brain_resolve_conflict
Arbitrate a contested topic by picking the winning side—success reaffirms the fix, failure retires the lesson with human-in-the-loop confidence.
Instructions
Arbitrate a contested topic by picking the winning side. winner="success" reaffirms the fix (the contradicting failure stops blocking recall); winner="failure" retires the fix (its CKG fixes-edges decay to ~0 and the losing lesson is archived). Human-in-the-loop resolution is the strongest possible confidence signal. List open conflicts first with brain_conflicts.
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": {
"instance_id": "<instance_id>",
"topic": "<topic>",
"winner": "<winner>"
},
"name": "brain_resolve_conflict"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| topic | Yes | The contested topic, e.g. "fix:jwks-rotation" | |
| winner | Yes | Which side wins the arbitration | |
| instance_id | Yes | Brain instance ID | |
| resolved_by | No | Who resolved it (agent name or "human"); default "human" |