graph_traverse
Traverse the knowledge graph of institutional memory with four lenses: connected_to, produced_by, provenance, and stats. Trace decisions, find what an agent produced, or get aggregate counts.
Instructions
Traverse the knowledge graph over institutional memory triples. Answers: 'show me everything connected to this issue', 'what did this agent produce', 'trace this decision back', 'which issues produced the most learnings'. Four lenses: connected_to, produced_by, provenance, stats.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"lens": "<lens>"
},
"name": "graph_traverse"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| lens | Yes | Traversal mode: connected_to (all connections to a node), produced_by (what an agent/persona produced), provenance (trace origin chain), stats (aggregate counts) | |
| node | No | Starting node. Examples: 'PROJ-123', 'cli', 'Scar: Done ≠ Deployed'. Required for all lenses except stats. | |
| depth | No | Max chain depth for provenance lens (default: 3) | |
| limit | No | Max triples to return (default: 50) | |
| project | No | Project namespace (e.g., 'my-project'). Scopes sessions and searches. | |
| predicate | No | Filter by predicate (optional) |