Unverified95% confidenceFactTime unknown
OpenClaw支持SubAgent机制，语言模型可以要求生成子Agent来处理子任务，但程序端禁止子Agent再使用繁殖工具以防止无限递归
1
Sources
95%
Confidence
Long-term
Relevance
6/3/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedOpenAI's function calling/tool use mechanism is a hard constraint; the model inference engine directly constrains the valid set of output tokens during the decoding phase, thereby guaranteeing format compliance at the protocol level.68% similarUnverified开放权重模型为开发者提供了本地部署、微调和审计模型行为的能力，这在纯闭源API模式下不可能65% similarUnverifiedRunning OpenCLI adapter commands does not consume LLM model tokens, but the process of having an Agent explore new websites and write new adapters still consumes model resources.64% similarUnverifiedOpenAI's Function Calling allows developers to set explicit invocation priorities and mutual exclusion rules for each function, whereas Claude's plugin ecosystem currently lacks a native conflict arbitration layer.64% similarUnverifiedOpenAI's Code Interpreter, Anthropic's Computer Use, and LangChain Tool Calling each achieve the goal of AI breaking through to execution channels in different ways.64% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/40383API
curl https://kongchang.com/api/v1/knowledge/claims/40383MCP
get_claim(id=40383)