 -13
- package/dist/knowledge/references/saas.specifications.catalogs.schema-org.discriminated-union.md +36 -14
- package/dist/knowledge/references/saas.specifications.catalogs.schema-org.entity-aggregate-offer.md +4 -3
- package/dist/knowledge/references/saas.specifications.catalogs.schema-org.entity-product.md +4 -4
- package/dist/knowledge/references/saas.specifications.catalogs.schema-org.entity-software-application.md +71 -0
- package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +6 -4
- package/dist/knowledge/references/saas.specifications.compliance.retention-enforcement-state.md +32 -0
- package/dist/knowledge/references/saas.specifications.governed-document-release.contract.md +14 -2
- package/dist/knowledge/references/saas.specifications.processor-register.md +77 -0
- package/dist/knowledge/references/saas.specifications.recipient-disclosures.md +71 -0
- package/dist/knowledge/references/saas.specifications.recipient-population.md +549 -0
- package/dist/knowledge/references/saas.specifications.resource-operation-spec.md +112 -45
- package/dist/knowledge/references/saas.specifications.resource-spec-config.md +13 -1
- package/dist/knowledge/references/saas.specifications.resource-spec-factory.md +17 -0
- package/dist/knowledge/references/saas.specifications.resource-spec-frontend-prose.md +16 -0
- package/dist/knowledge/references/saas.specifications.subject-data-recipients.md +98 -0
- package/dist/knowledge/references/saas.website.astro.bridge.md +32 -9
- package/dist/knowledge/references/saas.website.astro.head-renderer.md +1 -1
- package/dist/knowledge/references/saas.website.astro.label-loader.md +7 -4
- package/dist/knowledge/references/saas.website.astro.robots-renderer.md +15 -15
- package/dist/knowledge/references/saas.website.astro.site-context.md +5 -2
- package/dist/knowledge/references/saas.website.blog.bridge.md +17 -4
- package/dist/knowledge/references/saas.website.config.pricing-catalog-loader.md +61 -0
- package/dist/knowledge/references/saas.website.config.site-context-loader.md +154 -0
- package/dist/knowledge/references/saas.website.consent.banner.md +10 -10
- package/dist/knowledge/references/saas.website.design-tokens.colors.md +7 -4
- package/dist/knowledge/references/saas.website.design-tokens.radius.md +1 -1
- package/dist/knowledge/references/saas.website.factories.define-section.md +3 -3
- package/dist/knowledge/references/saas.website.page-layout.component.md +5 -2
- package/dist/knowledge/references/saas.website.pricing-offer-structured-data.md +140 -0
- package/dist/knowledge/references/saas.website.provider-component.slot.md +99 -0
- package/dist/knowledge/references/saas.website.root-config.schema.md +6 -6
- package/dist/knowledge/references/saas.website.runtime.context.md +23 -4
- package/dist/knowledge/references/saas.website.sections.definition-schema.md +14 -7
- package/dist/knowledge/references/saas.website.seo.robots-config.md +4 -3
- package/dist/knowledge/references/saas.website.structured-data.payload-shape.md +7 -5
- package/dist/knowledge/references/saas.website.submission-challenge.md +77 -0
- package/dist/knowledge/references/saas.website.use-pricing-catalog.hook.md +36 -0
- package/dist/knowledge/references/saas.website.use-runtime.hook.md +3 -2
- package/dist/knowledge/references/website-plan.config.md +39 -6
- package/dist/knowledge/references/zod.decorators.decorator-vocabulary.md +2 -1
- package/dist/knowledge/references/zod.decorators.display-edit-modes.md +21 -0
- package/dist/knowledge/references/zod.decorators.enums.frontend-handling.md +1 -2
- package/dist/knowledge/references/zod.decorators.file-schema.md +11 -10
- package/dist/knowledge/references/zod.decorators.file-vocabularies.md +7 -4
- package/dist/knowledge/references/zod.decorators.per-primitive-ui.md +8 -2
- package/dist/knowledge/references/zod.decorators.shared-structural-params.md +5 -1
- package/dist/knowledge/references/zod.decorators.structural-lifecycle-params.md +5 -1
- package/dist/knowledge/references/zod.factories.address.md +7 -7
- package/dist/knowledge/references/zod.factories.code.md +2 -2
- package/dist/knowledge/references/zod.factories.duration.md +4 -4
- package/dist/knowledge/references/zod.factories.money.md +3 -3
- package/dist/knowledge/registries/assurance-authority-bases.json +1 -1
- package/dist/knowledge/registries/framework-topics.json +1248 -54
- package/dist/knowledge/registries/playbooks.json +81 -109
- package/dist/knowledge/registries/source-tags.json +3201 -1118
- package/dist/knowledge/rules/live-context-door.md +29 -0
- package/dist/knowledge/skills/INDEX.md +27 -24
- package/dist/knowledge/skills/agent-work-review/SKILL.md +141 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-agent-work-capture-settings-api.md +38 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-agent-work-output-review-api.md +40 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-agent-work-override-rate-api.md +54 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-agent-work-review-config-api.md +28 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-agent-work-review-marker-api.md +108 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-agent-work-vocabulary-api.md +111 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-evaluation-dataset-export-api.md +43 -0
- package/dist/knowledge/skills/agent-work-review/references/framework-evaluation-export-authorization-api.md +42 -0
- package/dist/knowledge/skills/application-consumer-documentation-authoring/SKILL.md +31 -0
- package/dist/knowledge/skills/application-database-migrations/SKILL.md +1 -0
- package/dist/knowledge/skills/authorization-unit-narrowing/SKILL.md +1 -0
- package/dist/knowledge/skills/authorization-unit-narrowing/references/framework-unit-narrowing-declaration-api.md +9 -0
- package/dist/knowledge/skills/backend-addon-wiring/SKILL.md +6 -0
- package/dist/knowledge/skills/backend-addon-wiring/references/framework-backend-bootstrap-api.md +94 -16
- package/dist/knowledge/skills/backend-custom-operation/SKILL.md +21 -8
- package/dist/knowledge/skills/backend-custom-operation/references/framework-transactional-core-api.md +7 -0
- package/dist/knowledge/skills/brand-logo-authoring/SKILL.md +13 -5
- package/dist/knowledge/skills/compliance-document-authoring/SKILL.md +30 -6
- package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +160 -32
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-assurance-document-blueprint-contract.md +20 -0
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-governed-document-after-drafting.md +14 -2
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-processor-register-authoring.md +88 -0
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-provider-compliance-choice-api.md +112 -14
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-recipient-disclosures.md +209 -0
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-recipient-population.md +577 -0
- package/dist/knowledge/skills/compliance-document-authoring/references/framework-subject-data-recipients.md +549 -0
- package/dist/knowledge/skills/config-app-shell/SKILL.md +21 -0
- package/dist/knowledge/skills/config-app-shell/references/framework-app-shell-api.md +2 -2
- package/dist/knowledge/skills/config-app-shell/references/framework-app-shell-building-blocks-api.md +279 -0
- package/dist/knowledge/skills/config-app-shell/references/framework-shell-region-markers-api.md +66 -0
- package/dist/knowledge/skills/config-design-system/SKILL.md +1 -0
- package/dist/knowledge/skills/config-navigation/SKILL.md +114 -16
- package/dist/knowledge/skills/config-navigation/references/choosing-a-navigation-shape.md +314 -0
- package/dist/knowledge/skills/config-navigation/references/framework-navigation-layout-api.md +11 -7
- package/dist/knowledge/skills/config-navigation/references/framework-navigation-operation-override-api.md +29 -5
- package/dist/knowledge/skills/config-navigation/references/framework-navigation-vocabulary-api.md +40 -27
- package/dist/knowledge/skills/config-navigation/references/framework-navigation-zone-declaration-api.md +22 -20
- package/dist/knowledge/skills/config-navigation/references/how-navigation-resolves.md +112 -5
- package/dist/knowledge/skills/config-navigation/references/navigation-configuration-map.md +10 -10
- package/dist/knowledge/skills/config-navigation/references/navigation-zones.md +1 -1
- package/dist/knowledge/skills/config-saas/SKILL.md +3 -1
- package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +7 -0
- package/dist/knowledge/skills/config-saas/references/framework-audit-trail-config-api.md +21 -11
- package/dist/knowledge/skills/config-saas/references/framework-capability-resolution-api.md +5 -1
- package/dist/knowledge/skills/config-saas/references/framework-connection-target-credentials.md +59 -9
- package/dist/knowledge/skills/config-saas/references/framework-provider-capabilities-api.md +46 -0
- package/dist/knowledge/skills/config-saas/references/framework-systems-of-record-api.md +251 -12
- package/dist/knowledge/skills/config-saas-backend/SKILL.md +8 -0
- package/dist/knowledge/skills/config-saas-backend/references/framework-organization-types-api.md +81 -0
- package/dist/knowledge/skills/config-saas-backend/references/framework-tenant-teardown-api.md +37 -15
- package/dist/knowledge/skills/configure-billing/SKILL.md +64 -24
- package/dist/knowledge/skills/configure-billing/references/config-chain-and-failure-map.md +35 -2
- package/dist/knowledge/skills/configure-billing/references/example-backend-billing-enable-block.md +14 -0
- package/dist/knowledge/skills/configure-billing/references/example-backend-provider-module-shape.md +3 -0
- package/dist/knowledge/skills/configure-billing/references/framework-billing-frontend-api.md +25 -2
- package/dist/knowledge/skills/configure-billing/references/framework-product-catalog-api.md +73 -1
- package/dist/knowledge/skills/configure-billing/references/framework-referral-program.md +110 -0
- package/dist/knowledge/skills/configure-billing/references/framework-subscription-behavior-policy.md +27 -12
- package/dist/knowledge/skills/configure-coding-agent/SKILL.md +11 -2
- package/dist/knowledge/skills/configure-coding-agent/references/agent-selection.md +26 -2
- package/dist/knowledge/skills/email-add-template/SKILL.md +61 -24
- package/dist/knowledge/skills/email-add-template/references/framework-email-attachments-and-limits.md +5 -2
- package/dist/knowledge/skills/email-definition-wiring/SKILL.md +1 -0
- package/dist/knowledge/skills/email-labels-authoring/SKILL.md +2 -1
- package/dist/knowledge/skills/email-template-authoring/SKILL.md +1 -0
- package/dist/knowledge/skills/engine-component-registration/SKILL.md +1 -0
- package/dist/knowledge/skills/engine-product-definitions/SKILL.md +6 -0
- package/dist/knowledge/skills/flows-actors-a2a-exposure/SKILL.md +27 -3
- package/dist/knowledge/skills/flows-actors-autonomous-agents/SKILL.md +180 -0
- package/dist/knowledge/skills/flows-actors-autonomous-agents/references/binding-and-review.md +56 -0
- package/dist/knowledge/skills/flows-actors-autonomous-agents/references/framework-autonomous-agent-api.md +208 -0
- package/dist/knowledge/skills/flows-actors-autonomous-agents/references/framework-inbound-agents-api.md +51 -0
- package/dist/knowledge/skills/flows-actors-autonomous-agents/references/tool-posture.md +27 -0
- package/dist/knowledge/skills/flows-actors-chat-assistant/SKILL.md +31 -4
- package/dist/knowledge/skills/flows-actors-chat-assistant/examples/todo-assistant.example.md +26 -3
- package/dist/knowledge/skills/flows-actors-chat-assistant/references/framework-audit-agent-attribution-api.md +148 -0
- package/dist/knowledge/skills/flows-actors-chat-assistant/references/framework-decision-deadlines-api.md +287 -0
- package/dist/knowledge/skills/flows-actors-chat-assistant/references/framework-flows-actors-tool-api.md +202 -0
- package/dist/knowledge/skills/flows-actors-chat-assistant/references/framework-flows-actors-view-api.md +93 -15
- package/dist/knowledge/skills/flows-actors-chat-assistant/references/framework-tool-dispatch-obligations-api.md +96 -11
- package/dist/knowledge/skills/flows-actors-llm-agent-invocation/SKILL.md +2 -1
- package/dist/knowledge/skills/frontend-cdn-publish/SKILL.md +1 -0
- package/dist/knowledge/skills/frontend-component-catalog/SKILL.md +1 -0
- package/dist/knowledge/skills/frontend-component-catalog/references/framework-component-catalog.md +2 -2
- package/dist/knowledge/skills/frontend-component-catalog/references/framework-component-usage.md +14 -9
- package/dist/knowledge/skills/guidance-onboarding-authoring/SKILL.md +1 -0
- package/dist/knowledge/skills/i18n-label-generation/SKILL.md +1 -0
- package/dist/knowledge/skills/i18n-label-generation/references/framework-labelling-sections-api.md +5 -0
- package/dist/knowledge/skills/i18n-rerun-pipeline/SKILL.md +11 -9
- package/dist/knowledge/skills/i18n-rerun-pipeline/references/framework-labelling-sections-api.md +5 -0
- package/dist/knowledge/skills/i18n-translation-rerun/SKILL.md +8 -1
- package/dist/knowledge/skills/i18n-translation-rerun/references/framework-labelling-sections-api.md +5 -0
- package/dist/knowledge/skills/i18n-translation-rerun/references/translation-workflow.md +5 -0
- package/dist/knowledge/skills/inbound-channels/SKILL.md +301 -0
- package/dist/knowledge/skills/inbound-channels/references/email-channel.md +133 -0
- package/dist/knowledge/skills/inbound-channels/references/framework-inbound-channel-api.md +800 -0
- package/dist/knowledge/skills/inbound-channels/references/framework-inbound-email-api.md +222 -0
- package/dist/knowledge/skills/inbound-channels/references/framework-inbound-handler-api.md +231 -0
- package/dist/knowledge/skills/inbound-channels/references/inbound-delivery-lifecycle.md +135 -0
- package/dist/knowledge/skills/inbound-channels/references/receiving-email.md +297 -0
- package/dist/knowledge/skills/infra-environment-config/SKILL.md +150 -44
- package/dist/knowledge/skills/infra-environment-config/references/framework-backing-services-api.md +83 -74
- package/dist/knowledge/skills/layout-3d-adoption/SKILL.md +180 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/framework-3d-focal-plane-settings-api.md +53 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/framework-3d-frame-style-overrides-api.md +141 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/framework-3d-layout-contract-api.md +245 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/framework-3d-layout-registration-api.md +108 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/framework-shell-building-blocks-api.md +259 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/framework-shell-region-marker-api.md +52 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/layouts-and-transitions.md +43 -0
- package/dist/knowledge/skills/layout-3d-adoption/references/manual-adoption-and-removal.md +25 -0
- package/dist/knowledge/skills/local-environment-bootstrap/SKILL.md +32 -1
- package/dist/knowledge/skills/local-environment-bootstrap/references/local-environment-troubleshooting.md +2 -1
- package/dist/knowledge/skills/local-environment-bootstrap/references/wildo-cli-bootstrap-commands.md +36 -4
- package/dist/knowledge/skills/market-add-feature-benefit/SKILL.md +2 -1
- package/dist/knowledge/skills/market-add-feature-benefit/references/framework-feature-benefit-api.md +1 -1
- package/dist/knowledge/skills/market-alternatives/SKILL.md +3 -2
- package/dist/knowledge/skills/market-authoring-overview/SKILL.md +1 -0
- package/dist/knowledge/skills/market-authoring-overview/references/framework-market-references-api.md +7 -0
- package/dist/knowledge/skills/market-category/SKILL.md +2 -1
- package/dist/knowledge/skills/market-channels/SKILL.md +2 -1
- package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +7 -4
- package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +6 -4
- package/dist/knowledge/skills/market-generation-cli/SKILL.md +28 -13
- package/dist/knowledge/skills/market-generation-cli/references/framework-market-generation-cli.md +18 -3
- package/dist/knowledge/skills/market-icp/SKILL.md +2 -1
- package/dist/knowledge/skills/market-jobs-pains-gains/SKILL.md +4 -3
- package/dist/knowledge/skills/market-message-templates-authoring/SKILL.md +2 -1
- package/dist/knowledge/skills/market-message-templates-authoring/references/framework-message-template-api.md +1 -1
- package/dist/knowledge/skills/market-persona/SKILL.md +2 -1
- package/dist/knowledge/skills/market-positioning-authoring/SKILL.md +2 -1
- package/dist/knowledge/skills/market-positioning-authoring/references/framework-positioning-api.md +1 -1
- package/dist/knowledge/skills/market-proof-and-objection/SKILL.md +3 -2
- package/dist/knowledge/skills/market-scoring-interpretation/SKILL.md +1 -0
- package/dist/knowledge/skills/market-snapshot-validation/SKILL.md +1 -0
- package/dist/knowledge/skills/market-tone-of-voice/SKILL.md +2 -1
- package/dist/knowledge/skills/market-triggers-and-journey/SKILL.md +3 -2
- package/dist/knowledge/skills/milestones-and-celebrations/SKILL.md +1 -0
- package/dist/knowledge/skills/minion-authoring/SKILL.md +5 -1
- package/dist/knowledge/skills/model-cost-attribution/SKILL.md +143 -0
- package/dist/knowledge/skills/model-cost-attribution/references/framework-model-cost-pricing-api.md +211 -0
- package/dist/knowledge/skills/model-cost-attribution/references/framework-model-cost-summary-api.md +95 -0
- package/dist/knowledge/skills/model-cost-attribution/references/framework-work-attribution-api.md +117 -0
- package/dist/knowledge/skills/model-cost-attribution/references/framework-work-unit-api.md +677 -0
- package/dist/knowledge/skills/module-companion-exports/SKILL.md +17 -16
- package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +6 -4
- package/dist/knowledge/skills/module-registration/SKILL.md +2 -1
- package/dist/knowledge/skills/module-registration/references/framework-domain-modules-api.md +93 -15
- package/dist/knowledge/skills/module-registration/references/framework-notification-badges-api.md +86 -1
- package/dist/knowledge/skills/module-relationships/SKILL.md +3 -2
- package/dist/knowledge/skills/pdf-template-authoring/SKILL.md +34 -2
- package/dist/knowledge/skills/pdf-template-authoring/references/framework-pdf-collection-template-api.md +447 -0
- package/dist/knowledge/skills/provider-address-lookup/SKILL.md +207 -0
- package/dist/knowledge/skills/provider-address-lookup/references/framework-address-field-lookup-slot-api.md +82 -0
- package/dist/knowledge/skills/provider-address-lookup/references/framework-address-lookup-contract-api.md +214 -0
- package/dist/knowledge/skills/provider-address-lookup/references/framework-browser-operation-policy-api.md +143 -0
- package/dist/knowledge/skills/provider-address-lookup/references/google-places-setup.md +73 -0
- package/dist/knowledge/skills/provider-backend-package/SKILL.md +272 -33
- package/dist/knowledge/skills/provider-backend-package/references/framework-provider-augmentation-api.md +227 -0
- package/dist/knowledge/skills/provider-backend-package/references/framework-provider-credential-identity-api.md +101 -0
- package/dist/knowledge/skills/provider-backend-package/references/framework-provider-file-storage-adapter-api.md +245 -0
- package/dist/knowledge/skills/provider-backend-package/references/framework-provider-incremental-consent-api.md +88 -0
- package/dist/knowledge/skills/provider-backend-package/references/framework-provider-package-allow-list-api.md +111 -0
- package/dist/knowledge/skills/provider-backend-package/references/framework-provider-shared-connection-api.md +309 -0
- package/dist/knowledge/skills/provider-frontend-file-picker/SKILL.md +132 -23
- package/dist/knowledge/skills/provider-frontend-file-picker/references/framework-frontend-provider-consent-api.md +399 -0
- package/dist/knowledge/skills/provider-frontend-file-picker/references/framework-frontend-provider-module-api.md +29 -0
- package/dist/knowledge/skills/provider-frontend-file-picker/references/framework-frontend-public-config-api.md +115 -0
- package/dist/knowledge/skills/provider-frontend-file-picker/references/framework-provider-component-registry-api.md +386 -0
- package/dist/knowledge/skills/provider-frontend-module/SKILL.md +258 -0
- package/dist/knowledge/skills/provider-frontend-module/references/framework-frontend-facet-contracts-api.md +463 -0
- package/dist/knowledge/skills/provider-frontend-module/references/package-frontend-facets.md +61 -0
- package/dist/knowledge/skills/provider-operation-calls/SKILL.md +75 -24
- package/dist/knowledge/skills/provider-operation-calls/references/browser-door-answers.md +3 -3
- package/dist/knowledge/skills/provider-operation-calls/references/framework-browser-operation-policy-api.md +61 -0
- package/dist/knowledge/skills/provider-operation-calls/references/framework-connection-rate-budgets-api.md +176 -0
- package/dist/knowledge/skills/provider-operation-calls/references/framework-frontend-execute-operation-api.md +17 -2
- package/dist/knowledge/skills/provider-operation-calls/references/framework-provider-operation-executor-api.md +15 -0
- package/dist/knowledge/skills/provider-operation-calls/references/framework-provider-scope-reauthorization-api.md +127 -0
- package/dist/knowledge/skills/provider-operation-calls/references/framework-rest-operation-contract-api.md +25 -0
- package/dist/knowledge/skills/rate-limit-authoring/SKILL.md +6 -0
- package/dist/knowledge/skills/resource-add-field/SKILL.md +1 -0
- package/dist/knowledge/skills/resource-add-field/examples/add-priority-field-to-todos.example.md +1 -2
- package/dist/knowledge/skills/resource-add-field/references/framework-field-cross-layer-api.md +105 -6
- package/dist/knowledge/skills/resource-add-module/SKILL.md +1 -0
- package/dist/knowledge/skills/resource-add-module/references/framework-composition-scenarios-api.md +2 -1
- package/dist/knowledge/skills/resource-add-resource/SKILL.md +3 -0
- package/dist/knowledge/skills/resource-add-resource/references/framework-new-resource-core-config-api.md +124 -30
- package/dist/knowledge/skills/resource-config-wiring/SKILL.md +1 -0
- package/dist/knowledge/skills/resource-config-wiring/references/framework-administrative-continuity-codes-api.md +8 -0
- package/dist/knowledge/skills/resource-config-wiring/references/framework-authority-audit-interpretation.md +9 -0
- package/dist/knowledge/skills/resource-config-wiring/references/framework-collection-operation-declarations.md +17 -1
- package/dist/knowledge/skills/resource-config-wiring/references/framework-personal-data-declaration-api.md +124 -30
- package/dist/knowledge/skills/resource-config-wiring/references/framework-role-ceiling-api.md +7 -6
- package/dist/knowledge/skills/resource-config-wiring/references/framework-saas-models-resource-config-api.md +142 -34
- package/dist/knowledge/skills/resource-config-wiring/references/framework-system-access-reads-api.md +98 -0
- package/dist/knowledge/skills/resource-config-wiring/references/framework-user-notifications-api.md +86 -52
- package/dist/knowledge/skills/resource-custom-view/SKILL.md +1 -0
- package/dist/knowledge/skills/resource-custom-view/references/custom-view-contracts.md +100 -5
- package/dist/knowledge/skills/resource-external-data/SKILL.md +1026 -28
- package/dist/knowledge/skills/resource-external-data/references/declared-expressions.md +144 -0
- package/dist/knowledge/skills/resource-external-data/references/erasure-suppression.md +68 -0
- package/dist/knowledge/skills/resource-external-data/references/facet-augmentations.md +154 -0
- package/dist/knowledge/skills/resource-external-data/references/framework-external-data-pipeline-api.md +686 -11
- package/dist/knowledge/skills/resource-external-data/references/framework-http-api-binding-api.md +904 -31
- package/dist/knowledge/skills/resource-external-data/references/framework-pipeline-admin-endpoints-api.md +166 -6
- package/dist/knowledge/skills/resource-external-data/references/incremental-extraction.md +152 -0
- package/dist/knowledge/skills/resource-external-data/references/odata-v2-sources.md +60 -0
- package/dist/knowledge/skills/resource-external-data/references/outbound-pipelines.md +179 -0
- package/dist/knowledge/skills/resource-external-data/references/pipeline-destination-schema.md +1 -1
- package/dist/knowledge/skills/resource-external-data/references/provenance-cue.md +63 -0
- package/dist/knowledge/skills/resource-external-data/references/rate-budgets-and-pacing.md +122 -0
- package/dist/knowledge/skills/resource-external-data/references/read-through-writes.md +745 -0
- package/dist/knowledge/skills/resource-external-data/references/remote-references.md +85 -0
- package/dist/knowledge/skills/resource-external-data/references/rest-keyset-sources.md +85 -0
- package/dist/knowledge/skills/resource-external-data/references/system-of-record-actions.md +442 -0
- package/dist/knowledge/skills/resource-mcp-tool-exposure/SKILL.md +1 -0
- package/dist/knowledge/skills/resource-rag-source-fields/SKILL.md +1 -0
- package/dist/knowledge/skills/resource-rag-source-fields/references/framework-embeddings-capability-api.md +12 -0
- package/dist/knowledge/skills/resource-retention-binding/SKILL.md +186 -0
- package/dist/knowledge/skills/resource-retention-binding/references/framework-legal-holds-api.md +200 -0
- package/dist/knowledge/skills/resource-retention-binding/references/framework-retention-binding-api.md +111 -0
- package/dist/knowledge/skills/resource-retention-binding/references/framework-retention-enforcement-records-api.md +173 -0
- package/dist/knowledge/skills/resource-retention-binding/references/framework-retention-schedule-api.md +155 -0
- package/dist/knowledge/skills/resource-retention-binding/references/framework-statutory-retention-api.md +139 -0
- package/dist/knowledge/skills/resource-retention-binding/references/start-point-decisions.md +55 -0
- package/dist/knowledge/skills/resource-schema-authoring/SKILL.md +2 -2
- package/dist/knowledge/skills/resource-schema-authoring/examples/add-enum-field-with-ui.example.md +1 -2
- package/dist/knowledge/skills/resource-schema-authoring/references/field-type-selection.md +3 -1
- package/dist/knowledge/skills/resource-schema-authoring/references/framework-decorator-vocabulary-api.md +2 -1
- package/dist/knowledge/skills/resource-schema-authoring/references/framework-erasure-scrub-treatments-api.md +28 -0
- package/dist/knowledge/skills/resource-schema-authoring/references/framework-shared-structural-params-api.md +5 -1
- package/dist/knowledge/skills/resource-schema-authoring/references/framework-special-factories-api.md +34 -30
- package/dist/knowledge/skills/resource-schema-authoring/references/framework-zod-lifecycle-and-chainable-api.md +5 -1
- package/dist/knowledge/skills/resource-ui-behavior/SKILL.md +101 -42
- package/dist/knowledge/skills/resource-ui-behavior/references/framework-display-edit-modes-api.md +21 -0
- package/dist/knowledge/skills/resource-ui-behavior/references/framework-enum-frontend-handling-api.md +1 -2
- package/dist/knowledge/skills/resource-ui-behavior/references/framework-frontend-resource-ui-contracts-api.md +125 -6
- package/dist/knowledge/skills/resource-ui-behavior/references/framework-per-primitive-ui-api.md +8 -2
- package/dist/knowledge/skills/resource-ui-behavior/references/framework-related-resource-embeds-api.md +57 -1
- package/dist/knowledge/skills/resource-ui-behavior/references/framework-resource-layout-templates-api.md +61 -1
- package/dist/knowledge/skills/resource-ui-behavior/references/surface-decisions.md +110 -9
- package/dist/knowledge/skills/seeding-authoring/SKILL.md +1 -0
- package/dist/knowledge/skills/seeding-operations/SKILL.md +1 -0
- package/dist/knowledge/skills/service-provider-relationships/SKILL.md +455 -0
- package/dist/knowledge/skills/service-provider-relationships/references/framework-organization-types-api.md +270 -0
- package/dist/knowledge/skills/service-provider-relationships/references/framework-service-provider-activity-feed-api.md +129 -0
- package/dist/knowledge/skills/service-provider-relationships/references/framework-service-provider-capability-grants-api.md +161 -0
- package/dist/knowledge/skills/service-provider-relationships/references/framework-service-provider-client-authentication-api.md +224 -0
- package/dist/knowledge/skills/service-provider-relationships/references/framework-service-provider-relationships-api.md +576 -0
- package/dist/knowledge/skills/settings-placement-authoring/SKILL.md +1 -0
- package/dist/knowledge/skills/settings-placement-authoring/references/framework-settings-destinations-catalog.md +61 -0
- package/dist/knowledge/skills/spec-catalog-authoring/SKILL.md +43 -37
- package/dist/knowledge/skills/spec-catalog-authoring/references/catalog-spec-pattern-overview.md +15 -14
- package/dist/knowledge/skills/spec-companion-exports/SKILL.md +14 -16
- package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +6 -4
- package/dist/knowledge/skills/spec-component-update/SKILL.md +1 -0
- package/dist/knowledge/skills/spec-composite-view-update/SKILL.md +20 -21
- package/dist/knowledge/skills/spec-family-update/SKILL.md +1 -0
- package/dist/knowledge/skills/spec-feature-update/SKILL.md +1 -0
- package/dist/knowledge/skills/spec-resource-update/SKILL.md +13 -0
- package/dist/knowledge/skills/spec-resource-update/references/framework-spec-resource-contracts-api.md +158 -46
- package/dist/knowledge/skills/spec-update-after-change/SKILL.md +1 -0
- package/dist/knowledge/skills/spec-update-after-change/references/framework-spec-factory-api.md +17 -0
- package/dist/knowledge/skills/views-add-composite-view/SKILL.md +5 -1
- package/dist/knowledge/skills/views-add-custom-view/SKILL.md +1 -0
- package/dist/knowledge/skills/views-app-level/SKILL.md +2 -1
- package/dist/knowledge/skills/views-chart-authoring/SKILL.md +43 -1
- package/dist/knowledge/skills/views-chart-authoring/references/framework-resource-chart-data-api.md +102 -0
- package/dist/knowledge/skills/views-composite-authoring/SKILL.md +5 -1
- package/dist/knowledge/skills/views-composite-authoring/references/composite-embedding-checklist.md +3 -2
- package/dist/knowledge/skills/views-execution-authoring/SKILL.md +1 -0
- package/dist/knowledge/skills/website-anonymous-session/SKILL.md +29 -6
- package/dist/knowledge/skills/website-blog-authoring/SKILL.md +3 -2
- package/dist/knowledge/skills/website-blog-authoring/references/blog-adapter-api.md +17 -4
- package/dist/knowledge/skills/website-bundle-discipline/SKILL.md +23 -28
- package/dist/knowledge/skills/website-bundle-discipline/references/website-bundle-rules.md +7 -22
- package/dist/knowledge/skills/website-consent-gate-overrides/SKILL.md +167 -20
- package/dist/knowledge/skills/website-factory-advanced/SKILL.md +4 -3
- package/dist/knowledge/skills/website-inbound-contact-forms/SKILL.md +63 -6
- package/dist/knowledge/skills/website-inbound-contact-forms/references/framework-submission-challenge-api.md +275 -0
- package/dist/knowledge/skills/website-label-pack/SKILL.md +13 -5
- package/dist/knowledge/skills/website-layout-overrides/SKILL.md +6 -2
- package/dist/knowledge/skills/website-marketing-metadata-extension/SKILL.md +11 -2
- package/dist/knowledge/skills/website-navigation-authoring/SKILL.md +2 -1
- package/dist/knowledge/skills/website-page-authoring/SKILL.md +117 -33
- package/dist/knowledge/skills/website-page-authoring/references/framework-site-context-loader-api.md +164 -0
- package/dist/knowledge/skills/website-page-variants/SKILL.md +1 -0
- package/dist/knowledge/skills/website-primitive-overrides/SKILL.md +1 -0
- package/dist/knowledge/skills/website-section-contact/SKILL.md +65 -36
- package/dist/knowledge/skills/website-section-contact/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-cta/SKILL.md +32 -22
- package/dist/knowledge/skills/website-section-cta/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-faq/SKILL.md +99 -63
- package/dist/knowledge/skills/website-section-faq/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-feature-benefit-summary/SKILL.md +27 -18
- package/dist/knowledge/skills/website-section-feature-benefit-summary/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-feature-detail/SKILL.md +33 -22
- package/dist/knowledge/skills/website-section-feature-detail/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-footer-cta/SKILL.md +31 -20
- package/dist/knowledge/skills/website-section-footer-cta/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-hero/SKILL.md +65 -44
- package/dist/knowledge/skills/website-section-hero/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-pricing/SKILL.md +217 -200
- package/dist/knowledge/skills/website-section-pricing/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-section-pricing/references/framework-pricing-catalog-api.md +248 -0
- package/dist/knowledge/skills/website-section-social-proof/SKILL.md +45 -34
- package/dist/knowledge/skills/website-section-social-proof/references/define-website-section-api.md +19 -11
- package/dist/knowledge/skills/website-seo-aeo-geo/SKILL.md +8 -3
- package/dist/knowledge/skills/website-seo-aeo-geo/references/aeo-api.md +64 -34
- package/dist/knowledge/skills/website-seo-aeo-geo/references/seo-api.md +30 -25
- package/dist/knowledge/skills/worker-authoring/SKILL.md +1 -0
- package/dist/knowledge/topic-index.json +5957 -1729
- package/dist/tsconfig.build.tsbuildinfo +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/package.json +4 -4
- package/dist/knowledge/skills/journey-approve/SKILL.md +0 -63
- package/dist/knowledge/skills/journey-bootstrap-scope/SKILL.md +0 -77
- package/dist/knowledge/skills/journey-next/SKILL.md +0 -82
- package/dist/knowledge/skills/journey-report/SKILL.md +0 -56
- package/dist/knowledge/skills/journey-run/SKILL.md +0 -140
- package/dist/knowledge/skills/journey-status/SKILL.md +0 -60
- /package/dist/{knowledge/skills/journey-approve → claude-marketplace/plugins/wildo}/references/specification-family-map.md +0 -0
|
@@ -162,6 +162,17 @@ export enum BuildPlanTaskTargetKind {
|
|
|
162
162
|
* may touch are the same for every provider.
|
|
163
163
|
*/
|
|
164
164
|
PROVIDER_BINDING = 'PROVIDER_BINDING',
|
|
165
|
+
/**
|
|
166
|
+
* The application's BILLING CATALOGUE — the `ProductDefinition[]` in `shared-lib/src/engine/product.ts`
|
|
167
|
+
* (and the product specifications that document it), which the backend syncs to the billing
|
|
168
|
+
* provider and the public website reads for its pricing page (#1835).
|
|
169
|
+
*
|
|
170
|
+
* Its own kind because none of the others is true of it: the catalogue is application-wide (a plan
|
|
171
|
+
* belongs to no module), it lives in the shared library's ENGINE module that no `MODULE_*` scope
|
|
172
|
+
* reaches, and before it existed a journey-built application reached its website with an EMPTY
|
|
173
|
+
* catalogue, so the website re-typed the business model's prices by hand.
|
|
174
|
+
*/
|
|
175
|
+
BILLING_CATALOG = 'BILLING_CATALOG',
|
|
165
176
|
}
|
|
166
177
|
|
|
167
178
|
/**
|
|
@@ -244,6 +255,13 @@ export enum BuildPlanResourceStage {
|
|
|
244
255
|
|
|
245
256
|
const SlugSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);
|
|
246
257
|
|
|
258
|
+
/**
|
|
259
|
+
* The key of the domain-plan MODULE a task targets or produces (`deals`, `tasks-manager`). Same
|
|
260
|
+
* slug grammar as the other keys, declared as its own schema because it names one thing — a
|
|
261
|
+
* module — where the other slugs name resources, relationships, steps, workers and products.
|
|
262
|
+
*/
|
|
263
|
+
const ModuleRefSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);
|
|
264
|
+
|
|
247
265
|
/**
|
|
248
266
|
* The governed document a task produces, named as a COMPLIANCE-DOCUMENT CANDIDATE names it:
|
|
249
267
|
* `document:<namespace>.<id>`, e.g. `document:public.privacy-notice`.
|
|
@@ -392,6 +410,15 @@ export enum BuildPlanTaskProductKind {
|
|
|
392
410
|
APPLICATION_MINION = 'APPLICATION_MINION',
|
|
393
411
|
/** One provider declared in one runtime owner's scope. */
|
|
394
412
|
PROVIDER_BINDING = 'PROVIDER_BINDING',
|
|
413
|
+
/**
|
|
414
|
+
* One product of the application's billing catalogue — a plan, add-on or purchase the application
|
|
415
|
+
* sells — named by its catalogue `key`, which the catalogue file declares (`key: 'team'`).
|
|
416
|
+
*
|
|
417
|
+
* The KEY, not the file: `wildo init` writes `product.ts` with an empty catalogue, so the file proves
|
|
418
|
+
* nothing. Written from the accepted business model's pricing plans, with the plan's price as typed
|
|
419
|
+
* money and the pricing-surface facts (recommended, price disclosure, availability) the plan implies.
|
|
420
|
+
*/
|
|
421
|
+
APPLICATION_BILLING_PRODUCT = 'APPLICATION_BILLING_PRODUCT',
|
|
395
422
|
/** One website page, registered in the website root config by its manifest. */
|
|
396
423
|
WEBSITE_PAGE = 'WEBSITE_PAGE',
|
|
397
424
|
/** One section of one website page, declared in that page's sections file. */
|
|
@@ -401,6 +428,13 @@ export enum BuildPlanTaskProductKind {
|
|
|
401
428
|
* for the documentation portal to publish (#874's publication input).
|
|
402
429
|
*/
|
|
403
430
|
DOCUMENTATION_CHAPTER = 'DOCUMENTATION_CHAPTER',
|
|
431
|
+
/**
|
|
432
|
+
* One inbound CHANNEL handler — the code that decides what a message arriving on a channel causes
|
|
433
|
+
* (#1832). Named by the handler's `ref` (`matters.mail-intake`), which the handler file spells and whose
|
|
434
|
+
* file NAME is derived from it, so the module index's import of that file is what proves the handler is
|
|
435
|
+
* registered. Produced once per channel the integration plan declares (`inboundChannels`).
|
|
436
|
+
*/
|
|
437
|
+
INBOUND_CHANNEL_HANDLER = 'INBOUND_CHANNEL_HANDLER',
|
|
404
438
|
}
|
|
405
439
|
|
|
406
440
|
/**
|
|
@@ -440,7 +474,7 @@ export const BuildPlanTaskProductSchema = z.discriminatedUnion('kind', [
|
|
|
440
474
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_OPERATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, operationRef: SlugSchema }),
|
|
441
475
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_VIEW).systemEnum('BuildPlanTaskProductKind'), viewRef: SlugSchema }),
|
|
442
476
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_DOCUMENT).systemEnum('BuildPlanTaskProductKind'), documentRef: DocumentProductRefSchema }),
|
|
443
|
-
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MODULE).systemEnum('BuildPlanTaskProductKind'), moduleRef:
|
|
477
|
+
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MODULE).systemEnum('BuildPlanTaskProductKind'), moduleRef: ModuleRefSchema }),
|
|
444
478
|
z.strictObject({
|
|
445
479
|
kind: z.literal(BuildPlanTaskProductKind.APPLICATION_FRONTEND_CONFIG).systemEnum('BuildPlanTaskProductKind'),
|
|
446
480
|
configSurface: z.enum(FrontendConfigSurface).systemEnum('FrontendConfigSurface'),
|
|
@@ -471,9 +505,17 @@ export const BuildPlanTaskProductSchema = z.discriminatedUnion('kind', [
|
|
|
471
505
|
providerRef: SlugSchema,
|
|
472
506
|
scope: z.enum(ProviderBindingScope).systemEnum('ProviderBindingScope'),
|
|
473
507
|
}),
|
|
508
|
+
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_BILLING_PRODUCT).systemEnum('BuildPlanTaskProductKind'), productKey: SlugSchema }),
|
|
474
509
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_PAGE).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema }),
|
|
475
510
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_SECTION).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema, sectionRef: SlugSchema }),
|
|
476
511
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER).systemEnum('BuildPlanTaskProductKind'), chapterRef: SlugSchema }),
|
|
512
|
+
z.strictObject({
|
|
513
|
+
kind: z.literal(BuildPlanTaskProductKind.INBOUND_CHANNEL_HANDLER).systemEnum('BuildPlanTaskProductKind'),
|
|
514
|
+
/** The channel the handler serves — one the integration plan declared. Email is the only declarable channel. */
|
|
515
|
+
channel: z.literal(InboundChannelKind.EMAIL).systemEnum('InboundChannelKind'),
|
|
516
|
+
/** The handler's `ref`, exactly as `inboundHandlerRef()` will accept it. */
|
|
517
|
+
handlerRef: z.string().regex(INBOUND_HANDLER_REF_PATTERN),
|
|
518
|
+
}),
|
|
477
519
|
]);
|
|
478
520
|
export type BuildPlanTaskProduct = z.infer<typeof BuildPlanTaskProductSchema>;
|
|
479
521
|
|
|
@@ -544,12 +586,16 @@ export function buildPlanTaskProductIdentities(product: BuildPlanTaskProduct): r
|
|
|
544
586
|
// The SCOPE is part of the identity: one provider bound on the backend and on the website is two artifacts.
|
|
545
587
|
case BuildPlanTaskProductKind.PROVIDER_BINDING:
|
|
546
588
|
return [`${product.kind}:${product.scope}:${product.providerRef}`];
|
|
589
|
+
case BuildPlanTaskProductKind.APPLICATION_BILLING_PRODUCT:
|
|
590
|
+
return [`${product.kind}:${product.productKey}`];
|
|
547
591
|
case BuildPlanTaskProductKind.WEBSITE_PAGE:
|
|
548
592
|
return [`${product.kind}:${product.pageRef}`];
|
|
549
593
|
case BuildPlanTaskProductKind.WEBSITE_SECTION:
|
|
550
594
|
return [`${product.kind}:${product.pageRef}:${product.sectionRef}`];
|
|
551
595
|
case BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER:
|
|
552
596
|
return [`${product.kind}:${product.chapterRef}`];
|
|
597
|
+
case BuildPlanTaskProductKind.INBOUND_CHANNEL_HANDLER:
|
|
598
|
+
return [`${product.kind}:${product.handlerRef}`];
|
|
553
599
|
default: {
|
|
554
600
|
const unhandled: never = product;
|
|
555
601
|
throw new Error(`Unhandled build-plan task product ${JSON.stringify(unhandled)}.`);
|
|
@@ -557,17 +603,25 @@ export function buildPlanTaskProductIdentities(product: BuildPlanTaskProduct): r
|
|
|
557
603
|
}
|
|
558
604
|
}
|
|
559
605
|
|
|
606
|
+
/**
|
|
607
|
+
* The skill every billing-catalogue task is authored with (#1835): the product-catalogue contract, the
|
|
608
|
+
* money encoding (minor units), and the pricing-surface facts. The dispatch derives it from an
|
|
609
|
+
* `APPLICATION_BILLING_PRODUCT` product whatever the decomposer wrote, so an agent writing the catalogue
|
|
610
|
+
* the backend sells from is never without it.
|
|
611
|
+
*/
|
|
612
|
+
export const BILLING_CATALOG_SKILL_REF = 'configure-billing';
|
|
613
|
+
|
|
560
614
|
export const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [
|
|
561
|
-
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE), moduleRef:
|
|
615
|
+
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE), moduleRef: ModuleRefSchema }),
|
|
562
616
|
z.strictObject({
|
|
563
617
|
kind: z.literal(BuildPlanTaskTargetKind.RESOURCE_STAGE),
|
|
564
|
-
moduleRef:
|
|
618
|
+
moduleRef: ModuleRefSchema,
|
|
565
619
|
resourceRef: SlugSchema,
|
|
566
620
|
stage: z.enum(BuildPlanResourceStage),
|
|
567
621
|
}),
|
|
568
622
|
z.strictObject({
|
|
569
623
|
kind: z.literal(BuildPlanTaskTargetKind.RELATIONSHIP),
|
|
570
|
-
moduleRef:
|
|
624
|
+
moduleRef: ModuleRefSchema,
|
|
571
625
|
relationshipRef: SlugSchema,
|
|
572
626
|
}),
|
|
573
627
|
z.strictObject({
|
|
@@ -593,8 +647,8 @@ export const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [
|
|
|
593
647
|
*/
|
|
594
648
|
surface: z.enum(PlacementSurface).systemEnum('PlacementSurface'),
|
|
595
649
|
}),
|
|
596
|
-
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_FRONTEND), moduleRef:
|
|
597
|
-
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_BACKEND), moduleRef:
|
|
650
|
+
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_FRONTEND), moduleRef: ModuleRefSchema }),
|
|
651
|
+
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_BACKEND), moduleRef: ModuleRefSchema }),
|
|
598
652
|
z.strictObject({
|
|
599
653
|
kind: z.literal(BuildPlanTaskTargetKind.APPLICATION_FRONTEND_CONFIG),
|
|
600
654
|
configSurface: z.enum(FrontendConfigSurface).systemEnum('FrontendConfigSurface'),
|
|
@@ -613,6 +667,7 @@ export const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [
|
|
|
613
667
|
minionRef: SlugSchema,
|
|
614
668
|
}),
|
|
615
669
|
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.PROVIDER_BINDING), providerRef: SlugSchema }),
|
|
670
|
+
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.BILLING_CATALOG) }),
|
|
616
671
|
]);
|
|
617
672
|
export type BuildPlanTaskTarget = z.infer<typeof BuildPlanTaskTargetSchema>;
|
|
618
673
|
|
|
@@ -694,6 +749,16 @@ export const BuildPlanTaskSchema = z.strictObject({
|
|
|
694
749
|
* unresolved instead, which is what makes a producer drift legible rather than silent.
|
|
695
750
|
*/
|
|
696
751
|
servesRefs: z.array(NonEmptyStringSchema).default([]),
|
|
752
|
+
/**
|
|
753
|
+
* Who asked for this task DIRECTLY (#1608), rather than it being derived from the specifications: the
|
|
754
|
+
* signed-in person who added it in conversation. STAMPED by the append, never authored: a value in
|
|
755
|
+
* generated output is discarded. Absent on every task the decomposition derived.
|
|
756
|
+
*
|
|
757
|
+
* It is what keeps a requested task alive. Build decomposition refines the plan from the domain plan, and
|
|
758
|
+
* a task nothing in the specifications justifies would read as unjustified and be dropped; a requested
|
|
759
|
+
* task it leaves out is carried forward instead, keeping only the prerequisites the new plan still holds.
|
|
760
|
+
*/
|
|
761
|
+
requestedBy: NonEmptyStringSchema.optional(),
|
|
697
762
|
});
|
|
698
763
|
export type BuildPlanTask = z.infer<typeof BuildPlanTaskSchema>;
|
|
699
764
|
|
|
@@ -809,8 +874,8 @@ own composition and change-set capture.
|
|
|
809
874
|
This playbook is **idempotent** and, on a re-run, *advances the loop by one task*.
|
|
810
875
|
Before dispatching anything:
|
|
811
876
|
|
|
812
|
-
1. Read the current journey state and scope
|
|
813
|
-
|
|
877
|
+
1. Read the current journey state and scope from what this run is given — the loaded
|
|
878
|
+
specifications and the workspace sections of your brief — and do not re-derive it. Confirm the **build plan** is present
|
|
814
879
|
and approved, and confirm the **foundation** ran. For each build-plan task,
|
|
815
880
|
determine its dispatch state from its task row — **not yet dispatched**,
|
|
816
881
|
**dispatched-and-succeeded** (a captured change-set + a passed verify), or
|
|
@@ -922,8 +987,8 @@ The single-flight mutation lock still applies to the current shared workspace.
|
|
|
922
987
|
The playbook's `approval` declaration and the journey autonomy presets express policy
|
|
923
988
|
intent. The current playbook runner does not interpret them as pre-dispatch gates,
|
|
924
989
|
automatic authorization, or a GUIDED/YOLO mapping. A declared `approve_before` does
|
|
925
|
-
not create a pending Authority Request
|
|
926
|
-
|
|
990
|
+
not create a pending Authority Request, and no authority workflow exists to create one —
|
|
991
|
+
never invent one from an enum.
|
|
927
992
|
|
|
928
993
|
Likewise, do not infer enforced per-playbook or per-journey run ceilings from declared
|
|
929
994
|
budget fields. Respect the limits actually reported by the execution host. Inspect the
|
|
@@ -931,7 +996,7 @@ recorded changes and verification result after each task; no preset commits or a
|
|
|
931
996
|
|
|
932
997
|
## Step 3 — Dispatch the task through the coding-agent contract
|
|
933
998
|
|
|
934
|
-
|
|
999
|
+
The companion triggers the run (from a console, `wildo build run` or `/wildo:build`). The runner then performs the D4
|
|
935
1000
|
dispatch contract for you (you do not hand-assemble any of it):
|
|
936
1001
|
|
|
937
1002
|
1. **Context pack** — the runner composes the prompt: the task brief, the task's
|
|
@@ -961,12 +1026,9 @@ dispatch contract for you (you do not hand-assemble any of it):
|
|
|
961
1026
|
dirty-at-dispatch is the NORMAL state (parallel sessions), so the capture
|
|
962
1027
|
*attributes* rather than assuming the run had the tree to itself.
|
|
963
1028
|
|
|
964
|
-
// The trigger is
|
|
965
|
-
//
|
|
966
|
-
// runs one ACP prompt turn, and captures the change-set.
|
|
967
|
-
// That route is MUTATING, so the call must carry `x-wildo-companion-token`, read from
|
|
968
|
-
// `./.wildo-saas/state/companion.token` (mode 0600). Without it the companion answers `401` with a
|
|
969
|
-
// body that names nothing — the explanation is in the companion's own log.
|
|
1029
|
+
// The trigger is `wildo creation run <playbookRef>` or `wildo build run` (from a Claude Code session,
|
|
1030
|
+
// `/wildo:run` or `/wildo:build`), or the workbench; each reaches the companion with its local token.
|
|
1031
|
+
// The runner composes the typed context pack, runs one ACP prompt turn, and captures the change-set.
|
|
970
1032
|
|
|
971
1033
|
## Step 4 — Verify OUTSIDE the coding agent
|
|
972
1034
|
|
|
@@ -1019,9 +1081,9 @@ resolved. This playbook does not auto-retry a failed task — automated retry /
|
|
|
1019
1081
|
is a deferred build-loop-resilience concern, and human triage is the v1 disposition;
|
|
1020
1082
|
here the loop simply surfaces the failure and stops advancing that dependency chain.
|
|
1021
1083
|
|
|
1022
|
-
Then **loop**: on the next run of this playbook,
|
|
1023
|
-
just-dispatched task's outcome, and you select the next ready task
|
|
1024
|
-
significant stretch of dispatches with a
|
|
1084
|
+
Then **loop**: on the next run of this playbook, the build plan's task records reflect the
|
|
1085
|
+
just-dispatched task's outcome (`wildo build tasks`), and you select the next ready task
|
|
1086
|
+
(Step 1). Close a significant stretch of dispatches with a progress summary — what was
|
|
1025
1087
|
produced, which change-sets landed, what verify said, and any failed task left
|
|
1026
1088
|
flagged for triage.
|
|
1027
1089
|
|
|
@@ -1082,15 +1144,8 @@ one verified task at a time, until the build plan is fully dispatched.
|
|
|
1082
1144
|
|
|
1083
1145
|
## References
|
|
1084
1146
|
|
|
1085
|
-
-
|
|
1086
|
-
|
|
1087
|
-
see which tasks already dispatched.
|
|
1088
|
-
- `.claude/skills/journey-run/references/framework-playbook-approval-policy.md` — declaration semantics and the actual runner boundary.
|
|
1089
|
-
- `.claude/skills/journey-run/SKILL.md` — trigger the dispatch and monitor it; the
|
|
1090
|
-
runner composes the context pack, runs one prompt turn against the coding agent in
|
|
1091
|
-
the app workspace, captures the change-set, and runs the verify hook.
|
|
1092
|
-
- `.claude/skills/journey-report/SKILL.md` — summarize a stretch of dispatches:
|
|
1093
|
-
what was produced, which change-sets landed, and what the verify gates said.
|
|
1147
|
+
- A playbook's declared `approval` and failure policy gate nothing on a leaf run; they are read only
|
|
1148
|
+
at a composite lane's boundary, where they frame a decision for the person and revert nothing.
|
|
1094
1149
|
|
|
1095
1150
|
## Reviewer checklist — `dispatch-outcome-sound`
|
|
1096
1151
|
|
|
@@ -19,13 +19,8 @@
|
|
|
19
19
|
"outputs": [],
|
|
20
20
|
"stepOutputs": [],
|
|
21
21
|
"method": {
|
|
22
|
-
"guidance": "# Build Dispatch — One Build-Plan Task → One Verified Coding-Agent Run (v1 scaffold)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is a v1 scaffold methodology.** It is a working first cut of the\n> *single-flight* dispatch contract — dispatch exactly ONE build-plan task at a\n> time, capture its change-set, verify it outside the coding agent, record it, and\n> apply the failure disposition. The context-pack shape, the verify gate, and the\n> failure-handling below are deliberately explicit so they can be tuned against real\n> runs. Multi-agent parallelism, a concurrency scheduler, a run-completion\n> serializer, and a `revert_changeset` failure path are a **later phase** — do not\n> build them here (see the boundary section).\n\n## Where you are in the journey\n\nThis is the **second build-execution playbook** — the pivot from **decomposing the\nbuild** (the build-plan: the ordered coding-agent task graph) to **dispatching it**\n(turning one ordered task into an actually-run, verified coding-agent run). It runs\nin the **bottom-up phase**, after the build plan exists (`artifact_exists\nbuild-plan`) and the foundation step has authored the app's config and skeleton.\nYou are not re-opening the decomposition\nhere — you are turning one *approved, ordered* task into a *dispatched, verified*\nchange to the application.\n\nUpstream, the **build-decompose** playbook produced the ordered task graph you\nconsume; downstream, the **scale** playbook generalises this single-flight contract\nto many concurrent coding agents and interleaves the companion generation steps.\n**You author neither of those concerns** — see the boundary section.\n\n## The typed task you dispatch\n\nThe build plan is a typed family (`BuildPlanTaskGraph`): dispatch selects ONE\nREADY task (all declared prerequisite task refs have landed) and hands the\ncoding host exactly that task's `objective`, `target`, `produces`,\n`functionalTopic` and `skillRefs`. The host derives the physical\nallowed/prohibited paths and the fixed verification from the target kind;\nnothing in the task — and nothing in this method prose — authors a path, a\ncommand, a prompt or a runtime control.\n\n`target` and `produces` answer two different questions, and a task needs both.\n`target` is the WRITE SCOPE — where this run may edit, and several tasks\nlegitimately share one. `produces` is what the run is ACCOUNTABLE for: the\nartifacts whose presence in the application proves the task done. A task has\nlanded when every artifact it declares is present and committed, so a run that\nsatisfies the objective's prose without delivering those artifacts is not\nfinished — the plan will offer the task again.\n\n## Import Origins\n\n- `@wildo-ai/saas-specifications`\n\n## Source Excerpts\n\n### Origin Package: `@wildo-ai/saas-specifications`\n\n```typescript\n *\n * Versioning for the build-plan task-graph payload format itself. `V1` —\n * initial shape (one ordered `tasks` collection with typed targets and\n * declared prerequisites). The shape grows additively across versions; the\n * `version` field is the explicit marker for consumers that branch on era.\n */\nexport enum BuildPlanTaskGraphVersion {\n V1 = 'v1',\n}\n\n/** Stable prefix every build-plan task ref carries; the trusted runtime stamps it, a provider supplies only the slug. */\nexport const BUILD_PLAN_TASK_REF_PREFIX = 'build-task-';\n\n/**\n * WHAT a build task builds — a closed vocabulary, because the host derives\n * the physical mutation scope and verification policy from the target kind\n * and the model must never author those powers through free text.\n */\nexport enum BuildPlanTaskTargetKind {\n /** A whole application module (its shared-lib registration, backend module and frontend module skeletons). */\n MODULE = 'MODULE',\n /** One build stage of one resource: schema → config → ui-behavior → spec. */\n RESOURCE_STAGE = 'RESOURCE_STAGE',\n /** One relationship between two resources. */\n RELATIONSHIP = 'RELATIONSHIP',\n /** A companion-owned deterministic generation step (labels, email templates, logo or database migrations) interleaved by the build loop, never a coding-agent run. */\n COMPANION_GENERATION_STEP = 'COMPANION_GENERATION_STEP',\n /**\n * Authoring one SHELL SURFACE's placement configuration from the accepted\n * placement plan — the settings rail, the sidebar, the user menu or the\n * command palette.\n *\n * Its own kind rather than a reuse of the neighbours, because none of them is\n * true of it: it is not a MODULE or a RESOURCE_STAGE (it is application-wide\n * and belongs to no resource), not a RELATIONSHIP, and emphatically not a\n * COMPANION_GENERATION_STEP — that kind is documented as \"never a coding-agent\n * run\" and writing `settings-hub.config.ts` is exactly a coding-agent run.\n * Borrowing one would hand the host the wrong mutation scope and the wrong\n * verification, which is what the closed vocabulary exists to prevent.\n */\n SHELL_PLACEMENT = 'SHELL_PLACEMENT',\n /*\n * THE NON-RESOURCE SURFACES (#1490). Until 2026-09-22 the five kinds above were the whole\n * vocabulary, and every one of them is about a resource or the shell placement of one. The\n * decompose method meanwhile told the planner to emit tasks for views, navigation, the design\n * system, custom components, PDF templates, workers, minions, providers, the website and the\n * documentation — surfaces the framework's own composition scenarios and 85 of its 111 skills\n * already build. A task for any of them had no kind to declare, so it either declared none\n * (landing as RAN-not-PROVEN forever) or borrowed `MODULE` with a product the module scope could\n * not prove. The members below are those surfaces, one per write scope the host can derive.\n */\n /**\n * The FRONTEND and SPECIFICATION layers of one module — its composite, custom and chart views,\n * its custom components and their specifications.\n *\n * Narrower than `MODULE` on purpose: a view task never touches `shared-lib` or `backend-api`, so\n * handing it the four-layer scope also hands it four typechecks and the FK sweep for a change\n * that can only break the frontend and the specifications package.\n */\n MODULE_FRONTEND = 'MODULE_FRONTEND',\n /**\n * The BACKEND layer of one module beside its shared-lib declarations — PDF templates and their\n * bindings, backend addons (services, controllers, flows-actors), email definitions.\n *\n * Shared-lib is in scope because a PDF template is bound to a resource FIELD the config declares\n * (`generatedSummaryPdf`), and a backend addon usually declares its contract there first.\n */\n MODULE_BACKEND = 'MODULE_BACKEND',\n /**\n * ONE application-wide frontend configuration surface — navigation, the design system, the app\n * shell's composition, the global views — named by {@link FrontendConfigSurface}.\n *\n * Distinct from {@link SHELL_PLACEMENT}, which authors the placement plan's decisions into the\n * shell files: a placement puts a decided subject in a decided group, while this kind COMPOSES\n * the surface itself (which sidebar sections exist, which transitions the primary zone uses,\n * which palette the product carries). Same file for `APP_SHELL`, different question.\n */\n APPLICATION_FRONTEND_CONFIG = 'APPLICATION_FRONTEND_CONFIG',\n /** The marketing website workspace (`website/`), composed by the `add-website` scenario. Pages and sections are its products. */\n WEBSITE = 'WEBSITE',\n /**\n * The technical-documentation workspace (`technical-doc/`) and the specification package's\n * `technical-documentation/` declarations that feed it. Its generated tree is never written by a\n * task: the companion publishes into it, and the coding policy prohibits it by prefix.\n */\n TECHNICAL_DOCUMENTATION = 'TECHNICAL_DOCUMENTATION',\n /** One worker package (`workers/<workerRef>/`), Node or Rust, plus its declaration in the SaaS config. */\n WORKER = 'WORKER',\n /** One cron minion package (`minions/<minionRef>/`) plus its declaration in the SaaS config. */\n MINION = 'MINION',\n /**\n * Declaring one provider in the application — the SaaS config's provider scopes, the backend\n * package dependency, the frontend provider module and its companion contribution.\n *\n * Application-wide by construction: a provider binding names no module, and the four files it\n * may touch are the same for every provider.\n */\n PROVIDER_BINDING = 'PROVIDER_BINDING',\n}\n\n/**\n * WHICH application-wide frontend configuration surface a task composes — one file each, in\n * `frontend/src/config/`, and the coding policy resolves the member to that file exactly as\n * `SHELL_PLACEMENT` resolves a `PlacementSurface`.\n *\n * Its own vocabulary rather than a reuse of `PlacementSurface`: a placement surface is WHERE a\n * subject sits in the shell (settings hub, sidebar, user menu, command palette), and three of\n * those live in one file. A configuration surface is WHICH FILE a composition task authors, and\n * navigation and the design system are not places anything is placed.\n */\nexport enum FrontendConfigSurface {\n /** `frontend/src/config/navigation.config.ts` — zones, transitions, overlay appearance. */\n NAVIGATION = 'NAVIGATION',\n /** `frontend/src/config/design-system.config.ts` — palette, typography, shell appearance from the brand's visual tone. */\n DESIGN_SYSTEM = 'DESIGN_SYSTEM',\n /** `frontend/src/config/app-shell.config.ts` — top bar, sidebar sections, quick switcher: the shell's COMPOSITION, not a placement into it. */\n APP_SHELL = 'APP_SHELL',\n /** `frontend/src/config/global-views.config.ts` — the application-level launcher and view registrations. */\n GLOBAL_VIEWS = 'GLOBAL_VIEWS',\n}\n\n/**\n * The two shapes of guidance an application gives a person, and the file each is declared in.\n *\n * They are distinct because they are found differently: an onboarding DOCUMENT is embedded in a\n * screen (`EmbedOnboarding`) and is there whenever that screen is, while a guidance FLOW is started\n * by an event and shows once. Both are listed on the owning frontend module — `onboardingViews` and\n * `guidanceFlows`. Each kind has a CONVENTIONAL definitions file, which the authoring skill teaches\n * and a landing probe reads for the declared ref (alongside the module's `index.ts`, where a small\n * module may declare inline). A convention for generated applications: a hand-authored application\n * may keep its declarations elsewhere, and then simply is not probed by a build plan.\n */\nexport enum ApplicationGuidanceKind {\n /** `frontend/src/modules/<m>/app-level-views/onboarding-views.definitions.ts` — an embedded onboarding document. */\n ONBOARDING_DOCUMENT = 'ONBOARDING_DOCUMENT',\n /** `frontend/src/modules/<m>/app-level-views/guidance-flows.definitions.ts` — a triggered guidance flow. */\n GUIDANCE_FLOW = 'GUIDANCE_FLOW',\n}\n\n/**\n * The two worker runtimes the framework composes (`add-worker-node`, `add-worker-rust`). The\n * runtime decides the entry file a landing probe reads and whether a typecheck exists to run: a\n * Node worker is verified by its package typecheck, a Rust worker has no TypeScript to check and\n * the policy says so rather than inventing a command.\n *\n * Not the SaaS config's `WorkerRuntime`, which is a free-form `{ type, language }` pair an\n * application authors for deployment; this is the closed set a creation run can COMPOSE.\n */\nexport enum BuildPlanWorkerRuntime {\n NODE = 'NODE',\n RUST = 'RUST',\n}\n\n/**\n * WHERE a provider is bound — which runtime owner's scope its declaration lands in. Each member\n * is a different file, so a probe and a write grant both derive from it.\n *\n * Named after the SaaS config's own scope keys (`providers.scopes.backend`, `.companion`,\n * `.frontendServices.app`, `.frontendServices.website`), which the `add-provider` and\n * `add-file-picker-provider` scenarios write. Minion and worker scopes are deliberately absent:\n * a provider reaching a minion is declared on that minion's own `providers` block and belongs to\n * the {@link BuildPlanTaskTargetKind.MINION} task that builds it.\n */\nexport enum ProviderBindingScope {\n BACKEND = 'BACKEND',\n COMPANION = 'COMPANION',\n FRONTEND_APP = 'FRONTEND_APP',\n WEBSITE = 'WEBSITE',\n}\n\n/** The per-resource build stages, in their fixed order. */\nexport enum BuildPlanResourceStage {\n SCHEMA = 'SCHEMA',\n CONFIG = 'CONFIG',\n UI_BEHAVIOR = 'UI_BEHAVIOR',\n SPEC = 'SPEC',\n}\n\nconst SlugSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);\n\n/**\n * The governed document a task produces, named as a COMPLIANCE-DOCUMENT CANDIDATE names it:\n * `document:<namespace>.<id>`, e.g. `document:public.privacy-notice`.\n *\n * **This field was `SlugSchema`, and a slug cannot name a governed document — so until 2026-09-16 no\n * build plan in any application could declare a document the engine catalog defines.** A slug forbids\n * the colon and the dot, the catalog's definitions are `document-definition:public.privacy-notice`,\n * and `selectAssuranceDocumentBlueprintForDocumentRef` joins the two namespaces by exact suffix — so\n * every authored `documentRef` resolved to NO blueprint, and a blueprint is what says which sections,\n * facts and claim guards the document owes. The two vocabularies were disjoint by construction.\n *\n * The cost is measured rather than theoretical. Wonder CRM's plan declares two such products\n * (`gdpr-data-handling-governance`, `terminal-access-governance`), neither of which names anything;\n * the first was dispatched, and its agent spent a full turn establishing — with a positive control —\n * that the document does not exist and could only be invented, which the authoring skill forbids.\n *\n * The bare slug is STILL ACCEPTED, and that is deliberate rather than tidiness left undone: tightening\n * this to the namespaced form alone would make every already-accepted plan carrying one fail to parse,\n * and a build plan that cannot be READ stops the whole lane — the gate\n * `application-creation-directive.md` forbids, for a task nobody can fix by re-running anything. A slug\n * simply resolves to no blueprint, so the dispatcher skips that task with a message naming the ref,\n * and the rest of the plan proceeds.\n */\nconst DocumentProductRefSchema = z.union([\n z.string().regex(/^document:[a-z0-9]+(?:-[a-z0-9]+)*\\.[a-z0-9]+(?:-[a-z0-9]+)*$/),\n SlugSchema,\n]);\n/**\n * A skill ref is the skill's FOLDER id in the app-knowledge catalog, which is\n * also its `SKILL.md` frontmatter `name` — one id, kebab-case. The host refuses\n * any skill name outside `[a-z0-9-]+`, so a ref that does not match this shape\n * can never resolve to an installed skill.\n */\nconst SkillRefSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);\nconst NonEmptyStringSchema = z.string().trim().min(1);\n\n/**\n * WHAT a build task PRODUCES — the artifact whose presence in the application\n * proves the task is done.\n *\n * **This is not `target`, and the difference is the whole reason it exists.**\n * `target` is a WRITE SCOPE: the host turns it into the path prefixes a run may\n * mutate, and several tasks legitimately share one. `produces` is a PRODUCT\n * IDENTITY: it says which artifact this task, and no other, is accountable for.\n *\n * Measured 2026-09-10 on Wonder CRM (issue #597): `build-task-pipeline-view`\n * and `build-task-deal-follow-through-operation` carry BYTE-IDENTICAL targets\n * (`{ kind: MODULE, moduleRef: 'deals' }`), and 7 of that plan's 42 tasks share\n * 3 targets. Landing had been answered by narrowing the target to a module\n * DIRECTORY — which `wildo compose` commits on day one, and which cannot tell\n * two tasks apart even in principle. The loop reported 40 of 42 tasks landed\n * while no coding task had ever run, so `dispatch-next` skipped every one of\n * them and the phase-advance gate read a build that was all but complete.\n *\n * Like `target`, this stays SEMANTIC: a product names a resource, a field, a\n * relationship or a view — never a path, and never a command. The host owns the\n * translation from a product to the physical question it asks of the working\n * tree, exactly as it owns the translation from a target kind to path prefixes.\n * A model that could author the path could author its own mutation scope.\n */\nexport enum BuildPlanTaskProductKind {\n /**\n * Named fields on one resource's schema.\n *\n * The shape an ENRICHMENT task needs, and the reason a product cannot always\n * be \"a file\": every resource file already exists, written by the scaffold\n * with its self-described STARTER shape, so file presence answers nothing.\n * The FIELDS are what the task adds.\n */\n RESOURCE_SCHEMA_FIELDS = 'RESOURCE_SCHEMA_FIELDS',\n /**\n * One resource's declared operations — its registry presence, named by the verbs it gains.\n *\n * The VERBS, not the config file: `<r>.resources-config.ts` is written by the scaffold, so its\n * existence is satisfied before any task runs. That is the exact shape of the defect this\n * vocabulary replaces, and a kind that reproduced it would be worse than no kind at all.\n */\n RESOURCE_REGISTRATION = 'RESOURCE_REGISTRATION',\n /** One resource's frontend ui-behavior. */\n RESOURCE_UI_BEHAVIOR = 'RESOURCE_UI_BEHAVIOR',\n /**\n * One resource's specification, named by the fields it documents.\n *\n * The FIELDS, for the same reason as {@link RESOURCE_REGISTRATION}: every resource is scaffolded\n * with a `*.resource.specification.ts` documenting only the starter shape, so file existence\n * proves nothing about the task that was meant to enrich it.\n */\n RESOURCE_SPECIFICATION = 'RESOURCE_SPECIFICATION',\n /** One relationship edge between two resources, named by the domain plan's `relationshipRef`. */\n RESOURCE_RELATIONSHIP = 'RESOURCE_RELATIONSHIP',\n /** One named custom operation on one resource. */\n RESOURCE_OPERATION = 'RESOURCE_OPERATION',\n /** One named application-level view. */\n APPLICATION_VIEW = 'APPLICATION_VIEW',\n /** One named governed application document (a compliance notice, a governance statement). */\n APPLICATION_DOCUMENT = 'APPLICATION_DOCUMENT',\n /** One application module, registered across the layer registries under one module identity. */\n APPLICATION_MODULE = 'APPLICATION_MODULE',\n /*\n * THE NON-RESOURCE PRODUCTS (#1490). Each names an artifact of a surface the five target kinds\n * above `MODULE_FRONTEND` could not express, and each is probed by the host from committed bytes —\n * a declaration in the one file that registers it, never a directory a scenario already wrote.\n */\n /**\n * Named declarations in ONE application-wide frontend configuration file — a sidebar section\n * ref the app shell gains, a zone the navigation config declares, a token the design system sets.\n *\n * The DECLARATIONS, never the file: every `frontend/src/config/*.config.ts` is written by\n * `wildo init`, so its presence is true before any task runs. Same reasoning as\n * {@link RESOURCE_SCHEMA_FIELDS}, one level up.\n */\n APPLICATION_FRONTEND_CONFIG = 'APPLICATION_FRONTEND_CONFIG',\n /**\n * One composite view of one resource — the cross-resource surface a resource's ui-behavior\n * declares under `compositeViews`. Distinct from {@link APPLICATION_VIEW}, which is\n * application-level and owned by a module rather than a resource.\n */\n RESOURCE_COMPOSITE_VIEW = 'RESOURCE_COMPOSITE_VIEW',\n /** One custom operation or execution view of one resource, bound in its ui-behavior. */\n RESOURCE_CUSTOM_VIEW = 'RESOURCE_CUSTOM_VIEW',\n /** One chart view of one resource, declared under its ui-behavior's `chartViews`. */\n RESOURCE_CHART_VIEW = 'RESOURCE_CHART_VIEW',\n /** One custom frontend component, registered by `componentRef` in the module's or the engine's registrations. */\n CUSTOM_COMPONENT = 'CUSTOM_COMPONENT',\n /**\n * One milestone a module declares — the moment the application recognises and celebrates.\n *\n * Named by its identifier, which is what the module's `milestones.ts` declares\n * (`first-project-created` is spelled `FIRST_PROJECT_CREATED` there). The module FILE is not the\n * product: a module may carry milestones before this task runs, and only the identifier says this\n * one landed.\n */\n APPLICATION_MILESTONE = 'APPLICATION_MILESTONE',\n /** One onboarding document or guidance flow a module declares, named by its ref. */\n APPLICATION_GUIDANCE = 'APPLICATION_GUIDANCE',\n /** One PDF template bound to one resource's generated-file field. */\n PDF_TEMPLATE = 'PDF_TEMPLATE',\n /**\n * One worker's JOBS — the named handlers its entry file declares.\n *\n * The jobs, not the package: `add-worker-node` writes the package, so its directory proves\n * nothing. What a coding task adds is behaviour, and behaviour is a symbol in the entry file.\n */\n APPLICATION_WORKER = 'APPLICATION_WORKER',\n /** One minion's BEHAVIOURS — the named tick handlers its entry file declares. Same reasoning as the worker. */\n APPLICATION_MINION = 'APPLICATION_MINION',\n /** One provider declared in one runtime owner's scope. */\n PROVIDER_BINDING = 'PROVIDER_BINDING',\n /** One website page, registered in the website root config by its manifest. */\n WEBSITE_PAGE = 'WEBSITE_PAGE',\n /** One section of one website page, declared in that page's sections file. */\n WEBSITE_SECTION = 'WEBSITE_SECTION',\n /**\n * One authored documentation chapter — a consumer guide the specifications package declares\n * for the documentation portal to publish (#874's publication input).\n */\n DOCUMENTATION_CHAPTER = 'DOCUMENTATION_CHAPTER',\n}\n\n/**\n * One artifact a task is accountable for. Closed by construction: a product the\n * host cannot ask a question about is a product that can never be shown to have\n * landed, so the vocabulary only grows alongside the resolver that answers it.\n */\nexport const BuildPlanTaskProductSchema = z.discriminatedUnion('kind', [\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.RESOURCE_SCHEMA_FIELDS).systemEnum('BuildPlanTaskProductKind'),\n resourceRef: SlugSchema,\n /**\n * At least one field, because a task that enriches a schema with nothing is\n * the vacuity this whole field exists to stop: it would land the moment the\n * scaffold existed, which is the defect being fixed.\n */\n fieldRefs: z.array(NonEmptyStringSchema).min(1),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_REGISTRATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, operationRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_UI_BEHAVIOR).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_SPECIFICATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, fieldRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.RESOURCE_RELATIONSHIP).systemEnum('BuildPlanTaskProductKind'),\n relationshipRef: SlugSchema,\n /*\n * The two resources the edge relates, NAMED rather than parsed out of the ref.\n *\n * A ref is `<source>-<target>` by convention and that convention is not invertible:\n * `next-step-deal` splits as (`next`, `step-deal`) or (`next-step`, `deal`) and only the domain\n * plan knows which. The domain plan already carries both, so the plan passes them on instead of\n * making the host guess — a host that guesses wrong probes for a resource that does not exist\n * and reports the task permanently unlanded.\n */\n sourceResourceRef: SlugSchema,\n targetResourceRef: SlugSchema,\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_OPERATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, operationRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_VIEW).systemEnum('BuildPlanTaskProductKind'), viewRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_DOCUMENT).systemEnum('BuildPlanTaskProductKind'), documentRef: DocumentProductRefSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MODULE).systemEnum('BuildPlanTaskProductKind'), moduleRef: SlugSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.APPLICATION_FRONTEND_CONFIG).systemEnum('BuildPlanTaskProductKind'),\n configSurface: z.enum(FrontendConfigSurface).systemEnum('FrontendConfigSurface'),\n /** At least one, for the same vacuity reason as a schema's `fieldRefs`: the file exists on day one. */\n declarationRefs: z.array(NonEmptyStringSchema).min(1),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_COMPOSITE_VIEW).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, viewRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_CUSTOM_VIEW).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, viewRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_CHART_VIEW).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, chartRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.CUSTOM_COMPONENT).systemEnum('BuildPlanTaskProductKind'), componentRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MILESTONE).systemEnum('BuildPlanTaskProductKind'), milestoneRef: SlugSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.APPLICATION_GUIDANCE).systemEnum('BuildPlanTaskProductKind'),\n /** Which definitions file carries it — a document and a flow live in different ones. */\n guidanceKind: z.enum(ApplicationGuidanceKind).systemEnum('ApplicationGuidanceKind'),\n guidanceRef: SlugSchema,\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.PDF_TEMPLATE).systemEnum('BuildPlanTaskProductKind'),\n resourceRef: SlugSchema,\n /** The generated-file FIELD the template is bound to (`generatedSummaryPdf`) — a symbol, so any spelling. */\n templateRef: NonEmptyStringSchema,\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_WORKER).systemEnum('BuildPlanTaskProductKind'), workerRef: SlugSchema, jobRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MINION).systemEnum('BuildPlanTaskProductKind'), minionRef: SlugSchema, behaviorRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.PROVIDER_BINDING).systemEnum('BuildPlanTaskProductKind'),\n providerRef: SlugSchema,\n scope: z.enum(ProviderBindingScope).systemEnum('ProviderBindingScope'),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_PAGE).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_SECTION).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema, sectionRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER).systemEnum('BuildPlanTaskProductKind'), chapterRef: SlugSchema }),\n]);\nexport type BuildPlanTaskProduct = z.infer<typeof BuildPlanTaskProductSchema>;\n\n/**\n * Every artifact identity a product claims — one string per artifact, not one\n * per product, because a product may claim several.\n *\n * `RESOURCE_SCHEMA_FIELDS` is why this returns a list. Two tasks may both enrich\n * one resource's schema (a domain shape and a billing concern, say), and that is\n * legitimate; what must never overlap is the FIELDS. Comparing whole products\n * would refuse the legitimate pair, and comparing only the resource would let two\n * tasks claim one field and make landing ambiguous again.\n *\n * Derived from the product's own members rather than stored, and total over the\n * vocabulary, so a kind added tomorrow must state its identity here or fail to\n * compile — it cannot be silently treated as equal to its siblings.\n */\nexport function buildPlanTaskProductIdentities(product: BuildPlanTaskProduct): readonly string[] {\n switch (product.kind) {\n case BuildPlanTaskProductKind.RESOURCE_SCHEMA_FIELDS:\n return product.fieldRefs.map((fieldRef) => `${product.kind}:${product.resourceRef}:${fieldRef}`);\n case BuildPlanTaskProductKind.RESOURCE_REGISTRATION:\n return product.operationRefs.map((operationRef) => `${product.kind}:${product.resourceRef}:${operationRef}`);\n case BuildPlanTaskProductKind.RESOURCE_SPECIFICATION:\n return product.fieldRefs.map((fieldRef) => `${product.kind}:${product.resourceRef}:${fieldRef}`);\n case BuildPlanTaskProductKind.RESOURCE_UI_BEHAVIOR:\n return [`${product.kind}:${product.resourceRef}`];\n case BuildPlanTaskProductKind.RESOURCE_RELATIONSHIP:\n return [`${product.kind}:${product.relationshipRef}`];\n case BuildPlanTaskProductKind.RESOURCE_OPERATION:\n return [`${product.kind}:${product.resourceRef}:${product.operationRef}`];\n case BuildPlanTaskProductKind.APPLICATION_VIEW:\n return [`${product.kind}:${product.viewRef}`];\n case BuildPlanTaskProductKind.APPLICATION_DOCUMENT:\n /*\n * The ref AS AUTHORED, so a slug and a namespaced ref are different artifact identities even\n * where they mean the same document — the duplicate-artifact refusal cannot see two tasks\n * claiming one document if they spell it differently. Not normalisable: a slug carries no\n * namespace, so nothing can recover `public.` from `privacy-notice`. It costs nothing today\n * because a slug names no catalogued document at all, and the dispatcher skips such a task.\n */\n return [`${product.kind}:${product.documentRef}`];\n case BuildPlanTaskProductKind.APPLICATION_MODULE:\n return [`${product.kind}:${product.moduleRef}`];\n // One identity per DECLARATION, like schema fields: two tasks may compose one config file as\n // long as they declare different things in it.\n case BuildPlanTaskProductKind.APPLICATION_FRONTEND_CONFIG:\n return product.declarationRefs.map((declarationRef) => `${product.kind}:${product.configSurface}:${declarationRef}`);\n case BuildPlanTaskProductKind.RESOURCE_COMPOSITE_VIEW:\n case BuildPlanTaskProductKind.RESOURCE_CUSTOM_VIEW:\n return [`${product.kind}:${product.resourceRef}:${product.viewRef}`];\n case BuildPlanTaskProductKind.RESOURCE_CHART_VIEW:\n return [`${product.kind}:${product.resourceRef}:${product.chartRef}`];\n case BuildPlanTaskProductKind.CUSTOM_COMPONENT:\n return [`${product.kind}:${product.componentRef}`];\n case BuildPlanTaskProductKind.APPLICATION_MILESTONE:\n return [`${product.kind}:${product.milestoneRef}`];\n // The ref alone: a document and a flow sharing one ref is still one guidance identity, and the\n // runtime keys a person's saved state by it — two artifacts claiming it would collide there too.\n case BuildPlanTaskProductKind.APPLICATION_GUIDANCE:\n return [`${product.kind}:${product.guidanceRef}`];\n case BuildPlanTaskProductKind.PDF_TEMPLATE:\n return [`${product.kind}:${product.resourceRef}:${product.templateRef}`];\n case BuildPlanTaskProductKind.APPLICATION_WORKER:\n return product.jobRefs.map((jobRef) => `${product.kind}:${product.workerRef}:${jobRef}`);\n case BuildPlanTaskProductKind.APPLICATION_MINION:\n return product.behaviorRefs.map((behaviorRef) => `${product.kind}:${product.minionRef}:${behaviorRef}`);\n // The SCOPE is part of the identity: one provider bound on the backend and on the website is two artifacts.\n case BuildPlanTaskProductKind.PROVIDER_BINDING:\n return [`${product.kind}:${product.scope}:${product.providerRef}`];\n case BuildPlanTaskProductKind.WEBSITE_PAGE:\n return [`${product.kind}:${product.pageRef}`];\n case BuildPlanTaskProductKind.WEBSITE_SECTION:\n return [`${product.kind}:${product.pageRef}:${product.sectionRef}`];\n case BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER:\n return [`${product.kind}:${product.chapterRef}`];\n default: {\n const unhandled: never = product;\n throw new Error(`Unhandled build-plan task product ${JSON.stringify(unhandled)}.`);\n }\n }\n}\n\nexport const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE), moduleRef: SlugSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.RESOURCE_STAGE),\n moduleRef: SlugSchema,\n resourceRef: SlugSchema,\n stage: z.enum(BuildPlanResourceStage),\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.RELATIONSHIP),\n moduleRef: SlugSchema,\n relationshipRef: SlugSchema,\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.COMPANION_GENERATION_STEP),\n /** The companion generation step this task runs (e.g. i18n-labels, email-templates); resolved by the companion, never by a coding agent. */\n generationStepRef: SlugSchema,\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.SHELL_PLACEMENT),\n /**\n * Which shell surface this task authors — the placement family's OWN\n * `PlacementSurface`, deliberately not a build-plan copy of it.\n *\n * A copy was written first and was a defect, caught by probing the landing\n * renderer rather than by any test: `PlacementAddress` discriminates on\n * `surface` with `z.literal(...)` per option, so only the VALUES survive into\n * the schema, and the renderer resolves a discriminator by matching that value\n * SET against the exported enums. Two enums with identical values made the\n * match ambiguous, the renderer correctly refused to guess an owner, and the\n * address discriminator became unnameable — a landed placement plan would have\n * emitted `surface: \"SETTINGS_HUB\"` as a bare string instead of\n * `PlacementSurface.SETTINGS_HUB`. One concept, one named source.\n */\n surface: z.enum(PlacementSurface).systemEnum('PlacementSurface'),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_FRONTEND), moduleRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_BACKEND), moduleRef: SlugSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.APPLICATION_FRONTEND_CONFIG),\n configSurface: z.enum(FrontendConfigSurface).systemEnum('FrontendConfigSurface'),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.WEBSITE) }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.TECHNICAL_DOCUMENTATION) }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.WORKER),\n /** The worker's directory under `workers/` and its key in the SaaS config, in slug form. */\n workerRef: SlugSchema,\n runtime: z.enum(BuildPlanWorkerRuntime).systemEnum('BuildPlanWorkerRuntime'),\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.MINION),\n /** The minion's directory under `minions/` and its key in the SaaS config, in slug form. */\n minionRef: SlugSchema,\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.PROVIDER_BINDING), providerRef: SlugSchema }),\n]);\nexport type BuildPlanTaskTarget = z.infer<typeof BuildPlanTaskTargetSchema>;\n\n/**\n * One ordered build task. It names WHAT to build and WHY; it never carries\n * HOW (no paths, commands, prompts, cwd, model, profile). The host resolves\n * the physical allowed/prohibited paths and the fixed verification from the\n * target kind, and the installed skills from `skillRefs` against the app\n * knowledge catalog.\n *\n * Dependency readiness is DECLARED as prerequisite task refs and RESOLVED by\n * the host (a prerequisite is satisfied when its task has landed), never a\n * solved DAG the model must get right.\n */\nexport const BuildPlanTaskSchema = z.strictObject({\n /** `build-task-<slug>`, stamped by the trusted runtime. */\n taskRef: z.string().regex(new RegExp(`^${BUILD_PLAN_TASK_REF_PREFIX}[a-z0-9]+(?:-[a-z0-9]+)*$`)),\n /**\n * One sentence of intent: what this task delivers.\n *\n * Its OWN instance, not the file's shared leaf, which `templateRef` and the product ref lists also\n * hold. A display decorator mutates the instance it is applied to, and the workbench gives those\n * refs a receding identifier look, which the objective sentence then took too.\n */\n objective: z.string().trim().min(1),\n target: BuildPlanTaskTargetSchema,\n /**\n * The artifacts this task is accountable for — what proves it done.\n *\n * Coding tasks should declare at least one product that composition did not already\n * write. A target is a shared mutation scope; its scaffolded file is not evidence\n * that this task's intended work exists. Products identify the output to probe.\n *\n * Empty declarations remain representable and produce the advisory\n * `TASK_DECLARES_NO_PRODUCT`. The host may advance after a COMPLETED durable run,\n * while naming the task in `unverifiableLandedTaskRefs`: it ran, but its output\n * cannot be proven from a product declaration. An unexecuted task is not landed.\n * This distinction avoids repeatedly dispatching the same unprovable task without\n * presenting execution history as evidence that the intended product is correct.\n *\n * The ONE hard exception is a `COMPANION_GENERATION_STEP`, which must declare NONE.\n * That kind already carries its own typed landed condition, owned by the\n * generation-step service — a set computed asynchronously (planner units x\n * enabled locales), and for the migration step a STATE rather than files. A\n * product declared beside it would be read by nothing, which is the inert\n * declaration this field exists to avoid. Enforced on the graph below, in both\n * directions.\n */\n produces: z.array(BuildPlanTaskProductSchema).default([]),\n /**\n * Exactly ONE functional topic this task belongs to.\n *\n * **It does NOT drive ordering** — this said \"drives cross-app ordering\" until 2026-08-30 and\n * nothing ever ordered by it. Sequencing is `prerequisiteTaskRefs`, resolved by the host, and it\n * is the only thing that decides what may run next.\n *\n * What it DOES: the dispatch host stamps it into the coding-agent's task payload beside\n * `skillRefs`, so the agent is told which phase of building the application this task belongs to.\n * That is context an LLM reads, not a value the runtime branches on — the distinction matters,\n * because a reader who believes it orders will look here for a scheduling bug that lives in the\n * prerequisite graph. See issue #124.\n */\n functionalTopic: z.enum(MetaWorkflow_FunctionalTopic).systemEnum('MetaWorkflow_FunctionalTopic'),\n /** Installed app-knowledge skill folders that carry the technical HOW; resolved via the skills router at dispatch. */\n skillRefs: z.array(SkillRefSchema).min(1),\n /** Task refs that must have landed first; resolved by the host, not solved by the model. */\n prerequisiteTaskRefs: z.array(z.string()).default([]),\n /**\n * What this task is accountable to — traceability only, NEVER scope authority.\n *\n * The vocabulary is the five aspects `BUILD_PLAN_FAMILY_ASPECTS` declares as targets: functional\n * and non-functional requirements, roadmap phases, and the vision's success criteria and\n * constraints. It reads \"Requirement / roadmap refs\" until 2026-09-11, and the last two were added\n * because the producer had been writing them all along (#629) — the generation contract asks for a\n * plain string list, so nothing here has ever refused a key.\n *\n * A key outside those five is not rejected and must not be: this is traceability a human or a\n * model wrote down, and dropping it loses the intent. The workbench renders such a key as visibly\n * unresolved instead, which is what makes a producer drift legible rather than silent.\n */\n servesRefs: z.array(NonEmptyStringSchema).default([]),\n});\nexport type BuildPlanTask = z.infer<typeof BuildPlanTaskSchema>;\n\n/**\n * THE build-plan payload — a **single aggregate per product**: the ORDERED\n * task graph that turns the accepted domain plan into buildable units.\n *\n * **Artifact-family id: `build-plan`.** This schema is the shape of the\n * journey artifact selected by `MetaWorkflow_ArtifactSelector.family ===\n * 'build-plan'` (the `family` vocabulary stays an open string owned by the\n * selector surface; this note is the single place tying the SHAPE to the\n * NAME). Produced by the build-decompose playbook, consumed one task at a\n * time by build-dispatch (single-flight coding dispatch) and by the scale\n * playbook.\n *\n * Invariants enforced here: unique task refs; every prerequisite names a task\n * in this graph; no self-prerequisite. Cycle detection and ordering\n * soundness are the deterministic validator's job (`validateBuildPlanTaskGraph`).\n */\nexport const BuildPlanTaskGraphSchema = z.object({\n version: z.enum(BuildPlanTaskGraphVersion).default(BuildPlanTaskGraphVersion.V1),\n /**\n * At least one task, at the SCHEMA — not merely as a validator warning. The first live playbook-loop\n * run (2026-08-24) proved why: build-decompose answered `tasks: []`, which was schema-valid, passed\n * `_core` validation as a mere warning, and LANDED — overwriting a completed 3-task plan with a\n * vacuous artifact. Decomposing to zero tasks is a refusal (\"nothing to decompose\"), never an\n * artifact: an empty plan carries no information a reader could act on, and the file it replaces\n * does. Same vacuity class already closed on the requirements family (`functional: min(1)`).\n */\n tasks: z.array(BuildPlanTaskSchema).min(1),\n}).superRefine((graph, context) => {\n const refs = new Set<string>();\n graph.tasks.forEach((task, index) => {\n if (refs.has(task.taskRef)) {\n context.addIssue({ code: 'custom', message: `duplicate build task ref \"${task.taskRef}\"`, path: ['tasks', index, 'taskRef'] });\n }\n refs.add(task.taskRef);\n });\n /*\n * No two tasks claim the same artifact.\n *\n * This is what makes landing DECIDABLE, not a tidiness rule. If two tasks name\n * one product, the host cannot tell which of them a present artifact proves —\n * exactly the ambiguity that shared `target`s created, arriving through the\n * field that replaced them. Enforced here rather than left to the validator\n * because a graph that cannot answer \"has this task landed?\" is not a graph\n * the loop may run at all.\n */\n graph.tasks.forEach((task, index) => {\n const isGenerationStep = task.target.kind === BuildPlanTaskTargetKind.COMPANION_GENERATION_STEP;\n if (isGenerationStep && task.produces.length > 0) {\n context.addIssue({\n code: 'custom',\n message: `build task \"${task.taskRef}\" is a companion generation step and must declare no products; its landing is the generation step's own condition`,\n path: ['tasks', index, 'produces'],\n });\n }\n });\n const productOwners = new Map<string, string>();\n graph.tasks.forEach((task, index) => {\n task.produces.forEach((product, productIndex) => {\n buildPlanTaskProductIdentities(product).forEach((identity) => {\n const owner = productOwners.get(identity);\n if (owner !== undefined) {\n context.addIssue({\n code: 'custom',\n message: `build task \"${task.taskRef}\" claims the same artifact as \"${owner}\" (${identity}); an artifact is produced by exactly one task`,\n path: ['tasks', index, 'produces', productIndex],\n });\n return;\n }\n productOwners.set(identity, task.taskRef);\n });\n });\n });\n graph.tasks.forEach((task, index) => {\n task.prerequisiteTaskRefs.forEach((prerequisite, prerequisiteIndex) => {\n if (prerequisite === task.taskRef) {\n context.addIssue({ code: 'custom', message: `build task \"${task.taskRef}\" cannot be its own prerequisite`, path: ['tasks', index, 'prerequisiteTaskRefs', prerequisiteIndex] });\n } else if (!refs.has(prerequisite)) {\n context.addIssue({ code: 'custom', message: `build task \"${task.taskRef}\" names an unknown prerequisite \"${prerequisite}\"`, path: ['tasks', index, 'prerequisiteTaskRefs', prerequisiteIndex] });\n }\n });\n });\n});\nexport type BuildPlanTaskGraph = z.infer<typeof BuildPlanTaskGraphSchema>;\n```\n\n## What this playbook does\n\nYou are the **dispatch orchestrator**. This playbook reads the approved build plan\nand the current journey state and answers, for *one* task at a time: *\"dispatch this\ntask safely, verify it, and record what happened.\"* You do **not** produce a new\njourney artifact — the dispatch's observable result (the change-set + the task\nstatus) is materialized by the runner on the task row, not authored here (see \"What\nyou emit\"). You do **not** decompose the plan, author any schema, or write any code\n— the coding agent writes the code at dispatch time; the plan is the\nbuild-decompose playbook's; scale is the scale playbook's.\n\n## The dispatch contract — the runner owns the mechanism, you sequence it\n\nMost of the D4 dispatch contract is **runner mechanism**, not prose you re-implement:\nthe runner composes the context pack, opens a coding session with the agent over the\nAgent Client Protocol and sends one prompt turn, answers the agent's permission\nrequests within the declared ceiling, captures the change-set, runs the verify hook,\nholds the single-flight lock and applies its configured execution limits. Your method here is the **declarative recipe** the runner interprets —\n*which* task to dispatch next, *when* it is authorized, and *how* its outcome is\njudged. Do not hand-compose a dispatch prompt or drive git yourself; let the runner\nown composition and change-set capture.\n\n## Read state first — no artifact to write\n\nThis playbook is **idempotent** and, on a re-run, *advances the loop by one task*.\nBefore dispatching anything:\n\n1. Read the current journey state and scope through the `journey-status` skill (it\n owns the read; do not re-derive it here). Confirm the **build plan** is present\n and approved, and confirm the **foundation** ran. For each build-plan task,\n determine its dispatch state from its task row — **not yet dispatched**,\n **dispatched-and-succeeded** (a captured change-set + a passed verify), or\n **dispatched-and-failed** (a captured change-set but a failed/timed-out run or a\n failed verify). This tri-state matters: under `keep_and_flag` a **failed** task\n *also* has a captured change-set, so \"has a change-set\" alone does NOT mean the\n task is done — read the task's terminal status + verify outcome, not just the\n presence of a change-set.\n2. Read the approved **build plan** (`build-plan` — the ordered task graph). It is your\n work list.\n\n Evidence that the foundation ran is `./wildo.saas.config.ts` itself, committed: the\n app either has a config and a skeleton or it does not, and git answers that without a\n journey artifact standing in for it. (A `foundation-manifest` family was that stand-in\n until 2026-08-25; it was retired with the app-creation verification/digest aspect, and\n this playbook no longer gates on it.) The honest limitation inherited from the\n foundation step still applies: at scaffold depth the on-disk skeleton *materialization*\n depends on greenfield bring-up tooling (deferred). The dispatch contract is real and\n runs against an **existing** app skeleton — the dogfood app already has one.\n\n// Operator status: `wildo context journey` (eligibility board + runs in flight). Which tasks already\n// landed is read from GIT by the runner itself — a task is landed when every file it produces is\n// committed clean.\n\nYou **read** `build-plan`; you **write** no journey artifact\n— the runner records the change-set + task status on the dispatched task's row.\n\n## Precondition — the application must establish the agent's role, or dispatch stalls\n\nCheck this before the first dispatch of an application's life. It costs one look and it is the\ndifference between a working lane and one that burns model time producing nothing.\n\n**The application needs a root `CLAUDE.md` stating that a task dispatched by its dev companion is\nlegitimate work.** Without it the agent is right to refuse, and refusing is what it does.\n\nThe reason is structural rather than a matter of tone. A dispatched task reaches the agent as an\nordinary prompt — a user turn carrying an objective, a mutation scope and skill refs. Nothing in\nthat turn proves where it came from. So the agent is being handed conversational content that\ntells it to write files into a repository, which is indistinguishable from the thing every\ncareful agent is supposed to decline, and the more trustworthy the agent the more reliably it\ndeclines. Measured on a real application with no such file: two dispatched runs stalled, one\nanswering *\"content that arrives as conversational input doesn't get to reassign what I am\"*.\n\nThe failure does not look like a missing file. It looks like an agent that deliberates well,\nidentifies exactly which files it would author, explains its reasoning, asks a human to confirm,\nand ends its turn — `end_turn`, no error, no denial, an empty change set, and a bill for the\ntokens. Read as \"the agent chose not to work\", which invites prompt-tuning that cannot fix it.\n\n`wildo init` scaffolds this file. An application created before that, or one whose `CLAUDE.md`\ncovers only its own conventions, needs the section added. What it must establish:\n\n- the task is **selected by the host** from the accepted build plan, not composed by a caller;\n- its **file edits** are **confined before they arrive** — the host answers every permission request\n against the declared mutation scope and refuses paths outside it;\n- its **shell commands are NOT**, and the section must say so. A command declares no `locations`, so\n the scope predicate never runs for one; telling an agent it \"need not police itself\" is true of its\n edits and false of its commands, and that is the half a stray write comes through. Name the\n compensations with it: the post-run change set and the companion's warning DETECT such a write,\n they do not prevent it;\n- it is **reversible** — every write is an uncommitted working edit until something commits it. Do\n not state WHO commits as a property of the lane: that is the host's autonomy posture, it changes,\n and an agent that reads \"a human commits\" from a scaffold written under a different posture is\n working from a stale contract.\n\nTwo smaller things belong in the same section, because both were observed costing a run:\n\n- **Say what `allowedPathPrefixes` are relative to.** The agent receives bare prefixes such as\n `shared-lib/src/modules/<module>/` with no root, and cannot verify its own confinement against\n them. One sentence naming the application root removes the ambiguity.\n- **Do not name a task so it reads as a fixture.** An agent that concludes it is looking at a\n smoke test will say so and stop. Name the task after the product change it makes.\n\n## Step 1 — Select the next dispatchable task (single-flight)\n\nWalk the build plan in its authored order and pick the **first** task that is not\nyet dispatched (or a previously-**failed** task cleared for retry — see Step 5) and\nwhose prose prerequisites have all **succeeded**. Dispatch **exactly one** such task\nper run. If **no** task is ready — every task has already succeeded, or the only\nundispatched tasks are blocked behind a still-unresolved failure — there is nothing\nto dispatch: report the loop as done (or blocked on the failed task) and stop. An\nempty build plan is the same: nothing to dispatch, stop.\n\n- **Single-flight — one workspace-mutating run at a time.** The dispatch lane holds\n ONE workspace-mutation lock for the whole background run; a run plan carries **at\n most one** coding-agent task, and a second concurrent dispatch is refused. This is\n a hard runner floor, not a suggestion — do not try to dispatch two tasks in one\n run to \"go faster\". Batching across many agents is the scale playbook's job.\n- **A prerequisite must have SUCCEEDED, not merely been attempted.** A task is ready\n only when every task it depends on is dispatched-and-succeeded (verify passed).\n A prerequisite that is dispatched-and-**failed** (its change-set is flagged for\n triage under `keep_and_flag`) does **not** satisfy the dependency — its dependents\n stay **blocked** until the failure is triaged and the prerequisite re-dispatched\n successfully. Do not build a config on a schema whose run failed. Never dispatch a\n task before the stage it depends on (a config before its schema, a spec before its\n ui-behavior — the build-decompose playbook ordered these).\n- **Companion-generation steps are not coding-agent dispatches.** A build-plan task\n marked as a companion-owned generation step (labels / i18n, email templates,\n seeds) runs through its deterministic companion endpoint, not the coding-agent\n dispatch lane. Route it there; do not dispatch a coding agent for it. Interleaving\n those steps *concurrently* with coding runs at scale is the scale playbook's job —\n here you simply run the ready one in its turn.\n\n## Step 2 — Check the actual host authorization boundary\n\nA coding dispatch writes the application workspace. Read its selected task, readiness,\nmutation scope and the configured coding host's authorization policy before invoking it.\nThe single-flight mutation lock still applies to the current shared workspace.\n\nThe playbook's `approval` declaration and the journey autonomy presets express policy\nintent. The current playbook runner does not interpret them as pre-dispatch gates,\nautomatic authorization, or a GUIDED/YOLO mapping. A declared `approve_before` does\nnot create a pending Authority Request. Use `journey-approve` only for an actual\nrequest from an explicitly connected authority workflow; never invent one from an enum.\n\nLikewise, do not infer enforced per-playbook or per-journey run ceilings from declared\nbudget fields. Respect the limits actually reported by the execution host. Inspect the\nrecorded changes and verification result after each task; no preset commits or accepts them.\n\n## Step 3 — Dispatch the task through the coding-agent contract\n\nTrigger the run through the `journey-run` skill. The runner then performs the D4\ndispatch contract for you (you do not hand-assemble any of it):\n\n1. **Context pack** — the runner composes the prompt: the task brief, the task's\n skill pointers (`Read .claude/skills/<skillRef>/SKILL.md first` — the per-task\n HOW-skills the build plan named on this task), the relevant journey / definition\n artifacts, an introspected app-reality block, and the repo paths.\n2. **Session and one prompt turn** — the runner starts the agent over the Agent\n Client Protocol and opens a session rooted at the app workspace (cwd = the\n application root, so `./CLAUDE.md`, the sub-`CLAUDE.md`s, and the `.claude/` rules\n and skills load naturally), then sends the task as a single prompt turn. It is a\n session rather than a one-shot process, which is what makes the next three things\n possible at all:\n - **Permissions are answered, not assumed.** The agent asks before each action it\n considers privileged; the runner answers within the execution profile's declared\n ceiling and refuses anything above it, or anything touching a path outside the\n task's mutation scope. Refusals are counted on the task row, so a run that was\n held back is distinguishable from a run that had nothing to do.\n - **The turn can be cancelled.** Cancellation asks the agent to stop and waits, so\n the run terminalises with its change-set intact instead of being killed — an\n operator who stops a run still needs to know what it had already written.\n - **Usage is reported.** Tokens and cost come back from the run itself rather than\n being unavailable, which lets the host report a terminal timeout instead of leaving the run ambiguous.\n3. **Change-set capture** — the runner captures a git worktree snapshot before and\n after the run and attributes each touched file (the run's own edit vs. an\n already-dirty parallel-session file vs. a file that appeared during the run),\n recording a structured change-set on the task row. On the dogfood tree,\n dirty-at-dispatch is the NORMAL state (parallel sessions), so the capture\n *attributes* rather than assuming the run had the tree to itself.\n\n// The trigger is the companion's run route (`POST /api/companion/playbooks/<ref>/run`, via the\n// workbench or HTTP) — there is no CLI trigger yet. The runner composes the typed context pack,\n// runs one ACP prompt turn, and captures the change-set.\n// That route is MUTATING, so the call must carry `x-wildo-companion-token`, read from\n// `./.wildo-saas/state/companion.token` (mode 0600). Without it the companion answers `401` with a\n// body that names nothing — the explanation is in the companion's own log.\n\n## Step 4 — Verify OUTSIDE the coding agent\n\nTrust, but verify. The verify gate runs **outside** the coding agent, after the run,\nso the agent cannot mark its own homework:\n\n- **`dispatch-typecheck` (deterministic — the auto-run trust floor).** The runner\n maps this `deterministic_validator` gate (`validatorRef: typecheck`) onto the\n dispatch verification hook and runs a typecheck (`pnpm exec tsc --noEmit`) over the\n application workspace after the run, **outside** the coding agent. This is a\n **real, wired** gate — it actually executes and its result is recorded on the task\n row. A run whose typecheck fails is a failed run (apply the failure disposition in\n Step 5). At scaffold depth the gate is a **workspace-wide** typecheck (one static\n gate for every dispatch of this playbook); narrowing it to the specific package a\n given task touched — a per-task `typecheck:<pkgDir>` or a `vitest:<path>` targeted\n at the task's tests — is a later refinement, since a static playbook gate cannot\n vary per task.\n- **`dispatch-outcome-sound` (declarative reviewer checklist).** The six-invariant\n reviewer checklist (task accomplished, change-set scoped to the task, verify ran +\n passed, attribution clean, failure disposition correct, boundary discipline)\n is the *trust-but-verify reviewer* pass. It is **declarative** — the creator's\n review checklist; the compiled build-dispatch Evaluation Treatment is what the\n runtime judges with, and the deterministic typecheck above is what runs\n automatically.\n\n## Step 5 — Record the result and apply the failure disposition\n\nThe runner records the change-set + the task's terminal status on the task row. On a\n**failed or timed-out** run, the current coding host retains its captured changes for inspection (the declaration describes this as **`keep_and_flag`**): the\ncaptured change-set is **kept and flagged for human triage** — never silently\nreverted, and never left as an un-recorded half-applied state. The change-set capture\n*is* the flag: it attributes exactly which files the run touched, so a human can\nreview, keep, or unwind them.\n\n> **Why keep_and_flag, not revert_changeset (a v1 boundary).** Reverting a failed\n> run's edits is a *mutating* git operation, deliberately **outside** the read-only\n> change-set carve-out the dispatch lane observes (the runner *observes* git —\n> baseline/post-run snapshots — but stage/commit/revert stay a human/CLI concern).\n> So `keep_and_flag` is both the correct F-5 workspace-safety posture (no silent\n> half-applied state) and the behavior the runner actually enforces today. Wiring a\n> `revert_changeset` path is a deliberate later boundary decision, not a gap this\n> playbook papers over.\n\nOn a **succeeded** run (change-set captured + verify passed), the task is done and\nits dependents become eligible. On a **failed** run, the task is **not** done — it is\nflagged for human triage, and its dependents stay blocked (Step 1) until it is\ntriaged and cleared for re-dispatch. Triage is a human decision: keep + fix forward,\nunwind the flagged change-set by hand, or re-dispatch the task once its blocker is\nresolved. This playbook does not auto-retry a failed task — automated retry / backoff\nis a deferred build-loop-resilience concern, and human triage is the v1 disposition;\nhere the loop simply surfaces the failure and stops advancing that dependency chain.\n\nThen **loop**: on the next run of this playbook, `journey-status` reflects the\njust-dispatched task's outcome, and you select the next ready task (Step 1). Close a\nsignificant stretch of dispatches with a `journey-report` summary — what was\nproduced, which change-sets landed, what verify said, and any failed task left\nflagged for triage.\n\n## Refine, don't re-dispatch\n\n- **Never re-dispatch a SUCCEEDED task.** A task that is dispatched-and-succeeded\n (change-set captured + verify passed) is done — advance to the next ready task, do\n not re-run it because the plan was re-opened elsewhere. A dispatched-and-**failed**\n task is a different case: it is re-dispatchable once triaged (Step 5) — a captured\n change-set alone does not make a task \"finished\".\n- **Follow the plan's order.** If the build plan was refined upstream (a task added,\n an ordering corrected), respect the new order on the next selection — do not cache\n a stale work list across runs.\n- **A host execution refusal is a real stop.** When an actual execution limit is reported, stop dispatching\n and report what remains; do not do the coding work out-of-band to \"finish the\n build\" — that makes the journey's task history a lie.\n\n## Scaffold-depth boundary (owned by a sibling, or deferred to a later phase)\n\nKeep this playbook at **single-flight dispatch depth**. Explicitly **out of scope\nhere**:\n\n- **Re-decomposition.** You do NOT split modules/resources into tasks, re-order the\n graph, or add tasks — the **build-decompose** playbook owns the task graph. You\n read it and dispatch from it.\n- **Multi-agent scale + interleaving.** Running MANY coding agents concurrently, a\n concurrency scheduler, a run-completion serializer, and interleaving the companion\n generation steps *concurrently* with coding runs is the **scale** playbook. You\n dispatch **one** task at a time under the single-flight lock; you do NOT design the\n concurrency schedule.\n- **A `revert_changeset` failure path.** Undoing a failed run's edits is a mutating\n git op outside the read-only change-set carve-out — deferred. `keep_and_flag` (keep\n + flag the captured change-set for triage) is the v1 disposition.\n- **Auto-executed reviewer checklist.** The checklist ships **declarative** —\n the deterministic typecheck gate runs automatically and the compiled Evaluation\n Treatment is the judged protocol; nothing executes the checklist prose. Do not\n assume it auto-ran.\n- **Schema / field authoring + code generation.** You dispatch a task; the **coding\n agent** authors the fields, schemas, ui-behavior, and code at dispatch time. If you\n catch yourself writing application code or a resource schema here, stop — that is\n the dispatched agent's job, not the orchestrator's.\n\nIf you find yourself designing how MANY agents run concurrently rather than how ONE\ntask dispatches safely, stop — that is the scale playbook.\n\n## What you emit\n\n**No journey artifact.** This is a pure-orchestration playbook: the observable result\nof a dispatch — the **change-set** (files touched, attributed, summarized) and the\n**task status** — is materialized by the runner on the dispatched task's row, not\nauthored by this playbook. That is deliberately not duplicated into a separate\njourney artifact family: the task row already *is* the dispatch record, and a second\nhome for the same record would drift.\n\nDispatch uses the configured host's actual authorization boundary. The creator reviews\nthe recorded change-set and verification outcome afterwards —\none verified task at a time, until the build plan is fully dispatched.\n\n## References\n\n- `.claude/skills/journey-status/SKILL.md` — read the current journey state,\n scope, and budget; confirm the build plan is approved and the foundation ran, and\n see which tasks already dispatched.\n- `.claude/skills/journey-run/references/framework-playbook-approval-policy.md` — declaration semantics and the actual runner boundary.\n- `.claude/skills/journey-run/SKILL.md` — trigger the dispatch and monitor it; the\n runner composes the context pack, runs one prompt turn against the coding agent in\n the app workspace, captures the change-set, and runs the verify hook.\n- `.claude/skills/journey-report/SKILL.md` — summarize a stretch of dispatches:\n what was produced, which change-sets landed, and what the verify gates said.\n\n## Reviewer checklist — `dispatch-outcome-sound`\n\nFormerly authored as an `llm_judge` quality gate; the generic rubric-only gate kind was retired at the flexible-intelligence hard cut (judgment now runs only through a compiled Evaluation Treatment). The checklist itself is creator-facing review guidance and is kept here, verbatim (minus the retired runner's closing sentence, and with repository-specific wording made application-neutral):\n\nJudge whether ONE dispatched build-plan task ran soundly under the D4 dispatch contract — the trust-but-verify reviewer pass OUTSIDE the coding agent. Assess six invariants and mark each PASS / CONCERN / GAP with a one-line evidence note. (1) TASK ACCOMPLISHED — the change-set the run produced actually implements the dispatched task's target + stage (e.g. a schema task added the persisted shape; a ui-behavior task added field displays); a run whose change-set does not advance the task's stated target is a GAP (the dispatch produced nothing useful), and an empty change-set on a task that should have authored files is a GAP. (2) CHANGE-SET SCOPED TO THE TASK — the files touched belong to the task's target (its module / resource / stage) and the app workspace; edits sprawling into unrelated modules, Wildo package source outside the application workspace, or files no build-plan task owns are a CONCERN (scope creep the reviewer must flag). Files attributed BASELINE_DIRTY_AMBIGUOUS were already dirty and changed again during the run; this establishes uncertainty, not ownership by a parallel editor. Every changed path outside the declared scope — ambiguous or not, and including a parallel session's edits, which the capture cannot tell apart from the run's own — is RECORDED on the result as `outOfScopePaths`; nothing refuses the run for it. Treat each as a CONCERN and resolve its authorship during review, never as a GAP by itself. Committed-window entries and recognized concurrent host-lane paths are classified separately and left off that list. (3) VERIFY RAN + PASSED — the deterministic verify gate (typecheck) ran OUTSIDE the coding agent after the run and passed; a run recorded as succeeded whose typecheck the reviewer cannot confirm passed is a CONCERN, and a run whose typecheck FAILED but was recorded succeeded is a GAP. (4) ATTRIBUTION CLEAN (the single-flight signal) — the run's edits are cleanly attributable to it in the captured change-set (files classed RUN_EXCLUSIVE or APPEARED_DURING_RUN), consistent with the single-flight lock having held for this dispatch. A change-set the capture could NOT cleanly attribute to the run — dominated by BASELINE_DIRTY_AMBIGUOUS overlap, or captured across a HEAD that moved mid-run — is a CONCERN the reviewer must resolve by hand before accepting the run, not a clean pass (single-flight is a hard runner floor, so this invariant reads the attribution the run actually recorded rather than re-proving the lock). (5) FAILURE DISPOSITION CORRECT — a failed/timed-out run's captured change-set is KEPT + FLAGGED for human triage (keep_and_flag), never silently reverted nor silently left as an un-recorded half-applied state; a failed run with no recorded change-set flag is a GAP (F-5 workspace-safety violation). (6) BOUNDARY DISCIPLINE — the dispatch stays at single-task depth: it dispatches ONE task, captures + verifies + records it, and applies onFailure. It does NOT re-decompose the plan (the build-decompose playbook owns the task graph), does NOT run MANY coding agents concurrently / design a concurrency scheduler / interleave the companion generation steps at scale (the scale playbook), and does NOT itself author schemas / fields / code (the coding agent does that at dispatch time). Evidence of re-decomposition, multi-agent scale orchestration, or the dispatcher authoring code itself is a CONCERN (scope creep out of the single-flight dispatch lane). (The checklist is declarative: nothing executes it; the current host's deterministic checks apply; the approval enum alone adds no gate.)\n",
|
|
23
|
-
"skillRefs": [
|
|
24
|
-
"journey-status",
|
|
25
|
-
"journey-approve",
|
|
26
|
-
"journey-run",
|
|
27
|
-
"journey-report"
|
|
28
|
-
],
|
|
22
|
+
"guidance": "# Build Dispatch — One Build-Plan Task → One Verified Coding-Agent Run (v1 scaffold)\n\n### Target Application Framing\n\nThis knowledge is for configuring behavior in the target application.\nWildo is the framework surface being used, not the product being built.\n\nRead and apply these patterns from the application-developer point of view:\n\n- how the application should configure the relevant app-level file\n- how the application should use framework-provided factories, enums, and helpers\n- how the application should avoid mixing frontend, backend, and infrastructure concerns\n\n\n> **This is a v1 scaffold methodology.** It is a working first cut of the\n> *single-flight* dispatch contract — dispatch exactly ONE build-plan task at a\n> time, capture its change-set, verify it outside the coding agent, record it, and\n> apply the failure disposition. The context-pack shape, the verify gate, and the\n> failure-handling below are deliberately explicit so they can be tuned against real\n> runs. Multi-agent parallelism, a concurrency scheduler, a run-completion\n> serializer, and a `revert_changeset` failure path are a **later phase** — do not\n> build them here (see the boundary section).\n\n## Where you are in the journey\n\nThis is the **second build-execution playbook** — the pivot from **decomposing the\nbuild** (the build-plan: the ordered coding-agent task graph) to **dispatching it**\n(turning one ordered task into an actually-run, verified coding-agent run). It runs\nin the **bottom-up phase**, after the build plan exists (`artifact_exists\nbuild-plan`) and the foundation step has authored the app's config and skeleton.\nYou are not re-opening the decomposition\nhere — you are turning one *approved, ordered* task into a *dispatched, verified*\nchange to the application.\n\nUpstream, the **build-decompose** playbook produced the ordered task graph you\nconsume; downstream, the **scale** playbook generalises this single-flight contract\nto many concurrent coding agents and interleaves the companion generation steps.\n**You author neither of those concerns** — see the boundary section.\n\n## The typed task you dispatch\n\nThe build plan is a typed family (`BuildPlanTaskGraph`): dispatch selects ONE\nREADY task (all declared prerequisite task refs have landed) and hands the\ncoding host exactly that task's `objective`, `target`, `produces`,\n`functionalTopic` and `skillRefs`. The host derives the physical\nallowed/prohibited paths and the fixed verification from the target kind;\nnothing in the task — and nothing in this method prose — authors a path, a\ncommand, a prompt or a runtime control.\n\n`target` and `produces` answer two different questions, and a task needs both.\n`target` is the WRITE SCOPE — where this run may edit, and several tasks\nlegitimately share one. `produces` is what the run is ACCOUNTABLE for: the\nartifacts whose presence in the application proves the task done. A task has\nlanded when every artifact it declares is present and committed, so a run that\nsatisfies the objective's prose without delivering those artifacts is not\nfinished — the plan will offer the task again.\n\n## Import Origins\n\n- `@wildo-ai/saas-specifications`\n\n## Source Excerpts\n\n### Origin Package: `@wildo-ai/saas-specifications`\n\n```typescript\n *\n * Versioning for the build-plan task-graph payload format itself. `V1` —\n * initial shape (one ordered `tasks` collection with typed targets and\n * declared prerequisites). The shape grows additively across versions; the\n * `version` field is the explicit marker for consumers that branch on era.\n */\nexport enum BuildPlanTaskGraphVersion {\n V1 = 'v1',\n}\n\n/** Stable prefix every build-plan task ref carries; the trusted runtime stamps it, a provider supplies only the slug. */\nexport const BUILD_PLAN_TASK_REF_PREFIX = 'build-task-';\n\n/**\n * WHAT a build task builds — a closed vocabulary, because the host derives\n * the physical mutation scope and verification policy from the target kind\n * and the model must never author those powers through free text.\n */\nexport enum BuildPlanTaskTargetKind {\n /** A whole application module (its shared-lib registration, backend module and frontend module skeletons). */\n MODULE = 'MODULE',\n /** One build stage of one resource: schema → config → ui-behavior → spec. */\n RESOURCE_STAGE = 'RESOURCE_STAGE',\n /** One relationship between two resources. */\n RELATIONSHIP = 'RELATIONSHIP',\n /** A companion-owned deterministic generation step (labels, email templates, logo or database migrations) interleaved by the build loop, never a coding-agent run. */\n COMPANION_GENERATION_STEP = 'COMPANION_GENERATION_STEP',\n /**\n * Authoring one SHELL SURFACE's placement configuration from the accepted\n * placement plan — the settings rail, the sidebar, the user menu or the\n * command palette.\n *\n * Its own kind rather than a reuse of the neighbours, because none of them is\n * true of it: it is not a MODULE or a RESOURCE_STAGE (it is application-wide\n * and belongs to no resource), not a RELATIONSHIP, and emphatically not a\n * COMPANION_GENERATION_STEP — that kind is documented as \"never a coding-agent\n * run\" and writing `settings-hub.config.ts` is exactly a coding-agent run.\n * Borrowing one would hand the host the wrong mutation scope and the wrong\n * verification, which is what the closed vocabulary exists to prevent.\n */\n SHELL_PLACEMENT = 'SHELL_PLACEMENT',\n /*\n * THE NON-RESOURCE SURFACES (#1490). Until 2026-09-22 the five kinds above were the whole\n * vocabulary, and every one of them is about a resource or the shell placement of one. The\n * decompose method meanwhile told the planner to emit tasks for views, navigation, the design\n * system, custom components, PDF templates, workers, minions, providers, the website and the\n * documentation — surfaces the framework's own composition scenarios and 85 of its 111 skills\n * already build. A task for any of them had no kind to declare, so it either declared none\n * (landing as RAN-not-PROVEN forever) or borrowed `MODULE` with a product the module scope could\n * not prove. The members below are those surfaces, one per write scope the host can derive.\n */\n /**\n * The FRONTEND and SPECIFICATION layers of one module — its composite, custom and chart views,\n * its custom components and their specifications.\n *\n * Narrower than `MODULE` on purpose: a view task never touches `shared-lib` or `backend-api`, so\n * handing it the four-layer scope also hands it four typechecks and the FK sweep for a change\n * that can only break the frontend and the specifications package.\n */\n MODULE_FRONTEND = 'MODULE_FRONTEND',\n /**\n * The BACKEND layer of one module beside its shared-lib declarations — PDF templates and their\n * bindings, backend addons (services, controllers, flows-actors), email definitions.\n *\n * Shared-lib is in scope because a PDF template is bound to a resource FIELD the config declares\n * (`generatedSummaryPdf`), and a backend addon usually declares its contract there first.\n */\n MODULE_BACKEND = 'MODULE_BACKEND',\n /**\n * ONE application-wide frontend configuration surface — navigation, the design system, the app\n * shell's composition, the global views — named by {@link FrontendConfigSurface}.\n *\n * Distinct from {@link SHELL_PLACEMENT}, which authors the placement plan's decisions into the\n * shell files: a placement puts a decided subject in a decided group, while this kind COMPOSES\n * the surface itself (which sidebar sections exist, which transitions the primary zone uses,\n * which palette the product carries). Same file for `APP_SHELL`, different question.\n */\n APPLICATION_FRONTEND_CONFIG = 'APPLICATION_FRONTEND_CONFIG',\n /** The marketing website workspace (`website/`), composed by the `add-website` scenario. Pages and sections are its products. */\n WEBSITE = 'WEBSITE',\n /**\n * The technical-documentation workspace (`technical-doc/`) and the specification package's\n * `technical-documentation/` declarations that feed it. Its generated tree is never written by a\n * task: the companion publishes into it, and the coding policy prohibits it by prefix.\n */\n TECHNICAL_DOCUMENTATION = 'TECHNICAL_DOCUMENTATION',\n /** One worker package (`workers/<workerRef>/`), Node or Rust, plus its declaration in the SaaS config. */\n WORKER = 'WORKER',\n /** One cron minion package (`minions/<minionRef>/`) plus its declaration in the SaaS config. */\n MINION = 'MINION',\n /**\n * Declaring one provider in the application — the SaaS config's provider scopes, the backend\n * package dependency, the frontend provider module and its companion contribution.\n *\n * Application-wide by construction: a provider binding names no module, and the four files it\n * may touch are the same for every provider.\n */\n PROVIDER_BINDING = 'PROVIDER_BINDING',\n /**\n * The application's BILLING CATALOGUE — the `ProductDefinition[]` in `shared-lib/src/engine/product.ts`\n * (and the product specifications that document it), which the backend syncs to the billing\n * provider and the public website reads for its pricing page (#1835).\n *\n * Its own kind because none of the others is true of it: the catalogue is application-wide (a plan\n * belongs to no module), it lives in the shared library's ENGINE module that no `MODULE_*` scope\n * reaches, and before it existed a journey-built application reached its website with an EMPTY\n * catalogue, so the website re-typed the business model's prices by hand.\n */\n BILLING_CATALOG = 'BILLING_CATALOG',\n}\n\n/**\n * WHICH application-wide frontend configuration surface a task composes — one file each, in\n * `frontend/src/config/`, and the coding policy resolves the member to that file exactly as\n * `SHELL_PLACEMENT` resolves a `PlacementSurface`.\n *\n * Its own vocabulary rather than a reuse of `PlacementSurface`: a placement surface is WHERE a\n * subject sits in the shell (settings hub, sidebar, user menu, command palette), and three of\n * those live in one file. A configuration surface is WHICH FILE a composition task authors, and\n * navigation and the design system are not places anything is placed.\n */\nexport enum FrontendConfigSurface {\n /** `frontend/src/config/navigation.config.ts` — zones, transitions, overlay appearance. */\n NAVIGATION = 'NAVIGATION',\n /** `frontend/src/config/design-system.config.ts` — palette, typography, shell appearance from the brand's visual tone. */\n DESIGN_SYSTEM = 'DESIGN_SYSTEM',\n /** `frontend/src/config/app-shell.config.ts` — top bar, sidebar sections, quick switcher: the shell's COMPOSITION, not a placement into it. */\n APP_SHELL = 'APP_SHELL',\n /** `frontend/src/config/global-views.config.ts` — the application-level launcher and view registrations. */\n GLOBAL_VIEWS = 'GLOBAL_VIEWS',\n}\n\n/**\n * The two shapes of guidance an application gives a person, and the file each is declared in.\n *\n * They are distinct because they are found differently: an onboarding DOCUMENT is embedded in a\n * screen (`EmbedOnboarding`) and is there whenever that screen is, while a guidance FLOW is started\n * by an event and shows once. Both are listed on the owning frontend module — `onboardingViews` and\n * `guidanceFlows`. Each kind has a CONVENTIONAL definitions file, which the authoring skill teaches\n * and a landing probe reads for the declared ref (alongside the module's `index.ts`, where a small\n * module may declare inline). A convention for generated applications: a hand-authored application\n * may keep its declarations elsewhere, and then simply is not probed by a build plan.\n */\nexport enum ApplicationGuidanceKind {\n /** `frontend/src/modules/<m>/app-level-views/onboarding-views.definitions.ts` — an embedded onboarding document. */\n ONBOARDING_DOCUMENT = 'ONBOARDING_DOCUMENT',\n /** `frontend/src/modules/<m>/app-level-views/guidance-flows.definitions.ts` — a triggered guidance flow. */\n GUIDANCE_FLOW = 'GUIDANCE_FLOW',\n}\n\n/**\n * The two worker runtimes the framework composes (`add-worker-node`, `add-worker-rust`). The\n * runtime decides the entry file a landing probe reads and whether a typecheck exists to run: a\n * Node worker is verified by its package typecheck, a Rust worker has no TypeScript to check and\n * the policy says so rather than inventing a command.\n *\n * Not the SaaS config's `WorkerRuntime`, which is a free-form `{ type, language }` pair an\n * application authors for deployment; this is the closed set a creation run can COMPOSE.\n */\nexport enum BuildPlanWorkerRuntime {\n NODE = 'NODE',\n RUST = 'RUST',\n}\n\n/**\n * WHERE a provider is bound — which runtime owner's scope its declaration lands in. Each member\n * is a different file, so a probe and a write grant both derive from it.\n *\n * Named after the SaaS config's own scope keys (`providers.scopes.backend`, `.companion`,\n * `.frontendServices.app`, `.frontendServices.website`), which the `add-provider` and\n * `add-file-picker-provider` scenarios write. Minion and worker scopes are deliberately absent:\n * a provider reaching a minion is declared on that minion's own `providers` block and belongs to\n * the {@link BuildPlanTaskTargetKind.MINION} task that builds it.\n */\nexport enum ProviderBindingScope {\n BACKEND = 'BACKEND',\n COMPANION = 'COMPANION',\n FRONTEND_APP = 'FRONTEND_APP',\n WEBSITE = 'WEBSITE',\n}\n\n/** The per-resource build stages, in their fixed order. */\nexport enum BuildPlanResourceStage {\n SCHEMA = 'SCHEMA',\n CONFIG = 'CONFIG',\n UI_BEHAVIOR = 'UI_BEHAVIOR',\n SPEC = 'SPEC',\n}\n\nconst SlugSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);\n\n/**\n * The key of the domain-plan MODULE a task targets or produces (`deals`, `tasks-manager`). Same\n * slug grammar as the other keys, declared as its own schema because it names one thing — a\n * module — where the other slugs name resources, relationships, steps, workers and products.\n */\nconst ModuleRefSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);\n\n/**\n * The governed document a task produces, named as a COMPLIANCE-DOCUMENT CANDIDATE names it:\n * `document:<namespace>.<id>`, e.g. `document:public.privacy-notice`.\n *\n * **This field was `SlugSchema`, and a slug cannot name a governed document — so until 2026-09-16 no\n * build plan in any application could declare a document the engine catalog defines.** A slug forbids\n * the colon and the dot, the catalog's definitions are `document-definition:public.privacy-notice`,\n * and `selectAssuranceDocumentBlueprintForDocumentRef` joins the two namespaces by exact suffix — so\n * every authored `documentRef` resolved to NO blueprint, and a blueprint is what says which sections,\n * facts and claim guards the document owes. The two vocabularies were disjoint by construction.\n *\n * The cost is measured rather than theoretical. Wonder CRM's plan declares two such products\n * (`gdpr-data-handling-governance`, `terminal-access-governance`), neither of which names anything;\n * the first was dispatched, and its agent spent a full turn establishing — with a positive control —\n * that the document does not exist and could only be invented, which the authoring skill forbids.\n *\n * The bare slug is STILL ACCEPTED, and that is deliberate rather than tidiness left undone: tightening\n * this to the namespaced form alone would make every already-accepted plan carrying one fail to parse,\n * and a build plan that cannot be READ stops the whole lane — the gate\n * `application-creation-directive.md` forbids, for a task nobody can fix by re-running anything. A slug\n * simply resolves to no blueprint, so the dispatcher skips that task with a message naming the ref,\n * and the rest of the plan proceeds.\n */\nconst DocumentProductRefSchema = z.union([\n z.string().regex(/^document:[a-z0-9]+(?:-[a-z0-9]+)*\\.[a-z0-9]+(?:-[a-z0-9]+)*$/),\n SlugSchema,\n]);\n/**\n * A skill ref is the skill's FOLDER id in the app-knowledge catalog, which is\n * also its `SKILL.md` frontmatter `name` — one id, kebab-case. The host refuses\n * any skill name outside `[a-z0-9-]+`, so a ref that does not match this shape\n * can never resolve to an installed skill.\n */\nconst SkillRefSchema = z.string().regex(/^[a-z0-9]+(?:-[a-z0-9]+)*$/);\nconst NonEmptyStringSchema = z.string().trim().min(1);\n\n/**\n * WHAT a build task PRODUCES — the artifact whose presence in the application\n * proves the task is done.\n *\n * **This is not `target`, and the difference is the whole reason it exists.**\n * `target` is a WRITE SCOPE: the host turns it into the path prefixes a run may\n * mutate, and several tasks legitimately share one. `produces` is a PRODUCT\n * IDENTITY: it says which artifact this task, and no other, is accountable for.\n *\n * Measured 2026-09-10 on Wonder CRM (issue #597): `build-task-pipeline-view`\n * and `build-task-deal-follow-through-operation` carry BYTE-IDENTICAL targets\n * (`{ kind: MODULE, moduleRef: 'deals' }`), and 7 of that plan's 42 tasks share\n * 3 targets. Landing had been answered by narrowing the target to a module\n * DIRECTORY — which `wildo compose` commits on day one, and which cannot tell\n * two tasks apart even in principle. The loop reported 40 of 42 tasks landed\n * while no coding task had ever run, so `dispatch-next` skipped every one of\n * them and the phase-advance gate read a build that was all but complete.\n *\n * Like `target`, this stays SEMANTIC: a product names a resource, a field, a\n * relationship or a view — never a path, and never a command. The host owns the\n * translation from a product to the physical question it asks of the working\n * tree, exactly as it owns the translation from a target kind to path prefixes.\n * A model that could author the path could author its own mutation scope.\n */\nexport enum BuildPlanTaskProductKind {\n /**\n * Named fields on one resource's schema.\n *\n * The shape an ENRICHMENT task needs, and the reason a product cannot always\n * be \"a file\": every resource file already exists, written by the scaffold\n * with its self-described STARTER shape, so file presence answers nothing.\n * The FIELDS are what the task adds.\n */\n RESOURCE_SCHEMA_FIELDS = 'RESOURCE_SCHEMA_FIELDS',\n /**\n * One resource's declared operations — its registry presence, named by the verbs it gains.\n *\n * The VERBS, not the config file: `<r>.resources-config.ts` is written by the scaffold, so its\n * existence is satisfied before any task runs. That is the exact shape of the defect this\n * vocabulary replaces, and a kind that reproduced it would be worse than no kind at all.\n */\n RESOURCE_REGISTRATION = 'RESOURCE_REGISTRATION',\n /** One resource's frontend ui-behavior. */\n RESOURCE_UI_BEHAVIOR = 'RESOURCE_UI_BEHAVIOR',\n /**\n * One resource's specification, named by the fields it documents.\n *\n * The FIELDS, for the same reason as {@link RESOURCE_REGISTRATION}: every resource is scaffolded\n * with a `*.resource.specification.ts` documenting only the starter shape, so file existence\n * proves nothing about the task that was meant to enrich it.\n */\n RESOURCE_SPECIFICATION = 'RESOURCE_SPECIFICATION',\n /** One relationship edge between two resources, named by the domain plan's `relationshipRef`. */\n RESOURCE_RELATIONSHIP = 'RESOURCE_RELATIONSHIP',\n /** One named custom operation on one resource. */\n RESOURCE_OPERATION = 'RESOURCE_OPERATION',\n /** One named application-level view. */\n APPLICATION_VIEW = 'APPLICATION_VIEW',\n /** One named governed application document (a compliance notice, a governance statement). */\n APPLICATION_DOCUMENT = 'APPLICATION_DOCUMENT',\n /** One application module, registered across the layer registries under one module identity. */\n APPLICATION_MODULE = 'APPLICATION_MODULE',\n /*\n * THE NON-RESOURCE PRODUCTS (#1490). Each names an artifact of a surface the five target kinds\n * above `MODULE_FRONTEND` could not express, and each is probed by the host from committed bytes —\n * a declaration in the one file that registers it, never a directory a scenario already wrote.\n */\n /**\n * Named declarations in ONE application-wide frontend configuration file — a sidebar section\n * ref the app shell gains, a zone the navigation config declares, a token the design system sets.\n *\n * The DECLARATIONS, never the file: every `frontend/src/config/*.config.ts` is written by\n * `wildo init`, so its presence is true before any task runs. Same reasoning as\n * {@link RESOURCE_SCHEMA_FIELDS}, one level up.\n */\n APPLICATION_FRONTEND_CONFIG = 'APPLICATION_FRONTEND_CONFIG',\n /**\n * One composite view of one resource — the cross-resource surface a resource's ui-behavior\n * declares under `compositeViews`. Distinct from {@link APPLICATION_VIEW}, which is\n * application-level and owned by a module rather than a resource.\n */\n RESOURCE_COMPOSITE_VIEW = 'RESOURCE_COMPOSITE_VIEW',\n /** One custom operation or execution view of one resource, bound in its ui-behavior. */\n RESOURCE_CUSTOM_VIEW = 'RESOURCE_CUSTOM_VIEW',\n /** One chart view of one resource, declared under its ui-behavior's `chartViews`. */\n RESOURCE_CHART_VIEW = 'RESOURCE_CHART_VIEW',\n /** One custom frontend component, registered by `componentRef` in the module's or the engine's registrations. */\n CUSTOM_COMPONENT = 'CUSTOM_COMPONENT',\n /**\n * One milestone a module declares — the moment the application recognises and celebrates.\n *\n * Named by its identifier, which is what the module's `milestones.ts` declares\n * (`first-project-created` is spelled `FIRST_PROJECT_CREATED` there). The module FILE is not the\n * product: a module may carry milestones before this task runs, and only the identifier says this\n * one landed.\n */\n APPLICATION_MILESTONE = 'APPLICATION_MILESTONE',\n /** One onboarding document or guidance flow a module declares, named by its ref. */\n APPLICATION_GUIDANCE = 'APPLICATION_GUIDANCE',\n /** One PDF template bound to one resource's generated-file field. */\n PDF_TEMPLATE = 'PDF_TEMPLATE',\n /**\n * One worker's JOBS — the named handlers its entry file declares.\n *\n * The jobs, not the package: `add-worker-node` writes the package, so its directory proves\n * nothing. What a coding task adds is behaviour, and behaviour is a symbol in the entry file.\n */\n APPLICATION_WORKER = 'APPLICATION_WORKER',\n /** One minion's BEHAVIOURS — the named tick handlers its entry file declares. Same reasoning as the worker. */\n APPLICATION_MINION = 'APPLICATION_MINION',\n /** One provider declared in one runtime owner's scope. */\n PROVIDER_BINDING = 'PROVIDER_BINDING',\n /**\n * One product of the application's billing catalogue — a plan, add-on or purchase the application\n * sells — named by its catalogue `key`, which the catalogue file declares (`key: 'team'`).\n *\n * The KEY, not the file: `wildo init` writes `product.ts` with an empty catalogue, so the file proves\n * nothing. Written from the accepted business model's pricing plans, with the plan's price as typed\n * money and the pricing-surface facts (recommended, price disclosure, availability) the plan implies.\n */\n APPLICATION_BILLING_PRODUCT = 'APPLICATION_BILLING_PRODUCT',\n /** One website page, registered in the website root config by its manifest. */\n WEBSITE_PAGE = 'WEBSITE_PAGE',\n /** One section of one website page, declared in that page's sections file. */\n WEBSITE_SECTION = 'WEBSITE_SECTION',\n /**\n * One authored documentation chapter — a consumer guide the specifications package declares\n * for the documentation portal to publish (#874's publication input).\n */\n DOCUMENTATION_CHAPTER = 'DOCUMENTATION_CHAPTER',\n /**\n * One inbound CHANNEL handler — the code that decides what a message arriving on a channel causes\n * (#1832). Named by the handler's `ref` (`matters.mail-intake`), which the handler file spells and whose\n * file NAME is derived from it, so the module index's import of that file is what proves the handler is\n * registered. Produced once per channel the integration plan declares (`inboundChannels`).\n */\n INBOUND_CHANNEL_HANDLER = 'INBOUND_CHANNEL_HANDLER',\n}\n\n/**\n * One artifact a task is accountable for. Closed by construction: a product the\n * host cannot ask a question about is a product that can never be shown to have\n * landed, so the vocabulary only grows alongside the resolver that answers it.\n */\nexport const BuildPlanTaskProductSchema = z.discriminatedUnion('kind', [\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.RESOURCE_SCHEMA_FIELDS).systemEnum('BuildPlanTaskProductKind'),\n resourceRef: SlugSchema,\n /**\n * At least one field, because a task that enriches a schema with nothing is\n * the vacuity this whole field exists to stop: it would land the moment the\n * scaffold existed, which is the defect being fixed.\n */\n fieldRefs: z.array(NonEmptyStringSchema).min(1),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_REGISTRATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, operationRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_UI_BEHAVIOR).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_SPECIFICATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, fieldRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.RESOURCE_RELATIONSHIP).systemEnum('BuildPlanTaskProductKind'),\n relationshipRef: SlugSchema,\n /*\n * The two resources the edge relates, NAMED rather than parsed out of the ref.\n *\n * A ref is `<source>-<target>` by convention and that convention is not invertible:\n * `next-step-deal` splits as (`next`, `step-deal`) or (`next-step`, `deal`) and only the domain\n * plan knows which. The domain plan already carries both, so the plan passes them on instead of\n * making the host guess — a host that guesses wrong probes for a resource that does not exist\n * and reports the task permanently unlanded.\n */\n sourceResourceRef: SlugSchema,\n targetResourceRef: SlugSchema,\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_OPERATION).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, operationRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_VIEW).systemEnum('BuildPlanTaskProductKind'), viewRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_DOCUMENT).systemEnum('BuildPlanTaskProductKind'), documentRef: DocumentProductRefSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MODULE).systemEnum('BuildPlanTaskProductKind'), moduleRef: ModuleRefSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.APPLICATION_FRONTEND_CONFIG).systemEnum('BuildPlanTaskProductKind'),\n configSurface: z.enum(FrontendConfigSurface).systemEnum('FrontendConfigSurface'),\n /** At least one, for the same vacuity reason as a schema's `fieldRefs`: the file exists on day one. */\n declarationRefs: z.array(NonEmptyStringSchema).min(1),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_COMPOSITE_VIEW).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, viewRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_CUSTOM_VIEW).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, viewRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.RESOURCE_CHART_VIEW).systemEnum('BuildPlanTaskProductKind'), resourceRef: SlugSchema, chartRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.CUSTOM_COMPONENT).systemEnum('BuildPlanTaskProductKind'), componentRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MILESTONE).systemEnum('BuildPlanTaskProductKind'), milestoneRef: SlugSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.APPLICATION_GUIDANCE).systemEnum('BuildPlanTaskProductKind'),\n /** Which definitions file carries it — a document and a flow live in different ones. */\n guidanceKind: z.enum(ApplicationGuidanceKind).systemEnum('ApplicationGuidanceKind'),\n guidanceRef: SlugSchema,\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.PDF_TEMPLATE).systemEnum('BuildPlanTaskProductKind'),\n resourceRef: SlugSchema,\n /** The generated-file FIELD the template is bound to (`generatedSummaryPdf`) — a symbol, so any spelling. */\n templateRef: NonEmptyStringSchema,\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_WORKER).systemEnum('BuildPlanTaskProductKind'), workerRef: SlugSchema, jobRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_MINION).systemEnum('BuildPlanTaskProductKind'), minionRef: SlugSchema, behaviorRefs: z.array(NonEmptyStringSchema).min(1) }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.PROVIDER_BINDING).systemEnum('BuildPlanTaskProductKind'),\n providerRef: SlugSchema,\n scope: z.enum(ProviderBindingScope).systemEnum('ProviderBindingScope'),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_BILLING_PRODUCT).systemEnum('BuildPlanTaskProductKind'), productKey: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_PAGE).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_SECTION).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema, sectionRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER).systemEnum('BuildPlanTaskProductKind'), chapterRef: SlugSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskProductKind.INBOUND_CHANNEL_HANDLER).systemEnum('BuildPlanTaskProductKind'),\n /** The channel the handler serves — one the integration plan declared. Email is the only declarable channel. */\n channel: z.literal(InboundChannelKind.EMAIL).systemEnum('InboundChannelKind'),\n /** The handler's `ref`, exactly as `inboundHandlerRef()` will accept it. */\n handlerRef: z.string().regex(INBOUND_HANDLER_REF_PATTERN),\n }),\n]);\nexport type BuildPlanTaskProduct = z.infer<typeof BuildPlanTaskProductSchema>;\n\n/**\n * Every artifact identity a product claims — one string per artifact, not one\n * per product, because a product may claim several.\n *\n * `RESOURCE_SCHEMA_FIELDS` is why this returns a list. Two tasks may both enrich\n * one resource's schema (a domain shape and a billing concern, say), and that is\n * legitimate; what must never overlap is the FIELDS. Comparing whole products\n * would refuse the legitimate pair, and comparing only the resource would let two\n * tasks claim one field and make landing ambiguous again.\n *\n * Derived from the product's own members rather than stored, and total over the\n * vocabulary, so a kind added tomorrow must state its identity here or fail to\n * compile — it cannot be silently treated as equal to its siblings.\n */\nexport function buildPlanTaskProductIdentities(product: BuildPlanTaskProduct): readonly string[] {\n switch (product.kind) {\n case BuildPlanTaskProductKind.RESOURCE_SCHEMA_FIELDS:\n return product.fieldRefs.map((fieldRef) => `${product.kind}:${product.resourceRef}:${fieldRef}`);\n case BuildPlanTaskProductKind.RESOURCE_REGISTRATION:\n return product.operationRefs.map((operationRef) => `${product.kind}:${product.resourceRef}:${operationRef}`);\n case BuildPlanTaskProductKind.RESOURCE_SPECIFICATION:\n return product.fieldRefs.map((fieldRef) => `${product.kind}:${product.resourceRef}:${fieldRef}`);\n case BuildPlanTaskProductKind.RESOURCE_UI_BEHAVIOR:\n return [`${product.kind}:${product.resourceRef}`];\n case BuildPlanTaskProductKind.RESOURCE_RELATIONSHIP:\n return [`${product.kind}:${product.relationshipRef}`];\n case BuildPlanTaskProductKind.RESOURCE_OPERATION:\n return [`${product.kind}:${product.resourceRef}:${product.operationRef}`];\n case BuildPlanTaskProductKind.APPLICATION_VIEW:\n return [`${product.kind}:${product.viewRef}`];\n case BuildPlanTaskProductKind.APPLICATION_DOCUMENT:\n /*\n * The ref AS AUTHORED, so a slug and a namespaced ref are different artifact identities even\n * where they mean the same document — the duplicate-artifact refusal cannot see two tasks\n * claiming one document if they spell it differently. Not normalisable: a slug carries no\n * namespace, so nothing can recover `public.` from `privacy-notice`. It costs nothing today\n * because a slug names no catalogued document at all, and the dispatcher skips such a task.\n */\n return [`${product.kind}:${product.documentRef}`];\n case BuildPlanTaskProductKind.APPLICATION_MODULE:\n return [`${product.kind}:${product.moduleRef}`];\n // One identity per DECLARATION, like schema fields: two tasks may compose one config file as\n // long as they declare different things in it.\n case BuildPlanTaskProductKind.APPLICATION_FRONTEND_CONFIG:\n return product.declarationRefs.map((declarationRef) => `${product.kind}:${product.configSurface}:${declarationRef}`);\n case BuildPlanTaskProductKind.RESOURCE_COMPOSITE_VIEW:\n case BuildPlanTaskProductKind.RESOURCE_CUSTOM_VIEW:\n return [`${product.kind}:${product.resourceRef}:${product.viewRef}`];\n case BuildPlanTaskProductKind.RESOURCE_CHART_VIEW:\n return [`${product.kind}:${product.resourceRef}:${product.chartRef}`];\n case BuildPlanTaskProductKind.CUSTOM_COMPONENT:\n return [`${product.kind}:${product.componentRef}`];\n case BuildPlanTaskProductKind.APPLICATION_MILESTONE:\n return [`${product.kind}:${product.milestoneRef}`];\n // The ref alone: a document and a flow sharing one ref is still one guidance identity, and the\n // runtime keys a person's saved state by it — two artifacts claiming it would collide there too.\n case BuildPlanTaskProductKind.APPLICATION_GUIDANCE:\n return [`${product.kind}:${product.guidanceRef}`];\n case BuildPlanTaskProductKind.PDF_TEMPLATE:\n return [`${product.kind}:${product.resourceRef}:${product.templateRef}`];\n case BuildPlanTaskProductKind.APPLICATION_WORKER:\n return product.jobRefs.map((jobRef) => `${product.kind}:${product.workerRef}:${jobRef}`);\n case BuildPlanTaskProductKind.APPLICATION_MINION:\n return product.behaviorRefs.map((behaviorRef) => `${product.kind}:${product.minionRef}:${behaviorRef}`);\n // The SCOPE is part of the identity: one provider bound on the backend and on the website is two artifacts.\n case BuildPlanTaskProductKind.PROVIDER_BINDING:\n return [`${product.kind}:${product.scope}:${product.providerRef}`];\n case BuildPlanTaskProductKind.APPLICATION_BILLING_PRODUCT:\n return [`${product.kind}:${product.productKey}`];\n case BuildPlanTaskProductKind.WEBSITE_PAGE:\n return [`${product.kind}:${product.pageRef}`];\n case BuildPlanTaskProductKind.WEBSITE_SECTION:\n return [`${product.kind}:${product.pageRef}:${product.sectionRef}`];\n case BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER:\n return [`${product.kind}:${product.chapterRef}`];\n case BuildPlanTaskProductKind.INBOUND_CHANNEL_HANDLER:\n return [`${product.kind}:${product.handlerRef}`];\n default: {\n const unhandled: never = product;\n throw new Error(`Unhandled build-plan task product ${JSON.stringify(unhandled)}.`);\n }\n }\n}\n\n/**\n * The skill every billing-catalogue task is authored with (#1835): the product-catalogue contract, the\n * money encoding (minor units), and the pricing-surface facts. The dispatch derives it from an\n * `APPLICATION_BILLING_PRODUCT` product whatever the decomposer wrote, so an agent writing the catalogue\n * the backend sells from is never without it.\n */\nexport const BILLING_CATALOG_SKILL_REF = 'configure-billing';\n\nexport const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE), moduleRef: ModuleRefSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.RESOURCE_STAGE),\n moduleRef: ModuleRefSchema,\n resourceRef: SlugSchema,\n stage: z.enum(BuildPlanResourceStage),\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.RELATIONSHIP),\n moduleRef: ModuleRefSchema,\n relationshipRef: SlugSchema,\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.COMPANION_GENERATION_STEP),\n /** The companion generation step this task runs (e.g. i18n-labels, email-templates); resolved by the companion, never by a coding agent. */\n generationStepRef: SlugSchema,\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.SHELL_PLACEMENT),\n /**\n * Which shell surface this task authors — the placement family's OWN\n * `PlacementSurface`, deliberately not a build-plan copy of it.\n *\n * A copy was written first and was a defect, caught by probing the landing\n * renderer rather than by any test: `PlacementAddress` discriminates on\n * `surface` with `z.literal(...)` per option, so only the VALUES survive into\n * the schema, and the renderer resolves a discriminator by matching that value\n * SET against the exported enums. Two enums with identical values made the\n * match ambiguous, the renderer correctly refused to guess an owner, and the\n * address discriminator became unnameable — a landed placement plan would have\n * emitted `surface: \"SETTINGS_HUB\"` as a bare string instead of\n * `PlacementSurface.SETTINGS_HUB`. One concept, one named source.\n */\n surface: z.enum(PlacementSurface).systemEnum('PlacementSurface'),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_FRONTEND), moduleRef: ModuleRefSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE_BACKEND), moduleRef: ModuleRefSchema }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.APPLICATION_FRONTEND_CONFIG),\n configSurface: z.enum(FrontendConfigSurface).systemEnum('FrontendConfigSurface'),\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.WEBSITE) }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.TECHNICAL_DOCUMENTATION) }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.WORKER),\n /** The worker's directory under `workers/` and its key in the SaaS config, in slug form. */\n workerRef: SlugSchema,\n runtime: z.enum(BuildPlanWorkerRuntime).systemEnum('BuildPlanWorkerRuntime'),\n }),\n z.strictObject({\n kind: z.literal(BuildPlanTaskTargetKind.MINION),\n /** The minion's directory under `minions/` and its key in the SaaS config, in slug form. */\n minionRef: SlugSchema,\n }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.PROVIDER_BINDING), providerRef: SlugSchema }),\n z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.BILLING_CATALOG) }),\n]);\nexport type BuildPlanTaskTarget = z.infer<typeof BuildPlanTaskTargetSchema>;\n\n/**\n * One ordered build task. It names WHAT to build and WHY; it never carries\n * HOW (no paths, commands, prompts, cwd, model, profile). The host resolves\n * the physical allowed/prohibited paths and the fixed verification from the\n * target kind, and the installed skills from `skillRefs` against the app\n * knowledge catalog.\n *\n * Dependency readiness is DECLARED as prerequisite task refs and RESOLVED by\n * the host (a prerequisite is satisfied when its task has landed), never a\n * solved DAG the model must get right.\n */\nexport const BuildPlanTaskSchema = z.strictObject({\n /** `build-task-<slug>`, stamped by the trusted runtime. */\n taskRef: z.string().regex(new RegExp(`^${BUILD_PLAN_TASK_REF_PREFIX}[a-z0-9]+(?:-[a-z0-9]+)*$`)),\n /**\n * One sentence of intent: what this task delivers.\n *\n * Its OWN instance, not the file's shared leaf, which `templateRef` and the product ref lists also\n * hold. A display decorator mutates the instance it is applied to, and the workbench gives those\n * refs a receding identifier look, which the objective sentence then took too.\n */\n objective: z.string().trim().min(1),\n target: BuildPlanTaskTargetSchema,\n /**\n * The artifacts this task is accountable for — what proves it done.\n *\n * Coding tasks should declare at least one product that composition did not already\n * write. A target is a shared mutation scope; its scaffolded file is not evidence\n * that this task's intended work exists. Products identify the output to probe.\n *\n * Empty declarations remain representable and produce the advisory\n * `TASK_DECLARES_NO_PRODUCT`. The host may advance after a COMPLETED durable run,\n * while naming the task in `unverifiableLandedTaskRefs`: it ran, but its output\n * cannot be proven from a product declaration. An unexecuted task is not landed.\n * This distinction avoids repeatedly dispatching the same unprovable task without\n * presenting execution history as evidence that the intended product is correct.\n *\n * The ONE hard exception is a `COMPANION_GENERATION_STEP`, which must declare NONE.\n * That kind already carries its own typed landed condition, owned by the\n * generation-step service — a set computed asynchronously (planner units x\n * enabled locales), and for the migration step a STATE rather than files. A\n * product declared beside it would be read by nothing, which is the inert\n * declaration this field exists to avoid. Enforced on the graph below, in both\n * directions.\n */\n produces: z.array(BuildPlanTaskProductSchema).default([]),\n /**\n * Exactly ONE functional topic this task belongs to.\n *\n * **It does NOT drive ordering** — this said \"drives cross-app ordering\" until 2026-08-30 and\n * nothing ever ordered by it. Sequencing is `prerequisiteTaskRefs`, resolved by the host, and it\n * is the only thing that decides what may run next.\n *\n * What it DOES: the dispatch host stamps it into the coding-agent's task payload beside\n * `skillRefs`, so the agent is told which phase of building the application this task belongs to.\n * That is context an LLM reads, not a value the runtime branches on — the distinction matters,\n * because a reader who believes it orders will look here for a scheduling bug that lives in the\n * prerequisite graph. See issue #124.\n */\n functionalTopic: z.enum(MetaWorkflow_FunctionalTopic).systemEnum('MetaWorkflow_FunctionalTopic'),\n /** Installed app-knowledge skill folders that carry the technical HOW; resolved via the skills router at dispatch. */\n skillRefs: z.array(SkillRefSchema).min(1),\n /** Task refs that must have landed first; resolved by the host, not solved by the model. */\n prerequisiteTaskRefs: z.array(z.string()).default([]),\n /**\n * What this task is accountable to — traceability only, NEVER scope authority.\n *\n * The vocabulary is the five aspects `BUILD_PLAN_FAMILY_ASPECTS` declares as targets: functional\n * and non-functional requirements, roadmap phases, and the vision's success criteria and\n * constraints. It reads \"Requirement / roadmap refs\" until 2026-09-11, and the last two were added\n * because the producer had been writing them all along (#629) — the generation contract asks for a\n * plain string list, so nothing here has ever refused a key.\n *\n * A key outside those five is not rejected and must not be: this is traceability a human or a\n * model wrote down, and dropping it loses the intent. The workbench renders such a key as visibly\n * unresolved instead, which is what makes a producer drift legible rather than silent.\n */\n servesRefs: z.array(NonEmptyStringSchema).default([]),\n /**\n * Who asked for this task DIRECTLY (#1608), rather than it being derived from the specifications: the\n * signed-in person who added it in conversation. STAMPED by the append, never authored: a value in\n * generated output is discarded. Absent on every task the decomposition derived.\n *\n * It is what keeps a requested task alive. Build decomposition refines the plan from the domain plan, and\n * a task nothing in the specifications justifies would read as unjustified and be dropped; a requested\n * task it leaves out is carried forward instead, keeping only the prerequisites the new plan still holds.\n */\n requestedBy: NonEmptyStringSchema.optional(),\n});\nexport type BuildPlanTask = z.infer<typeof BuildPlanTaskSchema>;\n\n/**\n * THE build-plan payload — a **single aggregate per product**: the ORDERED\n * task graph that turns the accepted domain plan into buildable units.\n *\n * **Artifact-family id: `build-plan`.** This schema is the shape of the\n * journey artifact selected by `MetaWorkflow_ArtifactSelector.family ===\n * 'build-plan'` (the `family` vocabulary stays an open string owned by the\n * selector surface; this note is the single place tying the SHAPE to the\n * NAME). Produced by the build-decompose playbook, consumed one task at a\n * time by build-dispatch (single-flight coding dispatch) and by the scale\n * playbook.\n *\n * Invariants enforced here: unique task refs; every prerequisite names a task\n * in this graph; no self-prerequisite. Cycle detection and ordering\n * soundness are the deterministic validator's job (`validateBuildPlanTaskGraph`).\n */\nexport const BuildPlanTaskGraphSchema = z.object({\n version: z.enum(BuildPlanTaskGraphVersion).default(BuildPlanTaskGraphVersion.V1),\n /**\n * At least one task, at the SCHEMA — not merely as a validator warning. The first live playbook-loop\n * run (2026-08-24) proved why: build-decompose answered `tasks: []`, which was schema-valid, passed\n * `_core` validation as a mere warning, and LANDED — overwriting a completed 3-task plan with a\n * vacuous artifact. Decomposing to zero tasks is a refusal (\"nothing to decompose\"), never an\n * artifact: an empty plan carries no information a reader could act on, and the file it replaces\n * does. Same vacuity class already closed on the requirements family (`functional: min(1)`).\n */\n tasks: z.array(BuildPlanTaskSchema).min(1),\n}).superRefine((graph, context) => {\n const refs = new Set<string>();\n graph.tasks.forEach((task, index) => {\n if (refs.has(task.taskRef)) {\n context.addIssue({ code: 'custom', message: `duplicate build task ref \"${task.taskRef}\"`, path: ['tasks', index, 'taskRef'] });\n }\n refs.add(task.taskRef);\n });\n /*\n * No two tasks claim the same artifact.\n *\n * This is what makes landing DECIDABLE, not a tidiness rule. If two tasks name\n * one product, the host cannot tell which of them a present artifact proves —\n * exactly the ambiguity that shared `target`s created, arriving through the\n * field that replaced them. Enforced here rather than left to the validator\n * because a graph that cannot answer \"has this task landed?\" is not a graph\n * the loop may run at all.\n */\n graph.tasks.forEach((task, index) => {\n const isGenerationStep = task.target.kind === BuildPlanTaskTargetKind.COMPANION_GENERATION_STEP;\n if (isGenerationStep && task.produces.length > 0) {\n context.addIssue({\n code: 'custom',\n message: `build task \"${task.taskRef}\" is a companion generation step and must declare no products; its landing is the generation step's own condition`,\n path: ['tasks', index, 'produces'],\n });\n }\n });\n const productOwners = new Map<string, string>();\n graph.tasks.forEach((task, index) => {\n task.produces.forEach((product, productIndex) => {\n buildPlanTaskProductIdentities(product).forEach((identity) => {\n const owner = productOwners.get(identity);\n if (owner !== undefined) {\n context.addIssue({\n code: 'custom',\n message: `build task \"${task.taskRef}\" claims the same artifact as \"${owner}\" (${identity}); an artifact is produced by exactly one task`,\n path: ['tasks', index, 'produces', productIndex],\n });\n return;\n }\n productOwners.set(identity, task.taskRef);\n });\n });\n });\n graph.tasks.forEach((task, index) => {\n task.prerequisiteTaskRefs.forEach((prerequisite, prerequisiteIndex) => {\n if (prerequisite === task.taskRef) {\n context.addIssue({ code: 'custom', message: `build task \"${task.taskRef}\" cannot be its own prerequisite`, path: ['tasks', index, 'prerequisiteTaskRefs', prerequisiteIndex] });\n } else if (!refs.has(prerequisite)) {\n context.addIssue({ code: 'custom', message: `build task \"${task.taskRef}\" names an unknown prerequisite \"${prerequisite}\"`, path: ['tasks', index, 'prerequisiteTaskRefs', prerequisiteIndex] });\n }\n });\n });\n});\nexport type BuildPlanTaskGraph = z.infer<typeof BuildPlanTaskGraphSchema>;\n```\n\n## What this playbook does\n\nYou are the **dispatch orchestrator**. This playbook reads the approved build plan\nand the current journey state and answers, for *one* task at a time: *\"dispatch this\ntask safely, verify it, and record what happened.\"* You do **not** produce a new\njourney artifact — the dispatch's observable result (the change-set + the task\nstatus) is materialized by the runner on the task row, not authored here (see \"What\nyou emit\"). You do **not** decompose the plan, author any schema, or write any code\n— the coding agent writes the code at dispatch time; the plan is the\nbuild-decompose playbook's; scale is the scale playbook's.\n\n## The dispatch contract — the runner owns the mechanism, you sequence it\n\nMost of the D4 dispatch contract is **runner mechanism**, not prose you re-implement:\nthe runner composes the context pack, opens a coding session with the agent over the\nAgent Client Protocol and sends one prompt turn, answers the agent's permission\nrequests within the declared ceiling, captures the change-set, runs the verify hook,\nholds the single-flight lock and applies its configured execution limits. Your method here is the **declarative recipe** the runner interprets —\n*which* task to dispatch next, *when* it is authorized, and *how* its outcome is\njudged. Do not hand-compose a dispatch prompt or drive git yourself; let the runner\nown composition and change-set capture.\n\n## Read state first — no artifact to write\n\nThis playbook is **idempotent** and, on a re-run, *advances the loop by one task*.\nBefore dispatching anything:\n\n1. Read the current journey state and scope from what this run is given — the loaded\n specifications and the workspace sections of your brief — and do not re-derive it. Confirm the **build plan** is present\n and approved, and confirm the **foundation** ran. For each build-plan task,\n determine its dispatch state from its task row — **not yet dispatched**,\n **dispatched-and-succeeded** (a captured change-set + a passed verify), or\n **dispatched-and-failed** (a captured change-set but a failed/timed-out run or a\n failed verify). This tri-state matters: under `keep_and_flag` a **failed** task\n *also* has a captured change-set, so \"has a change-set\" alone does NOT mean the\n task is done — read the task's terminal status + verify outcome, not just the\n presence of a change-set.\n2. Read the approved **build plan** (`build-plan` — the ordered task graph). It is your\n work list.\n\n Evidence that the foundation ran is `./wildo.saas.config.ts` itself, committed: the\n app either has a config and a skeleton or it does not, and git answers that without a\n journey artifact standing in for it. (A `foundation-manifest` family was that stand-in\n until 2026-08-25; it was retired with the app-creation verification/digest aspect, and\n this playbook no longer gates on it.) The honest limitation inherited from the\n foundation step still applies: at scaffold depth the on-disk skeleton *materialization*\n depends on greenfield bring-up tooling (deferred). The dispatch contract is real and\n runs against an **existing** app skeleton — the dogfood app already has one.\n\n// Operator status: `wildo context journey` (eligibility board + runs in flight). Which tasks already\n// landed is read from GIT by the runner itself — a task is landed when every file it produces is\n// committed clean.\n\nYou **read** `build-plan`; you **write** no journey artifact\n— the runner records the change-set + task status on the dispatched task's row.\n\n## Precondition — the application must establish the agent's role, or dispatch stalls\n\nCheck this before the first dispatch of an application's life. It costs one look and it is the\ndifference between a working lane and one that burns model time producing nothing.\n\n**The application needs a root `CLAUDE.md` stating that a task dispatched by its dev companion is\nlegitimate work.** Without it the agent is right to refuse, and refusing is what it does.\n\nThe reason is structural rather than a matter of tone. A dispatched task reaches the agent as an\nordinary prompt — a user turn carrying an objective, a mutation scope and skill refs. Nothing in\nthat turn proves where it came from. So the agent is being handed conversational content that\ntells it to write files into a repository, which is indistinguishable from the thing every\ncareful agent is supposed to decline, and the more trustworthy the agent the more reliably it\ndeclines. Measured on a real application with no such file: two dispatched runs stalled, one\nanswering *\"content that arrives as conversational input doesn't get to reassign what I am\"*.\n\nThe failure does not look like a missing file. It looks like an agent that deliberates well,\nidentifies exactly which files it would author, explains its reasoning, asks a human to confirm,\nand ends its turn — `end_turn`, no error, no denial, an empty change set, and a bill for the\ntokens. Read as \"the agent chose not to work\", which invites prompt-tuning that cannot fix it.\n\n`wildo init` scaffolds this file. An application created before that, or one whose `CLAUDE.md`\ncovers only its own conventions, needs the section added. What it must establish:\n\n- the task is **selected by the host** from the accepted build plan, not composed by a caller;\n- its **file edits** are **confined before they arrive** — the host answers every permission request\n against the declared mutation scope and refuses paths outside it;\n- its **shell commands are NOT**, and the section must say so. A command declares no `locations`, so\n the scope predicate never runs for one; telling an agent it \"need not police itself\" is true of its\n edits and false of its commands, and that is the half a stray write comes through. Name the\n compensations with it: the post-run change set and the companion's warning DETECT such a write,\n they do not prevent it;\n- it is **reversible** — every write is an uncommitted working edit until something commits it. Do\n not state WHO commits as a property of the lane: that is the host's autonomy posture, it changes,\n and an agent that reads \"a human commits\" from a scaffold written under a different posture is\n working from a stale contract.\n\nTwo smaller things belong in the same section, because both were observed costing a run:\n\n- **Say what `allowedPathPrefixes` are relative to.** The agent receives bare prefixes such as\n `shared-lib/src/modules/<module>/` with no root, and cannot verify its own confinement against\n them. One sentence naming the application root removes the ambiguity.\n- **Do not name a task so it reads as a fixture.** An agent that concludes it is looking at a\n smoke test will say so and stop. Name the task after the product change it makes.\n\n## Step 1 — Select the next dispatchable task (single-flight)\n\nWalk the build plan in its authored order and pick the **first** task that is not\nyet dispatched (or a previously-**failed** task cleared for retry — see Step 5) and\nwhose prose prerequisites have all **succeeded**. Dispatch **exactly one** such task\nper run. If **no** task is ready — every task has already succeeded, or the only\nundispatched tasks are blocked behind a still-unresolved failure — there is nothing\nto dispatch: report the loop as done (or blocked on the failed task) and stop. An\nempty build plan is the same: nothing to dispatch, stop.\n\n- **Single-flight — one workspace-mutating run at a time.** The dispatch lane holds\n ONE workspace-mutation lock for the whole background run; a run plan carries **at\n most one** coding-agent task, and a second concurrent dispatch is refused. This is\n a hard runner floor, not a suggestion — do not try to dispatch two tasks in one\n run to \"go faster\". Batching across many agents is the scale playbook's job.\n- **A prerequisite must have SUCCEEDED, not merely been attempted.** A task is ready\n only when every task it depends on is dispatched-and-succeeded (verify passed).\n A prerequisite that is dispatched-and-**failed** (its change-set is flagged for\n triage under `keep_and_flag`) does **not** satisfy the dependency — its dependents\n stay **blocked** until the failure is triaged and the prerequisite re-dispatched\n successfully. Do not build a config on a schema whose run failed. Never dispatch a\n task before the stage it depends on (a config before its schema, a spec before its\n ui-behavior — the build-decompose playbook ordered these).\n- **Companion-generation steps are not coding-agent dispatches.** A build-plan task\n marked as a companion-owned generation step (labels / i18n, email templates,\n seeds) runs through its deterministic companion endpoint, not the coding-agent\n dispatch lane. Route it there; do not dispatch a coding agent for it. Interleaving\n those steps *concurrently* with coding runs at scale is the scale playbook's job —\n here you simply run the ready one in its turn.\n\n## Step 2 — Check the actual host authorization boundary\n\nA coding dispatch writes the application workspace. Read its selected task, readiness,\nmutation scope and the configured coding host's authorization policy before invoking it.\nThe single-flight mutation lock still applies to the current shared workspace.\n\nThe playbook's `approval` declaration and the journey autonomy presets express policy\nintent. The current playbook runner does not interpret them as pre-dispatch gates,\nautomatic authorization, or a GUIDED/YOLO mapping. A declared `approve_before` does\nnot create a pending Authority Request, and no authority workflow exists to create one —\nnever invent one from an enum.\n\nLikewise, do not infer enforced per-playbook or per-journey run ceilings from declared\nbudget fields. Respect the limits actually reported by the execution host. Inspect the\nrecorded changes and verification result after each task; no preset commits or accepts them.\n\n## Step 3 — Dispatch the task through the coding-agent contract\n\nThe companion triggers the run (from a console, `wildo build run` or `/wildo:build`). The runner then performs the D4\ndispatch contract for you (you do not hand-assemble any of it):\n\n1. **Context pack** — the runner composes the prompt: the task brief, the task's\n skill pointers (`Read .claude/skills/<skillRef>/SKILL.md first` — the per-task\n HOW-skills the build plan named on this task), the relevant journey / definition\n artifacts, an introspected app-reality block, and the repo paths.\n2. **Session and one prompt turn** — the runner starts the agent over the Agent\n Client Protocol and opens a session rooted at the app workspace (cwd = the\n application root, so `./CLAUDE.md`, the sub-`CLAUDE.md`s, and the `.claude/` rules\n and skills load naturally), then sends the task as a single prompt turn. It is a\n session rather than a one-shot process, which is what makes the next three things\n possible at all:\n - **Permissions are answered, not assumed.** The agent asks before each action it\n considers privileged; the runner answers within the execution profile's declared\n ceiling and refuses anything above it, or anything touching a path outside the\n task's mutation scope. Refusals are counted on the task row, so a run that was\n held back is distinguishable from a run that had nothing to do.\n - **The turn can be cancelled.** Cancellation asks the agent to stop and waits, so\n the run terminalises with its change-set intact instead of being killed — an\n operator who stops a run still needs to know what it had already written.\n - **Usage is reported.** Tokens and cost come back from the run itself rather than\n being unavailable, which lets the host report a terminal timeout instead of leaving the run ambiguous.\n3. **Change-set capture** — the runner captures a git worktree snapshot before and\n after the run and attributes each touched file (the run's own edit vs. an\n already-dirty parallel-session file vs. a file that appeared during the run),\n recording a structured change-set on the task row. On the dogfood tree,\n dirty-at-dispatch is the NORMAL state (parallel sessions), so the capture\n *attributes* rather than assuming the run had the tree to itself.\n\n// The trigger is `wildo creation run <playbookRef>` or `wildo build run` (from a Claude Code session,\n// `/wildo:run` or `/wildo:build`), or the workbench; each reaches the companion with its local token.\n// The runner composes the typed context pack, runs one ACP prompt turn, and captures the change-set.\n\n## Step 4 — Verify OUTSIDE the coding agent\n\nTrust, but verify. The verify gate runs **outside** the coding agent, after the run,\nso the agent cannot mark its own homework:\n\n- **`dispatch-typecheck` (deterministic — the auto-run trust floor).** The runner\n maps this `deterministic_validator` gate (`validatorRef: typecheck`) onto the\n dispatch verification hook and runs a typecheck (`pnpm exec tsc --noEmit`) over the\n application workspace after the run, **outside** the coding agent. This is a\n **real, wired** gate — it actually executes and its result is recorded on the task\n row. A run whose typecheck fails is a failed run (apply the failure disposition in\n Step 5). At scaffold depth the gate is a **workspace-wide** typecheck (one static\n gate for every dispatch of this playbook); narrowing it to the specific package a\n given task touched — a per-task `typecheck:<pkgDir>` or a `vitest:<path>` targeted\n at the task's tests — is a later refinement, since a static playbook gate cannot\n vary per task.\n- **`dispatch-outcome-sound` (declarative reviewer checklist).** The six-invariant\n reviewer checklist (task accomplished, change-set scoped to the task, verify ran +\n passed, attribution clean, failure disposition correct, boundary discipline)\n is the *trust-but-verify reviewer* pass. It is **declarative** — the creator's\n review checklist; the compiled build-dispatch Evaluation Treatment is what the\n runtime judges with, and the deterministic typecheck above is what runs\n automatically.\n\n## Step 5 — Record the result and apply the failure disposition\n\nThe runner records the change-set + the task's terminal status on the task row. On a\n**failed or timed-out** run, the current coding host retains its captured changes for inspection (the declaration describes this as **`keep_and_flag`**): the\ncaptured change-set is **kept and flagged for human triage** — never silently\nreverted, and never left as an un-recorded half-applied state. The change-set capture\n*is* the flag: it attributes exactly which files the run touched, so a human can\nreview, keep, or unwind them.\n\n> **Why keep_and_flag, not revert_changeset (a v1 boundary).** Reverting a failed\n> run's edits is a *mutating* git operation, deliberately **outside** the read-only\n> change-set carve-out the dispatch lane observes (the runner *observes* git —\n> baseline/post-run snapshots — but stage/commit/revert stay a human/CLI concern).\n> So `keep_and_flag` is both the correct F-5 workspace-safety posture (no silent\n> half-applied state) and the behavior the runner actually enforces today. Wiring a\n> `revert_changeset` path is a deliberate later boundary decision, not a gap this\n> playbook papers over.\n\nOn a **succeeded** run (change-set captured + verify passed), the task is done and\nits dependents become eligible. On a **failed** run, the task is **not** done — it is\nflagged for human triage, and its dependents stay blocked (Step 1) until it is\ntriaged and cleared for re-dispatch. Triage is a human decision: keep + fix forward,\nunwind the flagged change-set by hand, or re-dispatch the task once its blocker is\nresolved. This playbook does not auto-retry a failed task — automated retry / backoff\nis a deferred build-loop-resilience concern, and human triage is the v1 disposition;\nhere the loop simply surfaces the failure and stops advancing that dependency chain.\n\nThen **loop**: on the next run of this playbook, the build plan's task records reflect the\njust-dispatched task's outcome (`wildo build tasks`), and you select the next ready task\n(Step 1). Close a significant stretch of dispatches with a progress summary — what was\nproduced, which change-sets landed, what verify said, and any failed task left\nflagged for triage.\n\n## Refine, don't re-dispatch\n\n- **Never re-dispatch a SUCCEEDED task.** A task that is dispatched-and-succeeded\n (change-set captured + verify passed) is done — advance to the next ready task, do\n not re-run it because the plan was re-opened elsewhere. A dispatched-and-**failed**\n task is a different case: it is re-dispatchable once triaged (Step 5) — a captured\n change-set alone does not make a task \"finished\".\n- **Follow the plan's order.** If the build plan was refined upstream (a task added,\n an ordering corrected), respect the new order on the next selection — do not cache\n a stale work list across runs.\n- **A host execution refusal is a real stop.** When an actual execution limit is reported, stop dispatching\n and report what remains; do not do the coding work out-of-band to \"finish the\n build\" — that makes the journey's task history a lie.\n\n## Scaffold-depth boundary (owned by a sibling, or deferred to a later phase)\n\nKeep this playbook at **single-flight dispatch depth**. Explicitly **out of scope\nhere**:\n\n- **Re-decomposition.** You do NOT split modules/resources into tasks, re-order the\n graph, or add tasks — the **build-decompose** playbook owns the task graph. You\n read it and dispatch from it.\n- **Multi-agent scale + interleaving.** Running MANY coding agents concurrently, a\n concurrency scheduler, a run-completion serializer, and interleaving the companion\n generation steps *concurrently* with coding runs is the **scale** playbook. You\n dispatch **one** task at a time under the single-flight lock; you do NOT design the\n concurrency schedule.\n- **A `revert_changeset` failure path.** Undoing a failed run's edits is a mutating\n git op outside the read-only change-set carve-out — deferred. `keep_and_flag` (keep\n + flag the captured change-set for triage) is the v1 disposition.\n- **Auto-executed reviewer checklist.** The checklist ships **declarative** —\n the deterministic typecheck gate runs automatically and the compiled Evaluation\n Treatment is the judged protocol; nothing executes the checklist prose. Do not\n assume it auto-ran.\n- **Schema / field authoring + code generation.** You dispatch a task; the **coding\n agent** authors the fields, schemas, ui-behavior, and code at dispatch time. If you\n catch yourself writing application code or a resource schema here, stop — that is\n the dispatched agent's job, not the orchestrator's.\n\nIf you find yourself designing how MANY agents run concurrently rather than how ONE\ntask dispatches safely, stop — that is the scale playbook.\n\n## What you emit\n\n**No journey artifact.** This is a pure-orchestration playbook: the observable result\nof a dispatch — the **change-set** (files touched, attributed, summarized) and the\n**task status** — is materialized by the runner on the dispatched task's row, not\nauthored by this playbook. That is deliberately not duplicated into a separate\njourney artifact family: the task row already *is* the dispatch record, and a second\nhome for the same record would drift.\n\nDispatch uses the configured host's actual authorization boundary. The creator reviews\nthe recorded change-set and verification outcome afterwards —\none verified task at a time, until the build plan is fully dispatched.\n\n## References\n\n- A playbook's declared `approval` and failure policy gate nothing on a leaf run; they are read only\n at a composite lane's boundary, where they frame a decision for the person and revert nothing.\n\n## Reviewer checklist — `dispatch-outcome-sound`\n\nFormerly authored as an `llm_judge` quality gate; the generic rubric-only gate kind was retired at the flexible-intelligence hard cut (judgment now runs only through a compiled Evaluation Treatment). The checklist itself is creator-facing review guidance and is kept here, verbatim (minus the retired runner's closing sentence, and with repository-specific wording made application-neutral):\n\nJudge whether ONE dispatched build-plan task ran soundly under the D4 dispatch contract — the trust-but-verify reviewer pass OUTSIDE the coding agent. Assess six invariants and mark each PASS / CONCERN / GAP with a one-line evidence note. (1) TASK ACCOMPLISHED — the change-set the run produced actually implements the dispatched task's target + stage (e.g. a schema task added the persisted shape; a ui-behavior task added field displays); a run whose change-set does not advance the task's stated target is a GAP (the dispatch produced nothing useful), and an empty change-set on a task that should have authored files is a GAP. (2) CHANGE-SET SCOPED TO THE TASK — the files touched belong to the task's target (its module / resource / stage) and the app workspace; edits sprawling into unrelated modules, Wildo package source outside the application workspace, or files no build-plan task owns are a CONCERN (scope creep the reviewer must flag). Files attributed BASELINE_DIRTY_AMBIGUOUS were already dirty and changed again during the run; this establishes uncertainty, not ownership by a parallel editor. Every changed path outside the declared scope — ambiguous or not, and including a parallel session's edits, which the capture cannot tell apart from the run's own — is RECORDED on the result as `outOfScopePaths`; nothing refuses the run for it. Treat each as a CONCERN and resolve its authorship during review, never as a GAP by itself. Committed-window entries and recognized concurrent host-lane paths are classified separately and left off that list. (3) VERIFY RAN + PASSED — the deterministic verify gate (typecheck) ran OUTSIDE the coding agent after the run and passed; a run recorded as succeeded whose typecheck the reviewer cannot confirm passed is a CONCERN, and a run whose typecheck FAILED but was recorded succeeded is a GAP. (4) ATTRIBUTION CLEAN (the single-flight signal) — the run's edits are cleanly attributable to it in the captured change-set (files classed RUN_EXCLUSIVE or APPEARED_DURING_RUN), consistent with the single-flight lock having held for this dispatch. A change-set the capture could NOT cleanly attribute to the run — dominated by BASELINE_DIRTY_AMBIGUOUS overlap, or captured across a HEAD that moved mid-run — is a CONCERN the reviewer must resolve by hand before accepting the run, not a clean pass (single-flight is a hard runner floor, so this invariant reads the attribution the run actually recorded rather than re-proving the lock). (5) FAILURE DISPOSITION CORRECT — a failed/timed-out run's captured change-set is KEPT + FLAGGED for human triage (keep_and_flag), never silently reverted nor silently left as an un-recorded half-applied state; a failed run with no recorded change-set flag is a GAP (F-5 workspace-safety violation). (6) BOUNDARY DISCIPLINE — the dispatch stays at single-task depth: it dispatches ONE task, captures + verifies + records it, and applies onFailure. It does NOT re-decompose the plan (the build-decompose playbook owns the task graph), does NOT run MANY coding agents concurrently / design a concurrency scheduler / interleave the companion generation steps at scale (the scale playbook), and does NOT itself author schemas / fields / code (the coding agent does that at dispatch time). Evidence of re-decomposition, multi-agent scale orchestration, or the dispatcher authoring code itself is a CONCERN (scope creep out of the single-flight dispatch lane). (The checklist is declarative: nothing executes it; the current host's deterministic checks apply; the approval enum alone adds no gate.)\n",
|
|
23
|
+
"skillRefs": [],
|
|
29
24
|
"skillBodyRefs": [],
|
|
30
25
|
"contextSources": [],
|
|
31
26
|
"draftableDocumentDefinitionRefs": [],
|