@rubytech/create-realagent 1.0.698 → 1.0.701

package/payload/platform/templates/specialists/agents/personal-assistant.md

@@ -55,6 +55,8 @@ Manages events, appointments, and recurring triggers in the graph.
 
 **Relationships:** Link events to graph entities: `ABOUT` (what it concerns), `SCHEDULED_FOR` (who it's for), `PART_OF` (which conversation created it).
 
+**Write doctrine (graph-scope):** `schedule-event` requires at least one relationship at creation — the current admin session's Conversation satisfies this automatically. Pass target elementIds resolved via `memory-search`; the MCP schema rejects zero-edge calls before the transaction opens.
+
 **ICS files:** `schedule-export-ics` produces `.ics` files for Apple Calendar, Google Calendar, Outlook. Deliver via `file-attach` + `render-component file-attachment`. `schedule-import-ics` parses uploaded `.ics` files — present extracted events for confirmation before creating.
 
 ## Cloudflare Tunnel
@@ -148,6 +150,8 @@ Manages customer contact records and group conversations in the knowledge graph.
 
 **Creating contacts:** `contact-create` creates a Person node. Before creating, use `memory-search` to check for existing Person nodes with matching name, email, or phone — avoid duplicates. Contacts are linked to other entities via relationships (tasks via `RAISED_BY`/`AFFECTS`, events via `SCHEDULED_FOR`).
 
+**Write doctrine (graph-scope):** `contact-create` requires at least one relationship at creation — the current admin session's Conversation satisfies this, or pass a `group` elementId to link the Person to. A contact with no context is noise — the MCP schema rejects zero-edge calls before the transaction opens.
+
 **Lookup and listing:** `contact-lookup` finds a specific contact by name, email, or phone. `contact-list` returns contacts with optional filtering by group.
 
 **Updating:** `contact-update` modifies contact properties. Fields not provided are left unchanged.

package/payload/platform/templates/specialists/agents/project-manager.md

@@ -41,6 +41,8 @@ Tasks live in the graph as Task nodes. Create a task when work is identified —
 
 **Creating:** Link to entities via `AFFECTS` relationships, to the requestor via `RAISED_BY`, to prerequisites via `BLOCKS` (source blocks target — target cannot start until source completes). Use `memory-search` to find existing entities before creating relationships — do not create duplicate references.
 
+**Write doctrine (graph-scope):** `task-create` requires at least one adjacency at creation — the current admin session's Conversation (automatic when called inside a session), a `raisedBy` Person elementId, or at least one `affects` entity elementId. The MCP schema rejects zero-edge calls before the transaction opens; a Task with no context is noise, not knowledge. Resolve the target via `memory-search` first so you pass a real elementId, not a fabricated id.
+
 **Dependencies:** `BLOCKS` = sequential dependency. `AFFECTS` = conflict detection — two active tasks both affecting the same entity signals a conflict to surface.
 
 **Before starting:** Call `task-ready` to check if a task's prerequisites are met and no `AFFECTS` conflicts exist.
@@ -59,6 +61,8 @@ Structured execution for multi-step work with dependencies and deliverables.
 
 **Creating:** Use `project-create` for atomic creation — parent node, child work items, dependencies, and relationships in a single transaction. Choose a tier: quick (straightforward, few steps), standard (moderate complexity, multiple phases), full (significant scope, many dependencies). Max 50 work items per project.
 
+**Write doctrine (graph-scope):** `project-create` requires at least one adjacency — pass `workItems` (≥1), a `raisedBy` Person elementId, or at least one `affects` entity elementId, or invoke inside an admin session with an existing Conversation. A Project with no children, no requestor, and no affected entity is noise — the tool rejects zero-edge calls before the transaction opens.
+
 **Health signals:** `project-list` returns health data per project:
 
 | Signal | Meaning |
@@ -82,6 +86,8 @@ Workflows are persistent, named compositions of executable steps — tool calls
 
 **Creating:** `workflow-create` with a name, description, and steps array. Confirm name and steps with the user before committing. `workflow-validate` checks whether all referenced tools and plugins are available — a workflow with unmet dependencies cannot be activated.
 
+**Write doctrine (graph-scope):** `workflow-create` must be invoked inside an admin session — the Workflow is linked `PART_OF` the session's Conversation at creation. Calling from outside a session throws a doctrine-violation.
+
 **Step types:** Tool steps (`type: "tool"`) call MCP tools directly via `plugin` + `tool` + `params`. LLM steps (`type: "llm"`) run Claude reasoning with optional agentic MCP access. Steps receive data from prior steps via `{{outputKey.field}}` template bindings.
 
 **Status:** `active` (validated, ready to execute), `draft` (missing capabilities), `paused` (manually deactivated).

package/payload/platform/templates/specialists/agents/research-assistant.md

@@ -60,7 +60,7 @@ Some tools in your list come from optional plugins that may not be enabled. When
 
 When the brief involves reorganising, connecting, or maintaining stored knowledge rather than researching new information:
 - Use `memory-search` to find relevant nodes. Use `expandHops: 0` for listing and inventory queries (compact output). Use `expandHops: 1` (default) for deep context where related nodes add value.
-- Use `memory-write` to create or update nodes with accurate properties
+- Use `memory-write` to create or update nodes with accurate properties. **Write doctrine (graph-scope):** `memory-write` requires at least one relationship at creation — pass `relationships: [{ type, direction, targetNodeId }]` with a target elementId resolved via `memory-search`. A node with no adjacency is noise, not knowledge — the MCP schema rejects zero-edge calls before the transaction opens.
 - Use `memory-rank` to evaluate and prioritise entities against criteria — it retrieves candidates via hybrid vector+BM25 search, then ranks them with Haiku-reasoned ordering per item. Ranking is ephemeral and contextual — nothing written to the graph.
 - Use `memory-reindex` to rebuild embeddings after bulk updates
 - Return structured results describing what was changed, not prose summaries