OpenFn / OpenFn/lightning

AI assistant: Streaming is artificially delayed

Open
#5,085 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

AI
Dominant language
Elixir
Stars
296
Forks
86
Avg merge
1d 13h
Merged PRs (30d)
50

Description

Our streaming visualisation can take too much time. A couple of issues here:

  • It can be too slow for long answers. You have to wait when you just want to get the message asap, and it has already been generated in the backend.
  • If you navigate away from the tab, and come back after a while, the streaming animation only starts when you open the tab, even though the answer was received several minutes earlier. This may also limit AI-based testing.
  • The message box is greyed out while streaming, so you can start writing your next message.

Contributor guide

No contributing guide indexed for this repository

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.

Research direction

Start by tracing the AI assistant's streaming visualisation and message-box state. Verify that already-received answers display without artificial delay, remain available after navigating away and back, and leave the message box usable while streaming; add or update coverage for these behaviours if the relevant tests are found.

Written by the indexing model from the issue text.

Assessment

Tech stack
elixir
Domain
ai, frontend
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.