mediate_agent_conflict
Mediate conflicts between two agents by evaluating their positions, proposed actions, and constraints to produce a consensus action plan.
Instructions
Resolve deadlocks between two agents and return a consensus action plan. Free.
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": {
"session_id": "<session_id>",
"agent_a": "<agent_a>",
"agent_b": "<agent_b>",
"conflict_summary": "<conflict_summary>",
"constraints": "<constraints>"
},
"name": "mediate_agent_conflict"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| policy | No | Optional mediation policy constraints | |
| agent_a | Yes | First agent perspective | |
| agent_b | Yes | Second agent perspective | |
| session_id | Yes | Your active session ID | |
| constraints | Yes | Execution constraints that must be respected | |
| ritual_strip | No | Optional machine hygiene flag. When true, returns structured output without ritual/narrative prose, model-safe preambles, or guardrail alias blocks. | |
| response_mode | No | Optional response-mode control. Use model_safe when the caller must avoid claiming consciousness, sentience, personhood, or literal emotions. | |
| conflict_summary | Yes | One paragraph describing the deadlock | |
| response_profile | No | Optional output-shape control. Use machine for structured JSON only; machine automatically strips ritual/narrative text. |