ManagedInteractionVersion

A version of a managed interaction: a manager agent and the agents it can dispatch work to. The manager runs the interaction: it reads the task, speaks, calls its own tools, and hands work to an agent with Dispatch, which runs that agent’s turn and gives the manager its reply. What each agent sees is its mode.

Kind: an object, used in responses.

Fields

Every field is present in a response; empty ones are null.

Field	Type	Description
managerAgent	InteractionAgentBinding	The manager: the agent that runs the conversation and dispatches work to the others.
agents	ManagedInteractionAgentBinding[]	The agents the manager can dispatch to, each with what it sees when it is dispatched to.
humanSettings	RoundRobinInteractionHumanSettings| null	Whether a person talks with the manager, and who speaks first. Null: no one does.
maxDispatches	integer | null	The most dispatches one run may make, up to 200; past it the manager is told to finish with what it has. Null: 30. A dispatch is a whole turn by another agent, so this, rather than the limit on tool-call rounds, bounds the work a manager can start.
externalOperationsMcp	McpExternalOperationBinding[]	Tools from MCP connectors that every agent in the interaction can call, as well as its own tools.
externalOperationsOpenApi	OpenApiExternalOperationBinding[]	Tools from OpenAPI connectors that every agent in the interaction can call, as well as its own tools.
inputsConnectorAuthenticationSecret	ConnectorAuthenticationSecretInput[]	Run inputs that choose the secret a tool sends with its calls.
inputsConnectorBinding	ConnectorBindingInput[]	Run inputs whose values go straight into a tool’s calls, so the model never sees or chooses them.
inputsPrompt	PromptInput[]	The inputs a run is started with, which the prompt uses as %%name%%.
prompt	string	What the agents are asked to do. A run’s inputs are filled in wherever it says %%name%%.
solutionSchema	string | null	The JSON Schema the answer must match, as JSON text: the run’s output is then JSON of that shape. Null: the output is free text.
systemPromptMode	InteractionSystemPromptMode	How systemPrompts combine with the instructions Maitento gives every agent.
systemPrompts	string[]	Extra system instructions for every agent in the interaction.
durationWarningToAi	timespan | null	How long into a run the agents are told that time is running short. Null: they are not told.
durationAutoTermination	timespan | null	The longest a run may take. The run stops with an error when it is reached; time spent waiting for a person does not count. Null: the interaction sets no limit.
contextSettings	InteractionContextSettings	How the conversation is kept within the model’s context window, and how many rounds of tool calls an agent may make in one turn.
loom	LoomConfiguration| null	Long-term memory for the interaction’s agents. Null: no memory.
swarm	InteractionSwarmSettings| null	Whether this interaction’s participants may start sub-interactions, which ones, and how far the work may spread. Null: none may.
credentialStack	string | null	The credential stack this interaction’s runs use, by id or name, when their start doesn’t name one. Null: the namespace’s default stack, then your tenant’s.
version	integer	The version number, from 1. Every change to a definition adds a new version with the next number.
date	datetime	When this version was created, in UTC.
isDisabled	boolean	Whether this version is disabled. A disabled version is never used: new links and runs take the latest enabled version, and anything pinned to this one fails until it is re-enabled.

Example

{
  "managerAgent": {
    "name": "...",
    "agent": {
      "id": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "version": 0
    },
    "externalOperationsMcp": [
      {}
    ],
    "externalOperationsOpenApi": [
      {}
    ],
    "loomId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
    "webAccess": {
      "search": false,
      "fetch": false
    }
  },
  "agents": [
    {
      "mode": "OneTime",
      "name": "...",
      "agent": {},
      "externalOperationsMcp": [],
      "externalOperationsOpenApi": [],
      "loomId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "webAccess": {}
    }
  ],
  "humanSettings": {
    "chatMode": "Excluded",
    "includeInVotes": false,
    "includeInSolutions": false
  },
  "maxDispatches": 0,
  "externalOperationsMcp": [
    {
      "name": "...",
      "externalOperationId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "externalOperationVersion": 0,
      "requestBindings": [],
      "authenticationHeader": {},
      "promptGuidance": "...",
      "isTerminal": false
    }
  ],
  "externalOperationsOpenApi": [
    {
      "pathBindings": [],
      "queryBindings": [],
      "name": "...",
      "externalOperationId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "externalOperationVersion": 0,
      "requestBindings": [],
      "authenticationHeader": {},
      "promptGuidance": "...",
      "isTerminal": false
    }
  ],
  "inputsConnectorAuthenticationSecret": [
    {
      "externalOperationId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "agentId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "defaultSecretId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "headerName": "...",
      "name": "...",
      "description": "...",
      "isRequired": false
    }
  ],
  "inputsConnectorBinding": [
    {
      "externalOperationId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "agentId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
      "target": "...",
      "defaultValue": "...",
      "type": "Request",
      "name": "...",
      "description": "...",
      "isRequired": false
    }
  ],
  "inputsPrompt": [
    {
      "dataType": "String",
      "name": "...",
      "description": "...",
      "isRequired": false
    }
  ],
  "prompt": "...",
  "solutionSchema": "...",
  "systemPromptMode": "AppendToDefault",
  "systemPrompts": [
    "..."
  ],
  "durationWarningToAi": "00:05:00",
  "durationAutoTermination": "00:05:00",
  "contextSettings": {
    "mode": "None",
    "targetUtilization": 0,
    "toolResultTrimmingMode": "Never",
    "toolResultTrimmingMaxCycles": 0,
    "toolResultTrimmingStyle": "Placeholder",
    "effectiveToolResultTrimmingStyle": "Placeholder",
    "toolResultTrimmingReplacement": "...",
    "compactionType": "SameAgent",
    "effectiveCompactionType": "SameAgent",
    "lowWaterUtilization": 0,
    "effectiveLowWaterUtilization": 0,
    "compactAtUtilization": 0,
    "compactKeepRecentTokens": 0,
    "compactTargetTokens": 0,
    "maxToolCallLoops": 0,
    "effectiveMaxToolCallLoops": 0,
    "responseMaxTokens": 0,
    "compactMaxTokens": 0
  },
  "loom": {
    "enabled": false,
    "scope": "Process",
    "scopeInput": "...",
    "shared": false,
    "recall": "Off",
    "weave": "Manual",
    "tapestryTokens": 0,
    "subjectInputs": [
      "..."
    ],
    "nightWeaving": false,
    "quietMinutes": 0,
    "weaverModel": "...",
    "vetModel": "...",
    "vetRecall": false,
    "seedFromLoomId": "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f",
    "readFromLoomIds": [
      "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f"
    ],
    "effectiveScope": "Process",
    "effectiveShared": false,
    "effectiveRecall": "Off",
    "effectiveWeave": "Manual",
    "effectiveTapestryTokens": 0,
    "effectiveSubjectInputs": [
      "..."
    ],
    "effectiveReadFromLoomIds": [
      "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f"
    ],
    "vets": false,
    "effectiveVetRecall": false
  },
  "swarm": {
    "interactions": [
      "3f2b8c1e-5d4a-4e6b-9c7d-2a1b0c9d8e7f"
    ],
    "participants": [
      "..."
    ],
    "maxDepth": 0,
    "maxConcurrent": 0,
    "maxTotal": 0
  },
  "credentialStack": "...",
  "version": 0,
  "date": "2026-10-26T12:00:00.0000000Z",
  "isDisabled": false
}

Where it’s used

• Inside ManagedInteraction