calls_agent_duel
ActiveTool of io.github.saloprj/dialogbrain
declared in 1.17.0
Start an agent-vs-agent VOICE test call: two AI voice agents share one LiveKit room — a 'caller' persona agent pursues a task brief against the 'callee' business agent under test. Use to evaluate booking flows, latency, and conversation quality without a human caller. The CALLER agent should have an EMPTY voice_greeting (it must stay silent until the callee greets) and voice_filler_enabled=false. Afterwards inspect both call_ids with agents.traces_list / calls.get_transcript. A subscribe-only `listen` token is returned for listening in live.
Parameters schema
{
"type": "object",
"required": [
"callee_agent_id",
"caller_agent_id",
"task"
],
"properties": {
"task": {
"type": "string",
"description": "The caller's brief — objective, persona details (name, phone), and when to end the call. Woven into its prompt as call instructions."
},
"max_duration_s": {
"type": "integer",
"maximum": 900,
"minimum": 30,
"description": "Hard cap on the call in seconds (30-900, default 300)."
},
"callee_agent_id": {
"type": "integer",
"description": "Agent under test (answers and greets first). From agents.list."
},
"caller_agent_id": {
"type": "integer",
"description": "Customer-persona agent that places the call. Must be a different agent, active, with empty voice_greeting."
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
io.github.saloprj/dialogbrain
https://github.com/saloprj/dialogbrain-mcp
1/7 registries