OpenHands / OpenHands/extensions

Show LLM provenance in PR-review and Slack automation output

Open
#548 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement ready-for-dev
Dominant language
Python
Stars
148
Forks
90
Avg merge
1d 17h
Merged PRs (30d)
36

Description

Problem or Use Case

The GitHub PR-reviewer and Slack channel-monitor automations publish LLM-dependent judgments without identifying the LLM profile and model that generated them. The original report is OpenHands/automation#430, but these output implementations are owned by this repository.

Desired Behavior

Published PR reviews and Slack automation responses should include the LLM profile and concrete model used for the underlying conversation, using the same concise wording.

Acceptance Criteria
  • GitHub PR-review automation output displays its LLM profile and model.
  • Slack channel-monitor output displays its LLM profile and model.
  • Both automations use consistent, concise wording.
  • The displayed profile and model match the concrete agent settings used by the spawned conversation.
Additional Context

This same-repository tracking issue allows the Extensions PR readiness check to validate ownership and readiness while retaining the original cross-repository report as context.

This issue was created by an AI agent (OpenHands) on behalf of the user.

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 locating the GitHub PR-review and Slack channel-monitor automation implementations and tracing how each spawned conversation receives its agent settings. Compare both output paths and verify how the concrete LLM profile and model are available. Done means both outputs show the matching profile and model with consistent concise wording, with the relevant checks passing.

Written by the indexing model from the issue text.

Assessment

Tech stack
github, python
Domain
devops
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Active
Clarity
Mostly clear
Newbie friendliness
55/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.