chaitin / chaitin/MonkeyCode

UX Feedback: Agent task completion status & missing handover communication

Open
#970 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
TypeScript
Stars
4.7k
Forks
719
Avg merge
4h 30m
Merged PRs (30d)
83

Description

Hi Monkeycode Team,

As a PRO subscriber, i'd like to share some important UX feedback regarding how the agent communicates task completion in the chat.

Currently, when I send a request, I can see the agent's internal "Thought" logs while it works, but once it finishes, it simply stops without communicating whether the task is complete or if the code is ready to be pulled.

The main issue:
VERY OFTEN, I am left in the dark and forced to manually prompt the agent:

"Are you still there? Where are we at? Can I test it now?"

Only after I send this message does the agent wake up and reply with something like: "Yes, I implemented the feature, I'm committing now, you can do a git pull..."

Why this is frustrating:
The agent should not rely on me poking it to let me know it's done. I shouldn't have to guess if it's stuck, still thinking, or finished.

What we need:
Automatic Completion Response: As soon as the agent finishes its work (e.g., after the git push), it MUST automatically send a final response like:
"Task complete! I have implemented X and pushed the changes to branch Y. You can now do a git pull / checkout and test it."
Clear UI Status: A visual indicator showing explicitly whether the agent is Working or Finished / Waiting for user input.

This simple change would eliminate a lot of friction and dramatically improve the developer experience.
Thanks for your hard work on the platform!

Best regards,

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

No files or tests are named. Start by tracing the agent task-completion flow and the chat status UI; done means the agent sends a final completion and handover message automatically, while the interface clearly shows whether it is working, finished, or waiting for input.

Written by the indexing model from the issue text.

Assessment

Tech stack
typescript
Domain
developer-experience, frontend
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.