返回全部动态
OpenAI Agents JS SDK v0.17.0 发布：强化输出护栏安全与配置校验
原标题：v0.17.0
AI 摘要
OpenAI 发布了 Agents JavaScript SDK 的 v0.17.0 版本，主要引入了输出护栏重放安全机制，防止序列化检查点被不当重放，并在输出护栏拒绝结果时替换为占位文本。同时，该版本完善了护栏批处理结果的处理，并明确要求 OpenAI 客户端配置需在构造客户端时完成，否则会报错。
以上摘要由 AI 生成，可能存在误差。事实请以原文为准。
正文节选
## Key Changes ### Output-guardrail replay safety Serialized output-bearing approval checkpoints now fail closed with `UserError` when the SDK cannot prove which response owns a pending terminal tool output. Continue with the live `RunState` when possible, or start a new run from safe input instead of replaying ambiguous serialized items. When an output guardrail rejects a completed function-tool result used as final output, the SDK replaces rejected content in SDK-owned replay surfaces wi
发布时间：2026-08-19 22:37
抓取时间：2026-08-19 22:40
来源机构：OpenAI