NVIDIA / NVIDIA/NeMo-Agent-Toolkit

Large response payloads cause UI freeze and increased rendering latency

Open
#1,645 2 comments 0 reactions 1 assignee View on GitHub

@ericevans-nv is already working on this.

Since Feb 24, 2026.

improvement Needs Triage
Dominant language
Python
Stars
2.6k
Forks
762
Avg merge
21h 28m
Merged PRs (30d)
27

Description

Is this a new feature, an improvement, or a change to existing functionality?

Improvement

How would you describe the priority of this feature request

Medium

Please provide a clear description of problem this feature solves

The nat-ui frontend freezes or crashes when the backend sends large intermediate step payloads. Each intermediate step is parsed, processed, and rendered synchronously by the browser, and at scale the UI becomes unresponsive or crashes entirely even though the backend has already completed the response. The latency the user experiences is directly proportional to the total intermediate step payload size. For example, a response totaling 17.4 MB takes upwards of 3-5 minutes to render in the UI often freezing or crashing the browser entirely despite the backend completing in under 90 seconds.

Describe your ideal solution

Reduce the intermediate step payload size through compression and data reduction techniques in the StepAdaptor. This could include referencing previously sent data instead of re-embedding it, deduplicating events that carry identical payloads, and capping oversized payloads at a configurable maximum. The goal is to bring the payload size down to be proportional to the actual unique content without losing information available to the frontend.

Additional context

No response

Code of Conduct
  • I agree to follow this project's Code of Conduct
  • I have searched the open feature requests and have found no duplicates for this feature request

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.