Verified65% confidenceFactTime unknown
The OpenAI Agents SDK's Runner does not automatically save and maintain conversation history; each call to Runner.run() is independent.
3
Sources
65%
Confidence
Long-term
Relevance
5/31/2026
First Seen
Sources
OpenAI Agents SDK消息类型与对话历史管理实战指南
youtubeJames Briggs
Related Entities
Related Claims
Unverified在 OpenAI Agents SDK 中，Runner.run_sync 是同步调用方式，会立即返回响应，但无法在 Jupyter Notebook 中运行，因为 Notebook 自身已运行着事件循环，嵌套启动新循环会抛出 'This event loop is already running' 错误。70% similarUnverifiedOpenBot 当前版本直跑本机，开发模式没有身份验证，按单一管理员环境处理63% similarUnverifiedA Dry Run must be conducted before formal execution; the Dry Run only checks the plan and does not call the real business interface.61% similarUnverifiedOpenShell policy rules can be reloaded and take effect in real time without a restart.61% similarUnverifiedThe large model API itself does not store conversation history, and each call is independent, with the model able to see only the content explicitly passed in the current request.60% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/16170API
curl https://kongchang.com/api/v1/knowledge/claims/16170MCP
get_claim(id=16170)