Agent4.io · Schema
AgentIn
Artificial IntelligenceAutomationCustomer EngagementSoftware-as-a-ServiceAgent Platform
Properties
| Name | Type | Description |
|---|---|---|
| soul | string | |
| task | string | |
| tools | array | |
| skills | array | |
| knowledge_bases | array | |
| history_window | object | |
| max_output_tokens | object | |
| tool_call_max_tokens | object | 发起工具调用那一轮的输出预算(token)。工具的入参也算模型输出,而导出文档的入参就是整份文档,所以这个值决定了智能体一次能写多长的文档。 调大:面对大上下文的复杂问题,智能体能把话讲透、文档写全;代价是这类回合更慢(约 160 token/秒,写满 16K 约需 100 秒),且会更快消耗月度 token 配额。 调小:更快更省,但复杂问题会被迫简答。低于下限的值会被抬回下限——设得过小不会让 |
| model | object | |
| published | boolean | |
| greeting | object | |
| auto_greeting | boolean | |
| auto_suggest | boolean | |
| suggest_prompt | object | |
| ask_forms | boolean | |
| proactive_cta | boolean | |
| cta_prompt | object | |
| no_match_reply | object | |
| reasoning | boolean | |
| grounding_required | boolean | |
| injection_guard | boolean | |
| public_sources | boolean | |
| ambiguity_check | boolean | |
| deep_research | boolean | |
| on_demand_context | boolean | |
| guard_escalation | boolean | |
| menu_items | object |
JSON Schema
{
"$schema": "https://json-schema.org/draft/2020-12/schema",
"$id": "https://artifacts.apis.io/agent4-io/json-schema/agent4-io-agent-in-schema.json",
"title": "AgentIn",
"x-generated": "2026-11-01",
"x-method": "derived",
"x-generator": "derive-json-schema.py",
"x-source": "openapi/_original/agent4-io-api-openapi.json#/components/schemas/AgentIn",
"properties": {
"soul": {
"type": "string",
"title": "Soul",
"default": ""
},
"task": {
"type": "string",
"title": "Task",
"default": ""
},
"tools": {
"items": {
"type": "string"
},
"type": "array",
"title": "Tools",
"default": []
},
"skills": {
"items": {
"type": "string"
},
"type": "array",
"title": "Skills",
"default": []
},
"knowledge_bases": {
"items": {
"type": "string"
},
"type": "array",
"title": "Knowledge Bases",
"default": []
},
"history_window": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "History Window"
},
"max_output_tokens": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Output Tokens"
},
"tool_call_max_tokens": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Tool Call Max Tokens",
"description": "发起工具调用那一轮的输出预算(token)。工具的入参也算模型输出,而导出文档的入参就是整份文档,所以这个值决定了智能体一次能写多长的文档。\n\n调大:面对大上下文的复杂问题,智能体能把话讲透、文档写全;代价是这类回合更慢(约 160 token/秒,写满 16K 约需 100 秒),且会更快消耗月度 token 配额。\n\n调小:更快更省,但复杂问题会被迫简答。低于下限的值会被抬回下限——设得过小不会让文档变短,而是让参数 JSON 被截断、整个导出失败。\n\n留空使用平台默认值。"
},
"model": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Model"
},
"published": {
"type": "boolean",
"title": "Published",
"default": false
},
"greeting": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Greeting"
},
"auto_greeting": {
"type": "boolean",
"title": "Auto Greeting",
"default": false
},
"auto_suggest": {
"type": "boolean",
"title": "Auto Suggest",
"default": false
},
"suggest_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Suggest Prompt"
},
"ask_forms": {
"type": "boolean",
"title": "Ask Forms",
"default": true
},
"proactive_cta": {
"type": "boolean",
"title": "Proactive Cta",
"default": false
},
"cta_prompt": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Cta Prompt"
},
"no_match_reply": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "No Match Reply"
},
"reasoning": {
"type": "boolean",
"title": "Reasoning",
"default": false
},
"grounding_required": {
"type": "boolean",
"title": "Grounding Required",
"default": false
},
"injection_guard": {
"type": "boolean",
"title": "Injection Guard",
"default": true
},
"public_sources": {
"type": "boolean",
"title": "Public Sources",
"default": false
},
"ambiguity_check": {
"type": "boolean",
"title": "Ambiguity Check",
"default": false
},
"deep_research": {
"type": "boolean",
"title": "Deep Research",
"default": false
},
"on_demand_context": {
"type": "boolean",
"title": "On Demand Context",
"default": false
},
"guard_escalation": {
"type": "boolean",
"title": "Guard Escalation",
"default": false
},
"menu_items": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"title": "Menu Items"
}
},
"type": "object"
}
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/agent4-io-agent-in"
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.