Lexifina · Schema
AgentRunRequest
Legal AIDocument AutomationContract DraftingCollaboration ToolsEnterprise Security
Properties
| Name | Type | Description |
|---|---|---|
| document_id | object | The document the agent works on. Omit it for a conversation of its own: the agent answers, and creates or changes documents only through its tools. Continuing a conversation without document_id uses i |
| session_id | object | Continue this session's conversation. Omit to start a new session; API runs never select a browser session. |
| matter_ids | object | Matters a new conversation without a document is linked to, so the agent works within them. Only when starting one: omit session_id and document_id. |
| prompt_text | string | What the agent is to do, as the user would ask it. |
| source_prompt_text | object | Where the instruction came from, when it differs from prompt_text, for the record. |
| change_application_mode | string | manual stages the agent's changes for a person to accept; automatic applies them when the run finishes, where the organisation allows it. |
| document_version | object | Start only if the document is still at this version. |
| document_content_revision | object | Start only if the document's content is still at this revision. |
| document_content_hash | object | Start only if the document's content still has this hash. |
| attachments | object | Other documents the agent may read, such as a playbook or precedent. Access is checked for each. |
| folder_ids | object | Folders the agent may search. |
| reasoning_effort | object | How much the model reasons before answering: low, medium or high. |
| page_context | object | A page the user has open, sent with this message as context, such as the page beside a browser extension's panel. |
| mode | string | plan: the agent asks any questions, then returns a plan (result.plan) without changing the document. To carry it out, start a default-mode run with the prompt "Implement the plan." |
| skill | object | Run a skill: the firm's standard instructions for a task. |
| output_schema | object | A JSON Schema (type object). The run result then carries output: JSON matching it. |
| external_id | object | Your system's identifier for this run. |
| metadata | object | Up to 16 key-value pairs for your own use. |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/lexifina/json-schema/lexifina-agent-run-request-schema.json",
"title": "AgentRunRequest",
"x-generated": "2026-11-11",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/lexifina-openapi.json#/components/schemas/AgentRunRequest",
"properties": {
"document_id": {
"anyOf": [
{
"type": "string",
"maxLength": 200,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Document Id",
"description": "The document the agent works on. Omit it for a conversation of its own: the agent answers, and creates or changes documents only through its tools. Continuing a conversation without document_id uses its linked document, if it has one."
},
"session_id": {
"anyOf": [
{
"type": "string",
"maxLength": 128,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Session Id",
"description": "Continue this session's conversation. Omit to start a new session; API runs never select a browser session."
},
"matter_ids": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array",
"maxItems": 20
},
{
"type": "null"
}
],
"title": "Matter Ids",
"description": "Matters a new conversation without a document is linked to, so the agent works within them. Only when starting one: omit session_id and document_id."
},
"prompt_text": {
"type": "string",
"maxLength": 100000,
"minLength": 1,
"title": "Prompt Text",
"description": "What the agent is to do, as the user would ask it."
},
"source_prompt_text": {
"anyOf": [
{
"type": "string",
"maxLength": 100000,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Source Prompt Text",
"description": "Where the instruction came from, when it differs from prompt_text, for the record."
},
"change_application_mode": {
"type": "string",
"enum": [
"manual",
"automatic"
],
"title": "Change Application Mode",
"default": "manual",
"description": "manual stages the agent's changes for a person to accept; automatic applies them when the run finishes, where the organisation allows it."
},
"document_version": {
"anyOf": [
{
"type": "integer",
"minimum": 1.0
},
{
"type": "null"
}
],
"title": "Document Version",
"description": "Start only if the document is still at this version."
},
"document_content_revision": {
"anyOf": [
{
"type": "integer",
"minimum": 0.0
},
{
"type": "null"
}
],
"title": "Document Content Revision",
"description": "Start only if the document's content is still at this revision."
},
"document_content_hash": {
"anyOf": [
{
"type": "string",
"maxLength": 128,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Document Content Hash",
"description": "Start only if the document's content still has this hash."
},
"attachments": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/AttachmentRef"
},
"type": "array",
"maxItems": 20
},
{
"type": "null"
}
],
"title": "Attachments",
"description": "Other documents the agent may read, such as a playbook or precedent. Access is checked for each."
},
"folder_ids": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array",
"maxItems": 5
},
{
"type": "null"
}
],
"title": "Folder Ids",
"description": "Folders the agent may search."
},
"reasoning_effort": {
"anyOf": [
{
"type": "string",
"enum": [
"low",
"medium",
"high"
]
},
{
"type": "null"
}
],
"title": "Reasoning Effort",
"description": "How much the model reasons before answering: low, medium or high."
},
"page_context": {
"anyOf": [
{
"$ref": "#/$defs/PageContext"
},
{
"type": "null"
}
],
"description": "A page the user has open, sent with this message as context, such as the page beside a browser extension's panel."
},
"mode": {
"type": "string",
"enum": [
"default",
"plan"
],
"title": "Mode",
"description": "plan: the agent asks any questions, then returns a plan (result.plan) without changing the document. To carry it out, start a default-mode run with the prompt \"Implement the plan.\"",
"default": "default"
},
"skill": {
"anyOf": [
{
"$ref": "#/$defs/SkillRef"
},
{
"type": "null"
}
],
"description": "Run a skill: the firm's standard instructions for a task."
},
"output_schema": {
"anyOf": [
{
"additionalProperties": true,
"type": "object"
},
{
"type": "null"
}
],
"title": "Output Schema",
"description": "A JSON Schema (type object). The run result then carries output: JSON matching it."
},
"external_id": {
"anyOf": [
{
"type": "string",
"maxLength": 128,
"minLength": 1
},
{
"type": "null"
}
],
"title": "External Id",
"description": "Your system's identifier for this run."
},
"metadata": {
"anyOf": [
{
"additionalProperties": {
"type": "string"
},
"type": "object"
},
{
"type": "null"
}
],
"title": "Metadata",
"description": "Up to 16 key-value pairs for your own use."
}
},
"additionalProperties": false,
"type": "object",
"required": [
"prompt_text"
],
"$defs": {
"AttachmentRef": {
"properties": {
"document_id": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"title": "Document Id"
}
},
"additionalProperties": false,
"type": "object",
"required": [
"document_id"
],
"title": "AttachmentRef"
},
"PageContext": {
"properties": {
"url": {
"type": "string",
"maxLength": 2000,
"minLength": 1,
"pattern": "^https?://",
"title": "Url",
"description": "The page's address."
},
"title": {
"anyOf": [
{
"type": "string",
"maxLength": 300
},
{
"type": "null"
}
],
"title": "Title"
},
"kind": {
"type": "string",
"enum": [
"page",
"email",
"pdf"
],
"title": "Kind",
"description": "pdf: only the title and address are sent; attach the file for its text.",
"default": "page"
},
"text": {
"anyOf": [
{
"type": "string",
"maxLength": 40000
},
{
"type": "null"
}
],
"title": "Text",
"description": "The page's readable text."
},
"truncated": {
"type": "boolean",
"title": "Truncated",
"description": "True when the text was cut short before it was sent.",
"default": false
}
},
"additionalProperties": false,
"type": "object",
"required": [
"url"
],
"title": "PageContext",
"description": "A page the user has open, sent with the message as context: the agent reads it, and treats it as\nweb content rather than instructions. It is not shown as part of the user's message."
},
"SkillRef": {
"properties": {
"id": {
"type": "string",
"maxLength": 200,
"minLength": 1,
"title": "Id"
},
"version": {
"anyOf": [
{
"type": "string",
"maxLength": 64,
"minLength": 1
},
{
"type": "null"
}
],
"title": "Version",
"description": "Run only if the skill still has this version; otherwise 409."
},
"variables": {
"additionalProperties": {
"type": "string"
},
"type": "object",
"title": "Variables",
"description": "Values for the skill's declared arguments."
}
},
"additionalProperties": false,
"type": "object",
"required": [
"id"
],
"title": "SkillRef"
}
}
}
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
This JSON Schema
curl "https://apis.io/api/v1/json-schemas/lexifina-agent-run-request"
All schemas
curl "https://apis.io/api/v1/json-schemas?limit=25"
Calls without X-API-Key need no key. Calls with it need a paid plan — get a key.
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.