@wildo-ai/framework-knowledge 1.1.7 → 1.1.9
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/dist/claude-marketplace/plugins/wildo/.claude-plugin/plugin.json +1 -1
- package/dist/claude-marketplace/plugins/wildo/references/composites-and-the-loop.md +9 -2
- package/dist/claude-marketplace/plugins/wildo/references/creation-state.md +21 -0
- package/dist/claude-marketplace/plugins/wildo/references/derived-artifacts.md +121 -0
- package/dist/claude-marketplace/plugins/wildo/references/runs-judges-and-questions.md +29 -5
- package/dist/claude-marketplace/plugins/wildo/skills/answer/SKILL.md +29 -2
- package/dist/claude-marketplace/plugins/wildo/skills/build/SKILL.md +69 -24
- package/dist/claude-marketplace/plugins/wildo/skills/doctor/SKILL.md +10 -0
- package/dist/claude-marketplace/plugins/wildo/skills/run/SKILL.md +21 -5
- package/dist/claude-marketplace/plugins/wildo/skills/start/SKILL.md +31 -5
- package/dist/claude-marketplace/plugins/wildo/skills/status/SKILL.md +2 -0
- package/dist/claude-marketplace/plugins/wildo/skills/why/SKILL.md +11 -1
- 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 +11 -1
- package/dist/esm/framework-knowledge.definitions.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.d.ts +2 -2
- package/dist/esm/playbooks/bottom_up.assemble-verify/playbook.definition.js +2 -2
- 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 +11 -11
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.build/playbook.definition.js +29 -22
- 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 +3 -3
- 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 +59 -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.js +3 -3
- 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.js +1 -1
- package/dist/esm/playbooks/bottom_up.build-scale/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js +1 -1
- package/dist/esm/playbooks/bottom_up.conception/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.d.ts +2 -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 +5 -5
- package/dist/esm/playbooks/bottom_up.domain-plan/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts +8 -0
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js +12 -4
- package/dist/esm/playbooks/bottom_up.foundation/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts +25 -27
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js +85 -43
- package/dist/esm/playbooks/top_down.brand-identity/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts +40 -0
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js +41 -0
- package/dist/esm/playbooks/top_down.brand-name-research/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts +199 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js +201 -0
- package/dist/esm/playbooks/top_down.brand-name-screening-produce/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts +67 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.d.ts.map +1 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js +76 -0
- package/dist/esm/playbooks/top_down.brand-naming/playbook.definition.js.map +1 -0
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts +3 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.js +27 -18
- package/dist/esm/playbooks/top_down.business-model/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts +11 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-analysis/playbook.definition.js +11 -11
- 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 +2 -0
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js +3 -1
- package/dist/esm/playbooks/top_down.compliance-conception/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts +2 -0
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js +3 -1
- package/dist/esm/playbooks/top_down.compliance-posture/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts +5 -2
- package/dist/esm/playbooks/top_down.definition/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.definition/playbook.definition.js +16 -4
- package/dist/esm/playbooks/top_down.definition/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts +7 -3
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js +36 -2
- package/dist/esm/playbooks/top_down.phase-gate/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts +7 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.risk-register/playbook.definition.js +4 -2
- 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 +9 -3
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.d.ts.map +1 -1
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js +3 -3
- package/dist/esm/playbooks/top_down.scope-roadmap/playbook.definition.js.map +1 -1
- package/dist/esm/playbooks/top_down.vision-elicitation/playbook.definition.d.ts +35 -2
- 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 +30 -17
- 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/method.md +22 -7
- package/dist/knowledge/playbooks/bottom_up.assemble-verify/playbook.json +3 -3
- package/dist/knowledge/playbooks/bottom_up.build/method.md +17 -15
- package/dist/knowledge/playbooks/bottom_up.build/playbook.json +4 -3
- 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 +117 -28
- package/dist/knowledge/playbooks/bottom_up.build-decompose/playbook.json +4 -4
- package/dist/knowledge/playbooks/bottom_up.build-dispatch/method.md +133 -59
- package/dist/knowledge/playbooks/bottom_up.build-dispatch/playbook.json +2 -2
- package/dist/knowledge/playbooks/bottom_up.build-scale/method.md +169 -276
- package/dist/knowledge/playbooks/bottom_up.build-scale/playbook.json +2 -2
- package/dist/knowledge/playbooks/bottom_up.capability-composition/method.md +8 -1
- package/dist/knowledge/playbooks/bottom_up.capability-composition/playbook.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.conception/method.md +3 -2
- package/dist/knowledge/playbooks/bottom_up.conception/playbook.json +2 -2
- package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.domain-plan/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/bottom_up.domain-plan/method.md +22 -6
- package/dist/knowledge/playbooks/bottom_up.domain-plan/playbook.json +4 -3
- package/dist/knowledge/playbooks/bottom_up.foundation/playbook.json +13 -5
- package/dist/knowledge/playbooks/refinement.compliance-document-candidate/method.md +5 -2
- package/dist/knowledge/playbooks/refinement.compliance-document-candidate/playbook.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/top_down.brand-identity/method.md +71 -37
- package/dist/knowledge/playbooks/top_down.brand-identity/playbook.json +35 -38
- package/dist/knowledge/playbooks/top_down.brand-name-research/method.md +105 -0
- package/dist/knowledge/playbooks/top_down.brand-name-research/playbook.json +55 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-protocol.json +1 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/evaluation-treatment.json +1 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/method.md +78 -0
- package/dist/knowledge/playbooks/top_down.brand-name-screening-produce/playbook.json +63 -0
- package/dist/knowledge/playbooks/top_down.brand-naming/method.md +56 -0
- package/dist/knowledge/playbooks/top_down.brand-naming/playbook.json +65 -0
- package/dist/knowledge/playbooks/top_down.business-model/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/top_down.business-model/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/top_down.business-model/method.md +60 -6
- package/dist/knowledge/playbooks/top_down.business-model/playbook.json +15 -10
- package/dist/knowledge/playbooks/top_down.compliance-analysis/playbook.json +30 -10
- package/dist/knowledge/playbooks/top_down.compliance-conception/playbook.json +3 -1
- package/dist/knowledge/playbooks/top_down.compliance-posture/playbook.json +4 -1
- package/dist/knowledge/playbooks/top_down.definition/method.md +8 -3
- package/dist/knowledge/playbooks/top_down.definition/playbook.json +6 -4
- package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-protocol.json +1 -1
- package/dist/knowledge/playbooks/top_down.phase-gate/evaluation-treatment.json +1 -1
- package/dist/knowledge/playbooks/top_down.phase-gate/playbook.json +11 -1
- package/dist/knowledge/playbooks/top_down.risk-register/method.md +21 -0
- package/dist/knowledge/playbooks/top_down.risk-register/playbook.json +8 -2
- package/dist/knowledge/playbooks/top_down.scope-roadmap/playbook.json +4 -2
- package/dist/knowledge/playbooks/top_down.vision-elicitation/method.md +10 -0
- package/dist/knowledge/playbooks/top_down.vision-elicitation/playbook.json +40 -17
- package/dist/knowledge/references/brand.name-choice.config.md +127 -0
- package/dist/knowledge/references/brand.name-screening.config.md +253 -0
- package/dist/knowledge/references/build-plan.task-graph.config.md +64 -11
- package/dist/knowledge/references/business-model.pricing-plan.config.md +16 -0
- package/dist/knowledge/references/business-model.snapshot.config.md +64 -0
- package/dist/knowledge/references/business-model.snapshot.validation.md +68 -4
- package/dist/knowledge/references/capability-composition.config.md +67 -4
- package/dist/knowledge/references/example.data-seeding.minimal.md +29 -1
- package/dist/knowledge/references/market.snapshot.validation.md +1 -1
- package/dist/knowledge/references/saas.data-seeding.bootstrap-wiring.md +7 -1
- package/dist/knowledge/references/saas.data-seeding.definition-input.md +6 -0
- package/dist/knowledge/references/saas.models.queue.scheduled-recovery.md +81 -2
- package/dist/knowledge/references/saas.specifications.companion-exports.contract.md +10 -0
- package/dist/knowledge/references/saas.website.astro.label-loader.md +9 -0
- package/dist/knowledge/references/saas.website.factories.define-section.md +4 -0
- package/dist/knowledge/references/saas.website.page-manifest.schema.md +12 -3
- package/dist/knowledge/references/saas.website.page-sections.component.md +72 -0
- package/dist/knowledge/references/saas.website.sections.definition-schema.md +11 -0
- package/dist/knowledge/registries/assurance-authority-bases.json +1 -1
- package/dist/knowledge/registries/framework-topics.json +38 -1
- package/dist/knowledge/registries/playbooks.json +68 -20
- package/dist/knowledge/registries/source-tags.json +748 -695
- package/dist/knowledge/rules/live-context-door.md +5 -2
- package/dist/knowledge/skills/INDEX.md +2 -1
- package/dist/knowledge/skills/application-database-migrations/SKILL.md +1 -1
- package/dist/knowledge/skills/brand-name-screening/SKILL.md +154 -0
- package/dist/knowledge/skills/brand-name-screening/references/framework-brand-name-screening-api.md +394 -0
- package/dist/knowledge/skills/brand-name-screening/references/screening-procedure.md +65 -0
- package/dist/knowledge/skills/compliance-document-authoring/references/document-composition-privacy-notice.md +5 -2
- package/dist/knowledge/skills/config-saas/SKILL.md +31 -4
- package/dist/knowledge/skills/config-saas/references/compliance-declarations.md +14 -1
- package/dist/knowledge/skills/config-saas/references/framework-background-work-api.md +81 -2
- package/dist/knowledge/skills/email-add-template/SKILL.md +1 -1
- package/dist/knowledge/skills/i18n-rerun-pipeline/SKILL.md +1 -1
- package/dist/knowledge/skills/inbound-channels/SKILL.md +2 -2
- package/dist/knowledge/skills/local-environment-bootstrap/SKILL.md +11 -1
- package/dist/knowledge/skills/local-environment-bootstrap/references/derived-artifact-currency.md +122 -0
- package/dist/knowledge/skills/local-environment-bootstrap/references/framework-upgrade-and-dependency-alignment.md +11 -0
- package/dist/knowledge/skills/local-environment-bootstrap/references/wildo-cli-bootstrap-commands.md +9 -2
- package/dist/knowledge/skills/market-companion-prompt-enrichment/SKILL.md +11 -1
- package/dist/knowledge/skills/market-companion-prompt-enrichment/references/framework-companion-behavior-api.md +11 -1
- package/dist/knowledge/skills/market-message-templates-authoring/references/framework-message-template-api.md +1 -1
- package/dist/knowledge/skills/market-snapshot-validation/SKILL.md +1 -1
- package/dist/knowledge/skills/market-snapshot-validation/references/framework-snapshot-validation-api.md +1 -1
- package/dist/knowledge/skills/module-companion-exports/references/companion-exports-by-package.md +10 -0
- package/dist/knowledge/skills/module-relationships/SKILL.md +6 -4
- package/dist/knowledge/skills/seeding-authoring/SKILL.md +51 -3
- package/dist/knowledge/skills/seeding-authoring/references/framework-data-seeding-api.md +6 -0
- package/dist/knowledge/skills/seeding-operations/references/framework-data-seeding-operations-api.md +7 -1
- package/dist/knowledge/skills/spec-companion-exports/references/framework-companion-exports-contract-api.md +10 -0
- package/dist/knowledge/skills/website-factory-advanced/SKILL.md +4 -0
- package/dist/knowledge/skills/website-page-authoring/SKILL.md +84 -3
- package/dist/knowledge/skills/website-section-contact/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-contact/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-cta/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-cta/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-faq/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-faq/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-feature-benefit-summary/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-feature-benefit-summary/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-feature-detail/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-feature-detail/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-footer-cta/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-footer-cta/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-hero/SKILL.md +27 -9
- package/dist/knowledge/skills/website-section-hero/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-pricing/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-pricing/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-section-social-proof/SKILL.md +15 -0
- package/dist/knowledge/skills/website-section-social-proof/references/define-website-section-api.md +15 -0
- package/dist/knowledge/skills/website-seo-aeo-geo/SKILL.md +1 -1
- package/dist/knowledge/skills/website-seo-aeo-geo/references/aeo-api.md +11 -0
- package/dist/knowledge/topic-index.json +169 -43
- package/dist/tsconfig.build.tsbuildinfo +1 -1
- package/dist/tsconfig.tsbuildinfo +1 -1
- package/package.json +4 -4
|
@@ -1,4 +1,4 @@
|
|
|
1
|
-
# Build Dispatch —
|
|
1
|
+
# Build Dispatch — Build-Plan Tasks → Verified Coding-Agent Runs, in Parallel Waves
|
|
2
2
|
|
|
3
3
|
### Target Application Framing
|
|
4
4
|
|
|
@@ -12,14 +12,14 @@ Read and apply these patterns from the application-developer point of view:
|
|
|
12
12
|
- how the application should avoid mixing frontend, backend, and infrastructure concerns
|
|
13
13
|
|
|
14
14
|
|
|
15
|
-
> **
|
|
16
|
-
>
|
|
17
|
-
>
|
|
18
|
-
>
|
|
19
|
-
>
|
|
20
|
-
>
|
|
21
|
-
>
|
|
22
|
-
>
|
|
15
|
+
> **The build runs in parallel by default.** One run of this playbook starts a
|
|
16
|
+
> **wave**: up to N build-plan tasks at once, N being the application's **build
|
|
17
|
+
> parallelism** (`wildo workbench parallelism`, 5 unless the person set it). Each
|
|
18
|
+
> task in the wave follows the same per-task contract — its own coding run, its
|
|
19
|
+
> change-set captured, verified outside the coding agent, recorded, the failure
|
|
20
|
+
> disposition applied. With a build parallelism of `1` a run dispatches exactly
|
|
21
|
+
> ONE task, which is the single-flight mode. A `revert_changeset` failure path is
|
|
22
|
+
> still a **later phase** (see the boundary section).
|
|
23
23
|
|
|
24
24
|
## Where you are in the journey
|
|
25
25
|
|
|
@@ -33,9 +33,10 @@ here — you are turning one *approved, ordered* task into a *dispatched, verifi
|
|
|
33
33
|
change to the application.
|
|
34
34
|
|
|
35
35
|
Upstream, the **build-decompose** playbook produced the ordered task graph you
|
|
36
|
-
consume
|
|
37
|
-
|
|
38
|
-
|
|
36
|
+
consume. The **scale** playbook describes the same wave from the scheduling side —
|
|
37
|
+
the ready-set, the width, the reconciliation — and runs through the same runtime
|
|
38
|
+
branch as this one; prefer this playbook to start a build. **You author the task
|
|
39
|
+
graph neither here nor there** — see the boundary section.
|
|
39
40
|
|
|
40
41
|
## The typed task you dispatch
|
|
41
42
|
|
|
@@ -419,6 +420,16 @@ export enum BuildPlanTaskProductKind {
|
|
|
419
420
|
* money and the pricing-surface facts (recommended, price disclosure, availability) the plan implies.
|
|
420
421
|
*/
|
|
421
422
|
APPLICATION_BILLING_PRODUCT = 'APPLICATION_BILLING_PRODUCT',
|
|
423
|
+
/**
|
|
424
|
+
* One data seed a module declares — rows the application creates for itself, named by the seed's
|
|
425
|
+
* `seedKey` (`crm:demo-customers`).
|
|
426
|
+
*
|
|
427
|
+
* The seed is its own file, `backend-api/src/modules/<module>/seeds/<seedKey with ':' as '.'>.seed.ts`,
|
|
428
|
+
* and it lands only once the module registers it — a seed file nothing imports never runs. Its
|
|
429
|
+
* {@link BuildPlanDataSeedContent} says whether it is REFERENCE data the application needs everywhere
|
|
430
|
+
* or DEMONSTRATION data that must never reach production.
|
|
431
|
+
*/
|
|
432
|
+
APPLICATION_DATA_SEED = 'APPLICATION_DATA_SEED',
|
|
422
433
|
/** One website page, registered in the website root config by its manifest. */
|
|
423
434
|
WEBSITE_PAGE = 'WEBSITE_PAGE',
|
|
424
435
|
/** One section of one website page, declared in that page's sections file. */
|
|
@@ -437,6 +448,27 @@ export enum BuildPlanTaskProductKind {
|
|
|
437
448
|
INBOUND_CHANNEL_HANDLER = 'INBOUND_CHANNEL_HANDLER',
|
|
438
449
|
}
|
|
439
450
|
|
|
451
|
+
|
|
452
|
+
/**
|
|
453
|
+
* What a data seed's rows ARE, which decides where they may exist.
|
|
454
|
+
*
|
|
455
|
+
* - `REFERENCE` — rows the application needs to work wherever it runs: a closed list, a default
|
|
456
|
+
* record, a system template. Every environment, production included.
|
|
457
|
+
* - `DEMONSTRATION` — sample rows that make a freshly created application look lived-in (customers,
|
|
458
|
+
* projects, a few records per list). They must never sit beside real rows, so the seed declares
|
|
459
|
+
* `allowedApplicationEnvironments` without `production`, and the task lands only once it does.
|
|
460
|
+
*/
|
|
461
|
+
export enum BuildPlanDataSeedContent {
|
|
462
|
+
REFERENCE = 'REFERENCE',
|
|
463
|
+
DEMONSTRATION = 'DEMONSTRATION',
|
|
464
|
+
}
|
|
465
|
+
|
|
466
|
+
/**
|
|
467
|
+
* A data seed's key: kebab-case segments joined by `:` (`crm:demo-customers`), the convention a
|
|
468
|
+
* `DataSeedDefinition` documents. Constrained here because the seed's FILE is derived from it.
|
|
469
|
+
*/
|
|
470
|
+
export const DATA_SEED_KEY_PATTERN: RegExp = /^[a-z0-9]+(?:-[a-z0-9]+)*(?::[a-z0-9]+(?:-[a-z0-9]+)*)*$/;
|
|
471
|
+
|
|
440
472
|
/**
|
|
441
473
|
* One artifact a task is accountable for. Closed by construction: a product the
|
|
442
474
|
* host cannot ask a question about is a product that can never be shown to have
|
|
@@ -506,6 +538,13 @@ export const BuildPlanTaskProductSchema = z.discriminatedUnion('kind', [
|
|
|
506
538
|
scope: z.enum(ProviderBindingScope).systemEnum('ProviderBindingScope'),
|
|
507
539
|
}),
|
|
508
540
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.APPLICATION_BILLING_PRODUCT).systemEnum('BuildPlanTaskProductKind'), productKey: SlugSchema }),
|
|
541
|
+
z.strictObject({
|
|
542
|
+
kind: z.literal(BuildPlanTaskProductKind.APPLICATION_DATA_SEED).systemEnum('BuildPlanTaskProductKind'),
|
|
543
|
+
seedKey: z.string().regex(DATA_SEED_KEY_PATTERN),
|
|
544
|
+
/** The resource whose rows the seed writes — the `resourceType` it declares. */
|
|
545
|
+
resourceRef: SlugSchema,
|
|
546
|
+
content: z.enum(BuildPlanDataSeedContent).systemEnum('BuildPlanDataSeedContent'),
|
|
547
|
+
}),
|
|
509
548
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_PAGE).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema }),
|
|
510
549
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.WEBSITE_SECTION).systemEnum('BuildPlanTaskProductKind'), pageRef: SlugSchema, sectionRef: SlugSchema }),
|
|
511
550
|
z.strictObject({ kind: z.literal(BuildPlanTaskProductKind.DOCUMENTATION_CHAPTER).systemEnum('BuildPlanTaskProductKind'), chapterRef: SlugSchema }),
|
|
@@ -588,6 +627,9 @@ export function buildPlanTaskProductIdentities(product: BuildPlanTaskProduct): r
|
|
|
588
627
|
return [`${product.kind}:${product.scope}:${product.providerRef}`];
|
|
589
628
|
case BuildPlanTaskProductKind.APPLICATION_BILLING_PRODUCT:
|
|
590
629
|
return [`${product.kind}:${product.productKey}`];
|
|
630
|
+
// The key alone: two seeds may write one resource, and the key is what the seed run ledger tracks.
|
|
631
|
+
case BuildPlanTaskProductKind.APPLICATION_DATA_SEED:
|
|
632
|
+
return [`${product.kind}:${product.seedKey}`];
|
|
591
633
|
case BuildPlanTaskProductKind.WEBSITE_PAGE:
|
|
592
634
|
return [`${product.kind}:${product.pageRef}`];
|
|
593
635
|
case BuildPlanTaskProductKind.WEBSITE_SECTION:
|
|
@@ -611,6 +653,13 @@ export function buildPlanTaskProductIdentities(product: BuildPlanTaskProduct): r
|
|
|
611
653
|
*/
|
|
612
654
|
export const BILLING_CATALOG_SKILL_REF = 'configure-billing';
|
|
613
655
|
|
|
656
|
+
/**
|
|
657
|
+
* The skill every data-seed task is authored with (#2234): levels, modes, business keys, and the
|
|
658
|
+
* environment restriction that keeps demonstration rows out of production. The dispatch derives it from
|
|
659
|
+
* an `APPLICATION_DATA_SEED` product whatever the decomposer wrote.
|
|
660
|
+
*/
|
|
661
|
+
export const DATA_SEED_SKILL_REF = 'seeding-authoring';
|
|
662
|
+
|
|
614
663
|
export const BuildPlanTaskTargetSchema = z.discriminatedUnion('kind', [
|
|
615
664
|
z.strictObject({ kind: z.literal(BuildPlanTaskTargetKind.MODULE), moduleRef: ModuleRefSchema }),
|
|
616
665
|
z.strictObject({
|
|
@@ -738,15 +787,18 @@ export const BuildPlanTaskSchema = z.strictObject({
|
|
|
738
787
|
/**
|
|
739
788
|
* What this task is accountable to — traceability only, NEVER scope authority.
|
|
740
789
|
*
|
|
741
|
-
* The vocabulary is the
|
|
742
|
-
* and non-functional requirements, roadmap phases,
|
|
743
|
-
* constraints
|
|
744
|
-
*
|
|
745
|
-
*
|
|
790
|
+
* The vocabulary is the target aspects `BUILD_PLAN_FAMILY_ASPECTS` declares for this edge:
|
|
791
|
+
* functional and non-functional requirements, roadmap phases, the vision's success criteria and
|
|
792
|
+
* constraints, drafted features, pricing plans, and the brand's name, logo direction and visual
|
|
793
|
+
* tone. Each target after the first three was added because a producer had already been writing
|
|
794
|
+
* it (#629, #1433, #1835, #2221). A companion generation step serves what it consumes: the `logo`
|
|
795
|
+
* step serves the brand's logo direction and name.
|
|
746
796
|
*
|
|
747
|
-
*
|
|
748
|
-
*
|
|
749
|
-
*
|
|
797
|
+
* This schema accepts any non-empty string. Generation does not: the edge is DECLARED, so a key
|
|
798
|
+
* that resolves to no element of a target family (when that family has landed) is a dangling
|
|
799
|
+
* reference. The model is told so on retry, and the landing refuses it. That is why widening the
|
|
800
|
+
* vocabulary to what producers genuinely mean matters: a true link the vocabulary does not name
|
|
801
|
+
* fails generation. The workbench renders a key outside the vocabulary as visibly unresolved.
|
|
750
802
|
*/
|
|
751
803
|
servesRefs: z.array(NonEmptyStringSchema).default([]),
|
|
752
804
|
/**
|
|
@@ -770,9 +822,11 @@ export type BuildPlanTask = z.infer<typeof BuildPlanTaskSchema>;
|
|
|
770
822
|
* journey artifact selected by `MetaWorkflow_ArtifactSelector.family ===
|
|
771
823
|
* 'build-plan'` (the `family` vocabulary stays an open string owned by the
|
|
772
824
|
* selector surface; this note is the single place tying the SHAPE to the
|
|
773
|
-
* NAME). Produced by the build-decompose playbook, consumed
|
|
774
|
-
*
|
|
775
|
-
*
|
|
825
|
+
* NAME). Produced by the build-decompose playbook, consumed by
|
|
826
|
+
* build-dispatch (and build-scale, which runs the same branch): ready tasks
|
|
827
|
+
* are dispatched in parallel waves of up to the application's build
|
|
828
|
+
* parallelism (`wildo workbench parallelism`, 5 by default; 1 = one at a
|
|
829
|
+
* time).
|
|
776
830
|
*
|
|
777
831
|
* Invariants enforced here: unique task refs; every prerequisite names a task
|
|
778
832
|
* in this graph; no self-prerequisite. Cycle detection and ordering
|
|
@@ -864,14 +918,16 @@ Most of the D4 dispatch contract is **runner mechanism**, not prose you re-imple
|
|
|
864
918
|
the runner composes the context pack, opens a coding session with the agent over the
|
|
865
919
|
Agent Client Protocol and sends one prompt turn, answers the agent's permission
|
|
866
920
|
requests within the declared ceiling, captures the change-set, runs the verify hook,
|
|
867
|
-
|
|
921
|
+
keeps each task from being built twice at once, fills the wave to the configured width,
|
|
922
|
+
and applies its configured execution limits. Your method here is the **declarative recipe** the runner interprets —
|
|
868
923
|
*which* task to dispatch next, *when* it is authorized, and *how* its outcome is
|
|
869
924
|
judged. Do not hand-compose a dispatch prompt or drive git yourself; let the runner
|
|
870
925
|
own composition and change-set capture.
|
|
871
926
|
|
|
872
927
|
## Read state first — no artifact to write
|
|
873
928
|
|
|
874
|
-
This playbook is **idempotent** and, on a re-run, *advances the
|
|
929
|
+
This playbook is **idempotent** and, on a re-run, *advances the build by one wave*
|
|
930
|
+
(by one task when the build parallelism is `1`).
|
|
875
931
|
Before dispatching anything:
|
|
876
932
|
|
|
877
933
|
1. Read the current journey state and scope from what this run is given — the loaded
|
|
@@ -948,21 +1004,36 @@ Two smaller things belong in the same section, because both were observed costin
|
|
|
948
1004
|
- **Do not name a task so it reads as a fixture.** An agent that concludes it is looking at a
|
|
949
1005
|
smoke test will say so and stop. Name the task after the product change it makes.
|
|
950
1006
|
|
|
951
|
-
## Step 1 — Select the
|
|
952
|
-
|
|
953
|
-
Walk the build plan in its authored order
|
|
954
|
-
|
|
955
|
-
|
|
956
|
-
|
|
957
|
-
|
|
958
|
-
|
|
959
|
-
|
|
960
|
-
|
|
961
|
-
|
|
962
|
-
|
|
963
|
-
|
|
964
|
-
|
|
965
|
-
|
|
1007
|
+
## Step 1 — Select the ready tasks (the wave)
|
|
1008
|
+
|
|
1009
|
+
Walk the build plan in its authored order. A task is **ready** when it is not yet
|
|
1010
|
+
dispatched (or a previously-**failed** task cleared for retry — see Step 5), it is
|
|
1011
|
+
not already running, and its declared prerequisites have all **succeeded**. The
|
|
1012
|
+
runner selects ready tasks in that order and keeps up to the build parallelism of
|
|
1013
|
+
them running; when a run settles, its slot is refilled with whatever is ready THEN,
|
|
1014
|
+
so a task that just landed unlocks its dependents within the same wave. If **no**
|
|
1015
|
+
task is ready — every task has already succeeded, or the only undispatched tasks
|
|
1016
|
+
are blocked behind a still-unresolved failure — there is nothing to dispatch:
|
|
1017
|
+
report the build as done (or blocked on the failed task) and stop. An empty build
|
|
1018
|
+
plan is the same.
|
|
1019
|
+
|
|
1020
|
+
- **How many run at once is the build parallelism, and it is the person's call.**
|
|
1021
|
+
`wildo workbench parallelism` shows it (5 by default) and sets it; `1` means one
|
|
1022
|
+
workspace-mutating run at a time. The runner reads it at the start of every wave,
|
|
1023
|
+
so a change needs no restart. Do not try to widen a wave beyond it.
|
|
1024
|
+
- **The runs share ONE worktree, by design.** Concurrent runs may edit the same
|
|
1025
|
+
files. The runner does not prevent that; it prevents only a task being built
|
|
1026
|
+
twice at once, and it REPAIRS the rest when the wave's runs have settled: it
|
|
1027
|
+
commits what the runs' own accepts left as one change naming every run whose
|
|
1028
|
+
writes it carries, then re-runs ALONE each task whose finished product a sibling
|
|
1029
|
+
overwrote. Each run's record says which runs overlapped it (`concurrency`), and
|
|
1030
|
+
whether a failure is suspected to come from a sibling (`interferenceSuspected`).
|
|
1031
|
+
- **One wave is bounded.** A call takes at most four tasks per slot, and runs each
|
|
1032
|
+
generation step at most once; it then stops taking tasks, waits for its runs and
|
|
1033
|
+
returns. The next run of this playbook continues from where the build stands.
|
|
1034
|
+
- **One wave at a time.** A second wave is refused while one runs, including during
|
|
1035
|
+
its end-of-wave commit and repair: start the next only once the running one has
|
|
1036
|
+
ended.
|
|
966
1037
|
- **A prerequisite must have SUCCEEDED, not merely been attempted.** A task is ready
|
|
967
1038
|
only when every task it depends on is dispatched-and-succeeded (verify passed).
|
|
968
1039
|
A prerequisite that is dispatched-and-**failed** (its change-set is flagged for
|
|
@@ -974,15 +1045,16 @@ empty build plan is the same: nothing to dispatch, stop.
|
|
|
974
1045
|
- **Companion-generation steps are not coding-agent dispatches.** A build-plan task
|
|
975
1046
|
marked as a companion-owned generation step (labels / i18n, email templates,
|
|
976
1047
|
seeds) runs through its deterministic companion endpoint, not the coding-agent
|
|
977
|
-
dispatch lane. Route it there; do not dispatch a coding agent for it.
|
|
978
|
-
|
|
979
|
-
|
|
1048
|
+
dispatch lane. Route it there; do not dispatch a coding agent for it. In a wave
|
|
1049
|
+
the runner runs a ready generation step in its turn while the coding runs already
|
|
1050
|
+
started keep going.
|
|
980
1051
|
|
|
981
1052
|
## Step 2 — Check the actual host authorization boundary
|
|
982
1053
|
|
|
983
1054
|
A coding dispatch writes the application workspace. Read its selected task, readiness,
|
|
984
1055
|
mutation scope and the configured coding host's authorization policy before invoking it.
|
|
985
|
-
|
|
1056
|
+
Every run of a wave writes the same shared workspace; each is confined to its own task's
|
|
1057
|
+
mutation scope, and nothing confines it from its siblings (Step 1).
|
|
986
1058
|
|
|
987
1059
|
The playbook's `approval` declaration and the journey autonomy presets express policy
|
|
988
1060
|
intent. The current playbook runner does not interpret them as pre-dispatch gates,
|
|
@@ -1052,7 +1124,10 @@ so the agent cannot mark its own homework:
|
|
|
1052
1124
|
is the *trust-but-verify reviewer* pass. It is **declarative** — the creator's
|
|
1053
1125
|
review checklist; the compiled build-dispatch Evaluation Treatment is what the
|
|
1054
1126
|
runtime judges with, and the deterministic typecheck above is what runs
|
|
1055
|
-
automatically.
|
|
1127
|
+
automatically. **In a wave the runtime does not compose this judge per run**: each
|
|
1128
|
+
run's record carries its outcome, its checks, and what it overlapped, and the
|
|
1129
|
+
wave's end-of-run repair is on the wave's result. Read those; with a build
|
|
1130
|
+
parallelism of `1` the judge runs on the single dispatch as before.
|
|
1056
1131
|
|
|
1057
1132
|
## Step 5 — Record the result and apply the failure disposition
|
|
1058
1133
|
|
|
@@ -1082,8 +1157,8 @@ is a deferred build-loop-resilience concern, and human triage is the v1 disposit
|
|
|
1082
1157
|
here the loop simply surfaces the failure and stops advancing that dependency chain.
|
|
1083
1158
|
|
|
1084
1159
|
Then **loop**: on the next run of this playbook, the build plan's task records reflect the
|
|
1085
|
-
just
|
|
1086
|
-
(Step 1). Close a significant stretch of dispatches with a progress summary — what was
|
|
1160
|
+
outcomes of the wave that just ran (`wildo build tasks`), and the next wave selects from
|
|
1161
|
+
what is ready now (Step 1). Close a significant stretch of dispatches with a progress summary — what was
|
|
1087
1162
|
produced, which change-sets landed, what verify said, and any failed task left
|
|
1088
1163
|
flagged for triage.
|
|
1089
1164
|
|
|
@@ -1103,17 +1178,16 @@ flagged for triage.
|
|
|
1103
1178
|
|
|
1104
1179
|
## Scaffold-depth boundary (owned by a sibling, or deferred to a later phase)
|
|
1105
1180
|
|
|
1106
|
-
Keep this playbook at **
|
|
1107
|
-
here**:
|
|
1181
|
+
Keep this playbook at **dispatch depth**: which tasks run, under what contract, and
|
|
1182
|
+
what each run's outcome was. Explicitly **out of scope here**:
|
|
1108
1183
|
|
|
1109
1184
|
- **Re-decomposition.** You do NOT split modules/resources into tasks, re-order the
|
|
1110
1185
|
graph, or add tasks — the **build-decompose** playbook owns the task graph. You
|
|
1111
1186
|
read it and dispatch from it.
|
|
1112
|
-
- **
|
|
1113
|
-
|
|
1114
|
-
|
|
1115
|
-
|
|
1116
|
-
concurrency schedule.
|
|
1187
|
+
- **The width and the isolation model.** How many tasks run at once is the
|
|
1188
|
+
application's build parallelism, set by the person; the runs share one worktree and
|
|
1189
|
+
are repaired, not isolated. You do NOT choose a width, partition the worktree, or
|
|
1190
|
+
design a different schedule.
|
|
1117
1191
|
- **A `revert_changeset` failure path.** Undoing a failed run's edits is a mutating
|
|
1118
1192
|
git op outside the read-only change-set carve-out — deferred. `keep_and_flag` (keep
|
|
1119
1193
|
+ flag the captured change-set for triage) is the v1 disposition.
|
|
@@ -1126,8 +1200,8 @@ here**:
|
|
|
1126
1200
|
catch yourself writing application code or a resource schema here, stop — that is
|
|
1127
1201
|
the dispatched agent's job, not the orchestrator's.
|
|
1128
1202
|
|
|
1129
|
-
If you find yourself designing how MANY agents run concurrently
|
|
1130
|
-
|
|
1203
|
+
If you find yourself designing how MANY agents run concurrently, stop: the width is
|
|
1204
|
+
the build parallelism and the schedule is the runner's.
|
|
1131
1205
|
|
|
1132
1206
|
## What you emit
|
|
1133
1207
|
|
|
@@ -1139,8 +1213,8 @@ journey artifact family: the task row already *is* the dispatch record, and a se
|
|
|
1139
1213
|
home for the same record would drift.
|
|
1140
1214
|
|
|
1141
1215
|
Dispatch uses the configured host's actual authorization boundary. The creator reviews
|
|
1142
|
-
the recorded change-
|
|
1143
|
-
|
|
1216
|
+
the recorded change-sets and verification outcomes afterwards, wave by wave, until the
|
|
1217
|
+
build plan is fully dispatched.
|
|
1144
1218
|
|
|
1145
1219
|
## References
|
|
1146
1220
|
|
|
@@ -1151,4 +1225,4 @@ one verified task at a time, until the build plan is fully dispatched.
|
|
|
1151
1225
|
|
|
1152
1226
|
Formerly 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):
|
|
1153
1227
|
|
|
1154
|
-
Judge 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
|
|
1228
|
+
Judge 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 READ AGAINST THE WAVE — the run's edits are cleanly attributable to it in the captured change-set (files classed RUN_EXCLUSIVE or APPEARED_DURING_RUN). In a wave the runs share one worktree, so overlap is expected and RECORDED rather than prevented: the run's `concurrency` entry names the runs that overlapped it and the paths they both touched. A change-set dominated by BASELINE_DIRTY_AMBIGUOUS overlap, or captured across a HEAD that moved mid-run, is a CONCERN the reviewer resolves using that record before accepting the run; a run marked `interferenceSuspected`, or whose product a sibling overwrote, is a CONCERN until its re-run alone has landed. Overlap alone is not a GAP. (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 dispatch depth: it runs the ready tasks up to the build parallelism, captures + verifies + records each, and applies onFailure. It does NOT re-decompose the plan (the build-decompose playbook owns the task graph), does NOT choose its own width or a different isolation model (the build parallelism is the person's setting, and the runs share one worktree by design), and does NOT itself author schemas / fields / code (the coding agent does that at dispatch time). Evidence of re-decomposition, a width other than the configured one, or the dispatcher authoring code itself is a CONCERN (scope creep out of the dispatch lane). (The checklist is declarative: nothing executes it; the current host's deterministic checks apply; the approval enum alone adds no gate.)
|