agents

Update Agent

put/agents/{name}

Request

Base URL: https://api.agent4.io (the document declares no server; this is the origin it was published from)
URL: https://api.agent4.io/agents/{name}
Auth: none declared

Path parameters

namestring required

Request body

soulstring

taskstring

toolsstring[]

skillsstring[]

knowledge_basesstring[]

history_windowinteger nullable

max_output_tokensinteger nullable

tool_call_max_tokensinteger nullable

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——设得过小不会让文档变短，而是让参数 JSON 被截断、整个导出失败。

留空使用平台默认值。

modelstring nullable

publishedboolean

greetingstring nullable

auto_greetingboolean

auto_suggestboolean

suggest_promptstring nullable

ask_formsboolean

proactive_ctaboolean

cta_promptstring nullable

no_match_replystring nullable

reasoningboolean

grounding_requiredboolean

injection_guardboolean

public_sourcesboolean

ambiguity_checkboolean

deep_researchboolean

on_demand_contextboolean

guard_escalationboolean

menu_itemsstring[] nullable

Response

Successful Response