注意边界：通过跨项目和账户的云运行枢纽稳定Gemini Enterprise A2A
Mind the Boundary: Stabilizing Gemini Enterprise A2A via a Cloud Run Hub Across Projects and Accounts
AI总结：
通过跨项目和账户的云运行枢纽稳定Gemini Enterprise A2A，解决边界依赖认证和UI兼容性问题，实现可靠路由和稳定响应。
摘要：
企业对话用户界面日益需要在项目和账户边界内以安全且可重复的方式协调异构后端代理和工具。从Gemini Enterprise代理到代理（A2A）调用开始，我们实现了一个A2A枢纽调度器，该调度器在Cloud Run上路由查询到四条路径：一个部署在不同项目中的公共A2A代理、一个受IAM保护的Cloud Run A2A代理，一个结合Discovery Engine和Vertex AI Search并直接从Google Cloud Storage检索源文本的检索增强生成路径，以及一个通过Vertex AI进行一般问题回答的路径。我们表明，实际的互操作性不仅由协议符合性决定，还由Gemini Enterprise UI约束和边界依赖的认证决定。真实的UI请求以纯文本输入形式出现，并包含空的接受输出模式列表，因此在JSON-RPC响应中混合结构化数据可能触发UI错误。为了解决这个问题，我们强制在JSON-RPC端点上使用纯文本兼容模式，同时将结构化输出和调试信号分离到REST工具API中。在涵盖费用政策、项目管理协助、一般知识和事件响应截止期限提取的四条查询基准测试中，我们确认了确定性的路由和稳定的UI响应。对于检索路径，授予存储对象读取权限可以启用基于证据的十五分钟截止期限提取。所有实验均使用标记为a2a-hub-gemini-ui-stable-paper的仓库快照进行可重复性测试。
英文摘要：
Enterprise conversational UIs increasingly need to orchestrate heterogeneous backend agents and tools across project and account boundaries in a secure and reproducible way. Starting from Gemini Enterprise Agent-to-Agent (A2A) invocation, we implement an A2A Hub orchestrator on Cloud Run that routes queries to four paths: a public A2A agent deployed in a different project, an IAM-protected Cloud Run A2A agent in a different account, a retrieval-augmented generation path combining Discovery Engine and Vertex AI Search with direct retrieval of source text from Google Cloud Storage, and a general question answering path via Vertex AI. We show that practical interoperability is governed not only by protocol compliance but also by Gemini Enterprise UI constraints and boundary-dependent authentication. Real UI requests arrive as text-only inputs and include empty accepted output mode lists, so mixing structured data into JSON-RPC responses can trigger UI errors. To address this, we enforce a text-only compatibility mode on the JSON-RPC endpoint while separating structured outputs and debugging signals into a REST tool API. On a four-query benchmark spanning expense policy, project management assistance, general knowledge, and incident response deadline extraction, we confirm deterministic routing and stable UI responses. For the retrieval path, granting storage object read permissions enables evidence-backed extraction of the fifteen minute deadline. All experiments are reproducible using the repository snapshot tagged a2a-hub-gemini-ui-stable-paper.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
