Dependency Chain
Trace the dependency chain for a goal, project, or task in your knowledge graph.What it does
Maps out all dependencies for a given entity by traversing the knowledge graph to a specified depth. Returns a hierarchical view of what an entity depends on, organized by level, with confidence scores and evidence.Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
entity | string | Yes | The goal, project, or task to trace dependencies for (e.g., “Q2 launch”, “API redesign”, “onboarding flow”) |
maxDepth | number | No | Maximum depth to traverse (1-5, default: 3) |
Returns
Returns dependency information containing:- chain: Array of dependencies organized by depth level
- totalNodes: Total count of nodes in the dependency chain
- depth: Level in the dependency tree (1 = direct dependencies)
- label: Name of the dependency
- nodeType: Type of node (person, project, goal, tool, etc.)
- relationType: Type of relationship (depends_on, needs, etc.)
- confidence: Confidence score for the relationship
- evidenceMemoryIds: Memories that establish this dependency
Examples
Plan project work
Understand blocking issues
Trace goal dependencies
When to use
- Plan work — Identify all tasks needed before starting a project
- Find critical path — Understand which dependencies are blocking progress
- Estimate timelines — See what work must be sequential vs. parallel
- Identify bottlenecks — Spot dependencies that many things rely on
- Risk assessment — Understand how changes to a dependency affect downstream work
Errors
| Error | Cause | Resolution |
|---|---|---|
entity is required | No entity parameter provided | Provide a goal, project, or task name |
maxDepth must be a number | Invalid depth type | Pass a number between 1-5 |
| No dependencies found | Entity exists but has no dependencies in the graph | Check the entity name; add dependency memories via crystal_remember |
Notes
- Depth is clamped to 1-5 automatically (min: 1, max: 5)
- Default depth of 3 captures most practical dependency trees
- Results are organized by level for easy scanning
- Evidence memory IDs link back to where dependencies were recorded
- Total node count includes all nodes across all depths
- Circular dependencies are handled gracefully and will not cause infinite loops
- API-key clients use a recall-based fallback if the full graph query is unavailable
