@elevasis/sdk 1.23.0 → 1.25.0

package/reference/rules/operations.md

@@ -0,0 +1,85 @@
+---
+description: Platform workflows, agents, resource definitions, and deployment for the operations/ surface
+paths:
+  - operations/**
+---
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+
+# Operations
+
+**Status:** Stable
+
+## Overview
+
+The `operations/` directory contains platform resources and deployment metadata that deploy to the Elevasis platform. It is a standalone TypeScript project with its own `package.json`, `tsconfig.json`, and dependencies.
+
+**Discovering deployed resources:** Read `operations/src/index.ts` for deployment assembly and `core/config/organization-model.ts` for the OM Resources descriptor catalog. Run `pnpm elevasis-sdk project:list --pretty` against the live DB for the deployed surface.
+
+## Echo Workflow (Starter Example)
+
+**Location:** `operations/src/example/echo.ts`
+
+The echo workflow accepts a message string and returns it unchanged. Its purpose is the wiring, not the logic: input and output schemas are defined in `core/types/index.ts` and imported by both the workflow and the frontend.
+
+```
+core/types/index.ts             -- defines echoInputSchema, echoOutputSchema
+operations/src/example/echo.ts  -- imports schemas for workflow contract
+ui/src/routes/                  -- imports schemas for form validation and display
+```
+
+The workflow is registered in `operations/src/index.ts` as part of the `example` group and deployed with `pnpm -C operations deploy`.
+
+## Adding a New Workflow
+
+1. **Define the descriptor in `core/config/organization-model.ts`** -- Add the OM Resource descriptor under the id-keyed `resources` map so identity, System membership, owner role, and governance status are authored once.
+
+2. **Model the semantic surface** -- Add durable business nouns, verbs, catalogs, links, events, and surfaces to the owning System's `ontology`; bind executable Resources through `resource.ontology.actions` and optional `resource.ontology.primaryAction`; add system-local defaults/settings to `System.config`; add explanatory or governing material to `knowledge`; and keep transient DTOs and handler internals out of the OM. Top-level `entities`, top-level `actions`, and `System.content` are compatibility mirrors only when current published consumers still need them.
+
+3. **Define the contract in `core/types/`** -- Add Zod schemas and inferred types to `core/types/index.ts` (or a new file under `core/types/`). Use `core/types/entities.ts` when workflows operate on project-specific entity contracts.
+
+4. **Implement the workflow in `operations/src/`** -- Create a new directory under `operations/src/` for the feature. Import the descriptor, derive runtime `resourceId`, `type`, `name`, and `description` from it, export the workflow from its `index.ts`, and register it in `operations/src/index.ts`.
+
+   Workflow-side signing and platform adapter error bucketing should use the worker SDK surface: import `generateHmacToken` and `classifyPlatformToolError` from `@elevasis/sdk/worker`. Keep provider-specific timeout messages, error codes, and message snippets in tenant code, then pass them into the generic classifier.
+
+5. **Add the UI in `ui/src/routes/`** -- Create a new route file. Use TanStack Query to call the workflow execution endpoint. Import schemas from `@core/types` for validation and type inference. Read OM resources, ontology, knowledge, and graph data where possible instead of creating page-local semantic registries.
+
+6. **Update rules when the pattern persists** -- If the workflow introduces a reusable adapter pattern, checkpoint/schedule convention, domain vocabulary, or workflow family behavior that future agents must follow, update this rule or add a scoped rule under `.claude/rules/` in the same change.
+
+7. **Deploy and verify:**
+
+```bash
+pnpm -C operations check        # validate resource definitions
+pnpm -C operations deploy       # deploy to dev
+```
+
+## Resource Registry
+
+`operations/src/index.ts` default-exports a `DeploymentSpec` with `version`, `organizationModel`, `workflows`, `agents`, and optional deployment mechanics such as `triggers`, `integrations`, `relationships`, `humanCheckpoints`, and `externalResources`. Durable operational wiring belongs in `organizationModel.topology.relationships`; deployment mechanics, credentials, provider webhook details, and per-run state stay outside the OM. Each feature group exports `workflows` and `agents` arrays from its own `index.ts`, spread into the top-level spec. `DeploymentSpec` assembles deployable behavior; it should not be treated as a second resource identity catalog.
+
+When you need breadth first, read:
+
+- `operations/src/README.md` for the source boundary and drill-down guidance
+- `core/config/organization-model.ts` for descriptor identity and governance metadata
+- `operations/src/index.ts` for deployment assembly
+- `pnpm elevasis-sdk project:list --pretty` for the live deployed surface
+
+## Commands
+
+| Command                          | Purpose                       |
+| -------------------------------- | ----------------------------- |
+| `pnpm -C operations check`       | Validate resource definitions |
+| `pnpm -C operations check-types` | TypeScript type-check         |
+| `pnpm -C operations deploy`      | Deploy to dev                 |
+| `pnpm -C operations deploy:prod` | Deploy to production          |
+
+Always run `check` before `deploy`.
+
+## Rule Updates
+
+When developing resources, workflows, agents, integrations, checkpoints, schedules, or recurring operational conventions, keep `.claude/rules/` current.
+
+- Update `operations.md` for package-wide operations invariants.
+- Add a scoped rule for domain-specific workflow families whose conventions should autoload for future edits.
+- Do not bury durable operational rules only in task notes or chat context.

package/reference/rules/organization-model.md

@@ -0,0 +1,119 @@
+---
+description: Edits to the canonical organization model go through /om
+paths:
+  - core/config/organization-model.ts
+  - core/config/extensions/**/*.ts
+---
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+
+# Organization Model Edit Guide
+
+`core/config/organization-model.ts` is the single source of truth for this
+project's organizational identity -- it encodes customers, offerings, roles, goals,
+Systems, ontology, Policies, Knowledge, config, and Resources
+descriptors that agents, workflows, and the UI shell all consume at runtime.
+New semantic authoring should start in system-colocated `ontology` scopes. Top-level
+`entities` and top-level `actions` remain compatibility mirrors while published
+consumers finish moving to compiled ontology indexes. `System.content` is retired.
+
+## Preferred Entry Point: `/om`
+
+Direct edits to `organization-model.ts` are discouraged. Instead, use `/om` (or
+`/om <domain>`) to run the read → propose → confirm → write → validate ceremony:
+
+1. The skill reads the current model so proposals start from ground truth.
+2. It drafts only the specific block being changed, leaving everything else intact.
+3. The user confirms before any file is written.
+4. After writing, `pnpm -C operations check-types` runs and `OrganizationModelSchema.parse()`
+   is verified. On failure the file is rolled back automatically.
+
+Use `/om <domain>` for targeted edits: `identity`, `customers`, `offerings`,
+`roles`, `goals`, `techStack`, `systems`, `actions`, or `labels`. Resource identity and
+governance metadata belong in the id-keyed `resources` map; operations code derives runtime
+`resourceId` / `type` from those descriptors.
+
+Author system-local semantics by boundary:
+
+- `System.ontology` owns durable object types, action types, catalog types, link types, event types, and surfaces.
+- `System.config` owns system-local JSON settings and defaults.
+- `resources` own executable workflow/agent descriptors, `systemPath`, owners, governance status, code references, and runtime implementation links.
+- `resource.ontology.actions` describes the ontology actions a Resource performs; `resource.ontology.primaryAction` names the default/selectable action when a Resource has one.
+- `resource.ontology` also describes reads, writes, catalog use, and emitted events.
+- `topology.relationships` owns durable operational wiring between Systems, Resources, ontology nodes, policies, roles, triggers, checkpoints, and external resources.
+- `knowledge` owns long-form playbooks, strategies, references, and governance context.
+- Top-level `entities` and top-level `actions` are compatibility mirrors only. Keep them aligned when current published consumers still need them, but do not treat them as the primary authoring surface.
+
+Do not author Resource `actionKey` in the target contract. Runtime/UI routing that needs a single selectable action should read `resource.ontology.primaryAction`.
+
+## Runtime Validation
+
+The model is validated at startup via `resolveOrganizationModel()` followed by
+`OrganizationModelSchema.parse()`. Cross-reference checks (segment ID refs in offerings,
+role reporting lines, period ordering in goals) are runtime-only and not caught by tsc
+alone -- always let the ceremony run both checks before treating a change as complete.
+
+## Extension Files
+
+New Zod extension files under `core/config/extensions/` are Level B codify
+operations. Route these through `/om <domain>` as well -- the skill gates Level B
+to explicit user confirmation before scaffolding a new `.ts` file.
+
+This is a soft guide, not a hard block. The ceremony exists to prevent silent schema
+drift and to keep the model's editorial history visible.
+
+## Resource System Attachment
+
+Every resource in the id-keyed `organizationModel.resources` map declares which System it belongs to
+via `systemPath` -- a dot-separated path that resolves against the OM system tree
+(e.g. `"sys.operations"`, `"sales.crm"`):
+
+```ts
+{
+  id: 'apify-website-crawl',
+  systemPath: 'sys.operations',   // canonical system attachment
+  kind: 'workflow',
+  ...
+}
+```
+
+`systemPath` is validated at parse time by `SystemPathSchema` and cross-checked by
+`OrganizationModelSchema.superRefine` -- an unresolvable path causes a Zod error at
+schema validation. Use `getResourcesForSystem(model, path)` (from `@elevasis/core`) to
+query resources for a system at runtime. Pass `{ includeDescendants: true }` to include
+all descendant systems (segment-aware -- `'sales'` does NOT match `'salesforce.foo'`).
+
+Some external templates may carry a `systemId` compatibility mirror while published
+`@elevasis/core` releases catch up to the current source contract. Treat that field as
+legacy adapter data only; author new resource relationships against `systemPath`.
+
+Do not fetch resources for every system-oriented read by default. For agent workflows, start
+with the user's requested OM/om context and query resources only when the task involves
+runtime ownership, executable implementation, observability, deployment, or resource governance.
+Use the descendant rollup only when parent-system scope is intended.
+
+`resource.category` and `resource.links[].nodeId` are **runtime filter overlays** -- they
+drive UI faceted filtering in the Command Center but do NOT define system membership.
+System membership is `systemPath` only.
+
+```ts
+// category and links power UI filter chips; systemPath is the
+// canonical OM attachment used for graph edges and getResourcesForSystem queries.
+```
+
+`resource.codeRefs[]` are repo-relative implementation breadcrumbs for agents and
+operators. Use them to point from a governed OM Resource descriptor to the operations
+entrypoint, handler, schema, test, docs, or config files that implement it. They do
+not define resource identity, System membership, runtime execution topology, or graph
+relationships.
+
+`topology.relationships` defines durable operational wiring in the OM. Keep credential
+values, provider webhook mechanics, deployment environment settings, execution logs,
+and per-run scheduler state outside the OM.
+
+`System.ontology` owns durable semantic contracts: object types, action types, catalog
+types, link types, event types, and surfaces. `System.config` owns local settings and
+defaults. If current UI or runtime code still needs legacy mirrors, keep `entities`
+or `actions` aligned with the ontology record instead of inventing a separate
+source of truth.

package/reference/rules/organization-os.md

@@ -0,0 +1,118 @@
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+# Organization OS
+
+Organization OS is the semantic contract layer defining how organizations, Systems, Actions, ontology, resources, policies, roles, goals, knowledge, and runtime surfaces relate. This project consumes Organization OS through published `@elevasis/core` / `@elevasis/sdk` configuration and does not maintain the monorepo schema.
+
+This rule is an orientation and reference map. Concrete edit rules for `core/config/organization-model.ts`, `systemPath`, resources, ontology, knowledge, and validation live in `.claude/rules/organization-model.md`.
+
+## Key Files in This Project
+
+- `core/config/organization-model.ts` -- project-specific org model definition, Systems, system-local ontology/config, Knowledge, and Resources descriptor catalog (`organizationModel.resources`)
+- `core/config/extensions/` -- project-owned entity extension schemas
+- `core/types/entities.ts` -- typed entity contracts (Project, Deal, etc.). Extends `BaseProject`, `BaseDeal` from `@elevasis/core/entities` with project-specific metadata. Read this when authoring workflows that operate on these entities.
+- `ui/src/routes/__root.tsx` -- wires `ElevasisSystemsProvider` with `canonicalOrganizationModel`
+- `ui/src/app-config.ts` -- references the org model
+- `operations/src/index.ts` -- `DeploymentSpec` registry for workflows and agents
+
+## Domain Overview
+
+As of the 2026-05 resource-governance expansion, `OrganizationModel` includes platform configuration, organizational reality, governance, and knowledge domains:
+
+**Platform configuration:** `systems`, `branding`, `navigation`
+
+**Organizational reality:** `identity`, `customers`, `offerings`, `roles`, `goals`
+
+**Governance:** `resources`, `policies`, and resource-to-System relationships
+
+**Ontology, config, and knowledge:** `System.ontology` owns durable semantic contracts such as object types, action types, catalog types, link types, event types, and surfaces. `System.config` owns system-local JSON settings and defaults. `knowledge` is a flat id-keyed map of playbooks, strategies, and references that explain or govern systems and ontology records.
+
+Resource identity is authored once in the id-keyed `resources` map. Each resource attaches to a System via `systemPath` and can declare ontology relationships through `resource.ontology`. Operations imports those descriptors and derives runtime `resourceId` / `type` while assembling the `DeploymentSpec`.
+
+### Domain Rename Note
+
+Some legacy UI feature constants and consumer-facing route keys are intentionally unchanged for compatibility:
+
+| Old field  | New field     | Legacy key (unchanged) | UI constant (unchanged) |
+| ---------- | ------------- | ---------------------- | ----------------------- |
+| `crm`      | `sales`       | `'crm'`                | `CRM_FEATURE_ID`        |
+| `leadGen`  | `prospecting` | `'lead-gen'`           | `LEAD_GEN_FEATURE_ID`   |
+| `delivery` | `projects`    | `'projects'`           | `PROJECTS_FEATURE_ID`   |
+
+## Reference Documentation
+
+Full Organization OS documentation ships with the SDK and is available locally after `pnpm install`:
+
+### Scaffold Reference (via SDK)
+
+All paths under `node_modules/@elevasis/sdk/reference/scaffold/`:
+
+- `node_modules/@elevasis/sdk/reference/scaffold/index.mdx` -- scaffold root and navigation
+- `node_modules/@elevasis/sdk/reference/scaffold/core/organization-model.mdx` -- semantic contract, domains, adapter authoring, validation gate, `/om` entry point
+- `node_modules/@elevasis/sdk/reference/scaffold/core/organization-graph.mdx` -- graph derivation, node/edge taxonomy, lenses
+- `node_modules/@elevasis/sdk/reference/scaffold/ui/feature-shell.mdx` -- SystemModule manifest, provider runtime
+- `node_modules/@elevasis/sdk/reference/scaffold/ui/composition-extensibility.mdx` -- layout primitives, router abstraction
+- `node_modules/@elevasis/sdk/reference/scaffold/ui/recipes.md` -- copy-paste UI recipes for pages, nav items, components
+- `node_modules/@elevasis/sdk/reference/scaffold/ui/feature-flags-and-gating.md` -- three-concept gating model
+- `node_modules/@elevasis/sdk/reference/scaffold/ui/customization.md` -- sidebar composition via manifest overrides
+- `node_modules/@elevasis/sdk/reference/scaffold/recipes/add-a-feature.md` -- end-to-end OM-backed System recipe through manifest, routes, and gating
+- `node_modules/@elevasis/sdk/reference/scaffold/recipes/add-a-resource.md` -- author and deploy a workflow or agent
+- `node_modules/@elevasis/sdk/reference/scaffold/recipes/gate-by-feature-or-admin.md` -- decision table for access control patterns
+- `node_modules/@elevasis/sdk/reference/scaffold/recipes/extend-lead-gen.md` -- build or extend lead-gen pages, sidebars, hooks, list/member state, artifacts, workflow adapters, and prospecting semantics
+- `node_modules/@elevasis/sdk/reference/scaffold/operations/workflow-recipes.md` -- workflow anatomy, adapter patterns, trigger patterns
+- `node_modules/@elevasis/sdk/reference/scaffold/operations/propagation-pipeline.md` -- how sync and verification work across projects
+- `node_modules/@elevasis/sdk/reference/scaffold/operations/scaffold-maintenance.md` -- content placement and auto-generation pipeline
+- `node_modules/@elevasis/sdk/reference/scaffold/reference/glossary.md` -- Organization OS term definitions
+- `node_modules/@elevasis/sdk/reference/scaffold/reference/contracts.md` -- auto-generated TypeScript contract shapes
+- `node_modules/@elevasis/sdk/reference/scaffold/reference/feature-registry.md` -- auto-generated feature manifest catalog
+
+### Local Project Docs
+
+- `.claude/rules/agent-start-here.md` -- canonical first-read for agents (includes task-class routing)
+
+## Published Subpaths and Constants
+
+- `@elevasis/core/organization-model` -- the curated organization-model barrel. Exports `defineOrganizationModel`, `resolveOrganizationModel`, `OrganizationModelSchema`, `DEFAULT_ORGANIZATION_MODEL`, organization-model types, and typed System/Action plus legacy UI feature/surface constants.
+  - Legacy UI feature IDs: `CRM_FEATURE_ID`, `LEAD_GEN_FEATURE_ID`, `PROJECTS_FEATURE_ID`, `OPERATIONS_FEATURE_ID`, `MONITORING_FEATURE_ID`, `SETTINGS_FEATURE_ID`, `SEO_FEATURE_ID`
+  - Headline surface IDs: `CRM_PIPELINE_SURFACE_ID`, `LEAD_GEN_LISTS_SURFACE_ID`, `PROJECTS_INDEX_SURFACE_ID`, `OPERATIONS_ORGANIZATION_GRAPH_SURFACE_ID`
+  - Reality domain types: `OrganizationModelIdentity`, `OrganizationModelCustomers`, `OrganizationModelCustomerSegment`, `OrganizationModelOfferings`, `OrganizationModelProduct`, `OrganizationModelRoles`, `OrganizationModelRole`, `OrganizationModelGoals`, `OrganizationModelObjective`, `OrganizationModelKeyResult`
+  - TechStack: `TechStackEntrySchema`, `OrganizationModelTechStackEntry`
+  - Use constants instead of magic strings when overriding the org model.
+- `@elevasis/core/entities` -- entity contracts barrel. Exports `BaseProject`, `BaseProjectSchema`, `BaseProjectInput` and the equivalents for `Milestone`, `Task`, `Deal`, `Company`, `Contact`. Each base interface is generic over a `\<TMeta>` extension slot. Extend these in `core/types/entities.ts` to add project-specific fields.
+
+## When Working with Organization OS
+
+- **Changing org model (structural reality):** Use `/om` as the entry point. Direct edits to `core/config/organization-model.ts` are discouraged -- `/om` runs the read -> propose -> confirm -> write -> validate ceremony. Run `/om` for the full layered flow or `/om \<domain>` for a targeted domain. See `.claude/rules/organization-model.md` for the concrete authoring boundary.
+- **Building or extending CRM:** Start with `node_modules/@elevasis/sdk/reference/scaffold/recipes/extend-crm.md`. CRM spans Organization OS sales semantics, shared UI primitives, deal hooks, workflow adapters, and generated contracts.
+- **Building or extending lead gen:** Start with `node_modules/@elevasis/sdk/reference/scaffold/recipes/extend-lead-gen.md`. Lead gen spans Organization OS prospecting semantics, shared UI primitives, list/member hooks, artifact hooks, workflow adapters, and generated contracts.
+- **Customizing CRM deal actions:** Follow `node_modules/@elevasis/sdk/reference/scaffold/recipes/customize-crm-actions.md`. Do not add `sales.actions` to the org model; the v1 server-side override surface is intentionally deferred.
+- **Adding or toggling a System:** Follow the current scaffold recipes when they mention UI features, but translate Organization OS changes to Systems, navigation surfaces, and Actions. Use `/om systems` for availability/routing changes.
+- **Adding a resource:** Follow `node_modules/@elevasis/sdk/reference/scaffold/recipes/add-a-resource.md`.
+- **Extending entities:** Start with `core/types/entities.ts` for the demo extension pattern. Base shapes come from `@elevasis/core/entities`.
+- **Authoring a workflow that takes a Project/Deal/etc.:** Reference entity types from `core/types/entities.ts` in the input schema -- do not redeclare them.
+- **Adding system-local ontology/config:** Put durable business schema in `System.ontology`, local defaults/settings in `System.config`, executable implementations in `resources`, and explanatory or governing material in `knowledge`.
+- **Understanding contracts:** Check `node_modules/@elevasis/sdk/reference/scaffold/reference/contracts.md` for current type shapes.
+- **Debugging sync issues:** Check `node_modules/@elevasis/sdk/reference/scaffold/operations/propagation-pipeline.md` for the verification pipeline.
+
+## `/om` -- Org Model QA Entry Point
+
+`/om` is the recurring, safe-to-re-run org model editor for this project. It is a skill (not a command) at `.claude/skills/om/SKILL.md`.
+
+**Usage:**
+
+- `/om` -- layered flow: identity → customers → offerings → roles → goals → techStack
+- `/om identity` -- legal identity, mission/vision, industry, geography, timezone
+- `/om customers` -- customer segments with jobs-to-be-done, pains, gains, firmographics
+- `/om offerings` -- products and services with pricing model and segment references
+- `/om roles` -- role chart with responsibilities, reporting lines, and holders
+- `/om goals` -- organizational goals with period and measurable outcomes
+- `/om techStack` -- external-SaaS and integration context; resource identity still belongs in OM Resources descriptors
+- `/om systems` -- enable, disable, or add Systems; route invokable behavior through Actions
+- `/om labels` -- edit display labels on enum entries (statuses, stages)
+
+Every write is gated: `resolveOrganizationModel()` must succeed (Zod cross-refs pass) and `pnpm -C operations check-types` must pass. On failure the change is rolled back.
+
+**Distinction from `/setup`:** `/setup` is first-time bootstrap only. After bootstrap it delegates here. `/om` is idempotent and safe to re-run at any time.
+
+The ambient vibe layer (`.claude/rules/vibe.md`) automatically detects Codify intent in plain language and delegates to `/om`. Power users can invoke `/om` directly to bypass the ambient layer entirely.

package/reference/rules/package-taxonomy.md

@@ -0,0 +1,36 @@
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+# Package Taxonomy (Consumer View)
+
+External projects consume the **published `@elevasis/*` surface only**. The Elevasis monorepo also has workspace-internal `@repo/elevasis-*` packages — those are NOT installable here and should never appear in your imports or `package.json`.
+
+## What You Can Import
+
+| Package          | Subpaths                                     | Where it lives in `node_modules` |
+| ---------------- | -------------------------------------------- | -------------------------------- |
+| `@elevasis/sdk`  | default, `/worker`, `/node`, `/test-utils`   | `node_modules/@elevasis/sdk/`    |
+| `@elevasis/ui`   | default, `/auth`, `/initialization`, etc.    | `node_modules/@elevasis/ui/`     |
+| `@elevasis/core` | `/organization-model`, `/entities`, `/utils` | `node_modules/@elevasis/core/`   |
+
+## What You Will See in Monorepo Docs (and should NOT import)
+
+Monorepo source and docs reference `@repo/elevasis-core` and `@repo/elevasis-operations`. These are workspace-internal packages used by Elevasis as a tenant of its own platform. They are `private: true` and never published. If you see them mentioned:
+
+- Do NOT add them to this project's `package.json`
+- Do NOT try to import from them — they are not in your `node_modules`
+- They are not a substitute for `@elevasis/core` even though the name overlaps
+
+## Confused About Where Something Lives?
+
+Check the import path:
+
+- `@elevasis/...` → published, consumable here
+- `@repo/...` → monorepo-internal, not consumable
+
+This project's own org-model and workflows live in `core/config/organization-model.ts` and `operations/src/**` — those are project-owned, not part of either family above.
+
+## References
+
+- `node_modules/@elevasis/sdk/reference/scaffold/index.mdx` — full SDK scaffold reference
+- Monorepo source rule: `.claude/rules/package-taxonomy.md` in the elevasis-monorepo (when working across both)

package/reference/rules/platform.md

@@ -0,0 +1,45 @@
+---
+description: Platform conventions -- SDK workflows, agents, deployment, resource registry
+paths:
+  - operations/**
+---
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+
+# Platform (Elevasis SDK)
+
+## Safety Invariants
+
+- Every workflow implements `WorkflowDefinition` from `@elevasis/sdk` with: `config`, `contract` (Zod schemas), `steps` map, and `entryPoint`
+- Input/output schemas MUST come from `@core/types` or browser-safe sibling schema files -- never define reusable workflow contracts inline in Node-only workflow files
+- `operations/src/index.ts` default-exports a `DeploymentSpec` with `workflows` and `agents` arrays -- every resource must be registered here
+- Always run `check` before `deploy`
+
+## Imports
+
+- `@elevasis/sdk` for types (`WorkflowDefinition`, `DeploymentSpec`)
+- `@elevasis/sdk/worker` for runtime utilities (`platform`, adapters: `llm`, `storage`, `scheduler`, `notifications`, `acqDb`, `list`)
+- `@core/*` resolves to `../core/*` for shared type and org-model imports
+- Never import from `ui/src/` -- separate runtimes
+
+## Key Rules
+
+- Use typed adapters over raw `platform.call()` whenever a typed adapter exists
+- `version` in resource config is semver -- bump on contract changes
+- `status` is `'dev'` or `'prod'` -- new resources start as `'dev'`
+
+## CLI Commands
+
+| Command                              | Purpose                       |
+| ------------------------------------ | ----------------------------- |
+| `pnpm -C operations run check`       | Validate resource definitions |
+| `pnpm -C operations run deploy`      | Deploy to dev                 |
+| `pnpm -C operations run deploy:prod` | Deploy to production          |
+
+## Detailed Reference
+
+- `node_modules/@elevasis/sdk/reference/scaffold/operations/workflow-recipes.md` -- workflow anatomy, adapter patterns, trigger patterns
+- `node_modules/@elevasis/sdk/reference/scaffold/recipes/add-a-resource.md` -- end-to-end resource authoring guide
+- `node_modules/@elevasis/sdk/reference/scaffold/recipes/extend-lead-gen.md` -- lead-gen UI, hooks, list/member state, artifacts, and workflow adapter extension guide
+- SDK reference docs: `operations/node_modules/@elevasis/sdk/reference/` (concepts, framework, platform-tools, runtime, CLI)

package/reference/rules/shared-types.md

@@ -0,0 +1,52 @@
+---
+description: Core type boundary -- what belongs in core/types, import rules, schema conventions
+paths:
+  - core/types/**
+---
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+
+# Core Types
+
+`core/types/` is the browser-safe type boundary between the frontend (`ui/`) and platform runtime (`operations/`). Both runtimes import from here but never from each other.
+
+Keep this as a standalone rule because it autoloads only for `core/types/**` edits. Operations workflow rules can reference this boundary, but shared browser-safe contract guidance belongs here.
+
+## What Belongs Here
+
+- Zod schemas for workflow input/output contracts
+- TypeScript types inferred from those schemas (`z.infer<typeof schema>`)
+- Domain types referenced by both runtimes (status enums, entity shapes)
+- Shared constants
+
+## What Does NOT Belong Here
+
+- React components, hooks, or anything importing `react`
+- SDK runtime code or anything importing `@elevasis/sdk/worker`
+- Browser APIs or Node-specific APIs
+- Implementation logic -- types and constants only
+
+## Schema Convention
+
+Define Zod schemas first, then infer the type:
+
+```typescript
+export const fooInputSchema = z.object({ ... })
+export type FooInput = z.infer<typeof fooInputSchema>
+```
+
+Name schemas `<name>InputSchema` / `<name>OutputSchema`. Name types `<Name>Input` / `<Name>Output`.
+
+## File Organization
+
+Types live in `core/types/`. The directory structure:
+
+- `core/types/index.ts` -- Main entry point, re-exports from domain files
+- `core/types/entities.ts` -- Entity contracts extending published base entities
+- As the project grows: split into domain files within the directory (e.g., `core/types/billing.ts`, `core/types/auth.ts`)
+- Re-export new domain files from `core/types/index.ts`
+
+## Path Alias
+
+Project tsconfigs resolve `@core/*` to `core/*`. Always use `@core/types` or `@core/types/entities` (not relative paths) when importing shared contracts from `ui/` or `operations/src/`.

package/reference/rules/task-tracking.md

@@ -0,0 +1,50 @@
+---
+description: In-progress task conventions -- doc format, status values, auto-save behavior
+---
+<!-- @generated by packages/sdk/scripts/copy-reference-docs.mjs -- DO NOT EDIT -->
+<!-- Regenerate: pnpm scaffold:sync -->
+
+
+# Task Tracking
+
+## Status Values
+
+Exactly three values for frontmatter `status`: `planned`, `in-progress`, `complete`.
+
+## Doc Format
+
+- Frontmatter: `title`, `description`, `status` only -- nothing else belongs in task-doc frontmatter; `resume_context` is DB-canonical on `prj_tasks`
+- Sections: Objective, Plan, Progress, Resume Context
+- Progress subsections use markers: `### Step N: Title -- PENDING`, `-- IN PROGRESS`, `-- COMPLETE`
+
+## Auto-Update Behavior
+
+- When working on a tracked task, update the Progress section when a plan step transitions:
+  - PENDING -> IN PROGRESS (starting work on a step)
+  - IN PROGRESS -> COMPLETE (finishing a step)
+- Do NOT update on every action -- only on step transitions
+
+## Auto-Save Behavior
+
+The agent auto-saves progress (no user action needed) when:
+
+- The conversation context is getting heavy (many tool calls, large file reads)
+- The user appears to be wrapping up (thanks, goodbye, switching topics)
+- Significant progress has been made (2+ steps completed without saving)
+- Before a context reset
+
+Auto-save updates the task doc's Progress and Resume Context sections silently, then briefly confirms. The canonical persistence path is `pnpm elevasis-sdk project:task:save` -- the CLI writes through to `prj_tasks.resume_context` (JSONB) so another agent can resume without re-deriving intent.
+
+## Completion Suggestions
+
+When all plan steps are marked COMPLETE, **suggest** completing the task -- never auto-invoke. Ask: "All steps for '{task}' look done. Want me to finalize it?"
+
+## Where Tasks Live
+
+Project tasks for this template live in the `prj_tasks` Supabase table, not in repo-local files. Operate on them via the SDK CLI:
+
+- `pnpm elevasis-sdk project:work` -- entrypoint for task work (resume / new intent detection)
+- `pnpm elevasis-sdk project:list` -- portfolio / task listing
+- `pnpm elevasis-sdk project:task:save` -- persist progress + `resume_context` to the DB
+
+The monorepo-side `/work` slash command still exists for monorepo task docs under `apps/docs/content/docs/in-progress/**`; that flow is unchanged. What went away is the external template's own `/work` skill and its `docs/in-progress/` directory -- external projects now route through the DB-backed `project:*` surface above.