get_subgraph
Explore relationships between architecture concepts by traversing a knowledge graph to identify prerequisites, alternatives, conflicts, and synergies in multi-agent system designs.
Instructions
QUERY PLANNER — Bounded graph traversal from seed concepts. Given one or more concept IDs (from match_concepts or list_concepts), performs BFS up to max_hops and returns all reachable nodes and edges. Use relationship types to discover what the user is missing: alternative_to for competing approaches, requires for prerequisites, conflicts_with for incompatibilities, complements for synergies. Pass consultation_id to log traversal steps for coverage tracking.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| concept_ids | Yes | List of concept IDs to start traversal from | |
| max_hops | No | Maximum traversal depth (1-3, default: 2) | |
| confidence_threshold | No | Minimum edge confidence to traverse (0.0-1.0, default: 0.5) | |
| max_edges | No | Maximum edges to return (1-200, default: 50) | |
| include_descriptions | No | Include edge description text (default: false) | |
| consultation_id | No | Optional consultation ID from match_concepts to log this step |