StartAgentRunRequestBody
Request body for starting an agent run: a JSON:API document, `{ "data": { "type": "StartAgentRunRequest", "attributes": { ... } } }`, per the ZI public-API standard for request bodies. The run input lives in `data.attributes`; the same body is used by Start Agent Run and Start Agent Run (Stream).
Properties
| Name | Type | Description |
|---|---|---|
| data | object | The primary data of the document |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://raw.githubusercontent.com/api-evangelist/gtm/main/json-schema/gtm-start-agent-run-request-body-schema.json",
"title": "StartAgentRunRequestBody",
"description": "Request body for starting an agent run: a JSON:API document,\n`{ \"data\": { \"type\": \"StartAgentRunRequest\", \"attributes\": { ... } } }`,\nper the ZI public-API standard for request bodies. The run input lives in\n`data.attributes`; the same body is used by Start Agent Run and Start Agent\nRun (Stream).",
"x-generated": "2026-10-20",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/gtm-agent-api-v1-api-openapi.yml#/components/schemas/StartAgentRunRequestBody",
"type": "object",
"required": [
"data"
],
"properties": {
"data": {
"allOf": [
{
"$ref": "#/$defs/StartAgentRunRequest"
}
],
"description": "The primary data of the document"
}
},
"$defs": {
"AgentArtifactPart": {
"type": "object",
"properties": {
"text": {
"type": "string",
"description": "Inline text content (text part)."
},
"file": {
"allOf": [
{
"$ref": "#/$defs/AgentFileContent"
}
],
"description": "File content by link or bytes (file part)."
},
"data": {
"description": "Structured content with no downloadable form, e.g. a created CRM record or a data agent's structured result (data part)."
},
"metadata": {
"type": "object",
"additionalProperties": {},
"description": "Producer-defined metadata for this part."
}
},
"description": "One part of an artifact. Exactly one of `text`, `file`, or `data` is set,\nwhich determines the part's kind; `metadata` may accompany any. The\nmultipart protocol (chunk concatenation, rendering) keys off which one is\nset."
},
"AgentFileContent": {
"type": "object",
"properties": {
"uri": {
"type": "string",
"format": "uri",
"description": "Link to downloadable content (e.g. a generated document)."
},
"bytes": {
"type": "string",
"description": "Base64-encoded binary content."
},
"name": {
"type": "string",
"description": "Display filename."
},
"mimeType": {
"type": "string",
"description": "MIME type of the file content."
}
},
"description": "File content: exactly one of `uri` (a link, e.g. the platform's\ntoken-gated document route) or `bytes` (base64). `name` is always present\non emitted files (the server falls back to the object type rather than\nemit a nameless file)."
},
"AgentRunMessage": {
"type": "object",
"required": [
"parts"
],
"properties": {
"parts": {
"type": "array",
"items": {
"$ref": "#/$defs/AgentArtifactPart"
},
"description": "The message's content parts. Each is exactly one of `text`, `file`, or `data`; at most one `data` part is allowed."
}
},
"description": "The caller's message to the agent -- the run's entire input, as an ordered\nlist of content parts (the same part shape artifacts use). There is no\n`role` (the sender is always the caller) and no message id (the run itself\nis the identity), so `parts` is the whole of it.\n\nParts by kind: `text` parts carry prose and are joined into the agent's\nprompt; a `data` part carries the structured argument object the agent's\n`inputSchema` data entry types; `file` parts are declared in the shape but not yet\naccepted. AT MOST ONE `data` part may be present -- parts have no names and\ntheir order carries no meaning, so a second anonymous payload would be\nstructure no schema can address; nest multiple structured payloads inside\nthe one data object instead."
},
"StartAgentRunAttributes": {
"type": "object",
"required": [
"message"
],
"properties": {
"message": {
"allOf": [
{
"$ref": "#/$defs/AgentRunMessage"
}
],
"description": "The run's input, as one message of content parts: `{ \"parts\": [ { \"text\": \"...\" }, { \"data\": { ... } } ] }`. Prose goes in `text` parts; the structured argument object (typed by the agent's `inputSchema` data entry) goes in a single `data` part. See AgentRunMessage for the rules."
},
"contextId": {
"type": "string",
"description": "Conversation to continue this run within, as a UUID; omit to start fresh. Platform agents resume that conversation thread. Teams agents are single-shot: a supplied contextId is accepted and ignored (each Teams run gets a fresh server-minted context regardless). A malformed value returns `400` with a pointer to `/data/attributes/contextId`."
},
"returnImmediately": {
"type": "boolean",
"description": "Whether the request returns immediately. Default `true` starts the run asynchronously and returns the in-progress run while execution continues in the background. Set `false` to keep the connection open while the agent executes, up to 300 seconds. If the run does not complete within that window, the response returns the in-progress run and execution continues in the background. Ignored by Start Agent Run (Stream), which always streams.",
"default": true
},
"taskId": {
"type": "string",
"description": "OPTIONAL, and omitted for almost every call. Omit it to START a new run\n(the default, and the only mode implemented today). Set it to an existing\nrun's id ONLY to CONTINUE that run when it is paused awaiting input\n(`TASK_STATE_INPUT_REQUIRED` / `TASK_STATE_AUTH_REQUIRED`): the message is\ndelivered as the answer and the run resumes. This is A2A's `Message.taskId`\n(the run id is the taskId).\n\nOnly agents whose `capabilities.interactive` is `true` accept a taskId;\nothers return `400`. An unknown run returns `404`; a terminal or\nnot-awaiting-input run returns `409`. No agent declares `interactive` yet,\nso continuation is not available in practice -- the field is specified for\nforward compatibility, not for use today."
}
},
"description": "Attributes for starting an agent run."
},
"StartAgentRunRequest": {
"type": "object",
"required": [
"type",
"attributes"
],
"properties": {
"type": {
"type": "string",
"description": "The type of the resource",
"default": "StartAgentRunRequest",
"pattern": "StartAgentRunRequest"
},
"attributes": {
"allOf": [
{
"$ref": "#/$defs/StartAgentRunAttributes"
}
],
"description": "The attributes defining the resource"
}
},
"description": "The run input as a JSON:API resource: `data.attributes` carries the message and optional contextId."
}
}
}
Work with this as data
Every JSON Schema here is available over the APIs.io API and to AI agents over MCP.
MCP server
One button, every client — Claude, Cursor, VS Code and the rest.
https://apis.io/mcp
Tools for schemas
4 MCP tools reach this
find_json_schemasBrowse and filter every JSON Schema in the catalog.apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.resolveTurn a domain, URL or GitHub org into the provider it belongs to.find_cohortsEvery scored population of providers in the catalog.
Call it yourself
curl for this page
curl "https://apis.io/api/v1/json-schemas/gtm-start-agent-run-request-body"
curl "https://apis.io/api/v1/json-schemas?limit=25"
Discovery needs no key. Ratings and market analysis are Pro.
Get an API key
Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.
A second provider on the same verified email joins the account you already have.