Mind the Boundary: Stabilizing Gemini Enterprise A2A via a Cloud Run Hub Across Projects and Accounts
Takao Morita

TL;DR
This paper presents a Cloud Run-based A2A Hub for Gemini Enterprise, enabling secure, cross-project, and cross-account orchestration of heterogeneous backend agents with improved UI stability and reproducibility.
Contribution
It introduces a Cloud Run orchestrator for Gemini Enterprise A2A that handles multi-path routing, enforces UI-compatible protocols, and ensures stable, reproducible interactions across complex cloud boundaries.
Findings
Successful multi-path routing in enterprise A2A interactions
Enforcement of text-only mode improves UI stability
Reproducible experiments on real-world enterprise queries
Abstract
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,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Business Process Modeling and Analysis · Scientific Computing and Data Management
