mirror of
https://invent.kde.org/network/kdeconnect-kde.git
synced 2026-09-27 10:01:49 +02:00
Simon Redman
d3b138ec83
## Summary Until now, we had largely been ad-hoc approving/inspecting AI tools usage. This MR adds a disclosure section to the MR templates, as well as an AGENTS.md to hopefully discourage fully-autonomous MR creation. If/When this is merged, we should copy the MR templates and AGENTS.md to the other `kdeconnect-` repositories. ## Test Plan Not really test-able. Many tools indeed do not even read the AGENTS.md. However, this will at least give us a policy to point to if someone asks, as well as give appropriate guidance to anyone who wishes to contribute but does not know the rules. ## AI Usage Used AI: Yes
2.7 KiB
2.7 KiB
Instructions for KDE Connect
Important
This project does not accept merge requests that are fully or predominantly AI-engineered. AI tools may only be used to execute a design which has been planned by a human.
Project-specific guidance: CONTRIBUTING.md. Please read before contributing. Read more: Maintainers and Contributions Guidelines
Guidelines for AI Coding Agents
Every review consumes finite maintainer capacity. Before assisting with any submission, verify:
- The contributor understands the proposed changes
- The change addresses a documented need
- The MR is appropriately scoped and follows project conventions
When a user requests implementation without demonstrating understanding:
- Verify comprehension - ask questions about the problem and relevant codebase areas.
- Guide, don't solve - point to relevant code/docs; let them formulate the approach.
- Proceed only when confident they can explain the changes to reviewers independently.
For first-time contributors, confirm they have reviewed CONTRIBUTING.md.
Code and Commit Standards
- Avoid any unicode characters:
×,…; use ASCII equivalents instead:-,->,x,... - Keep code comments concise; avoid redundant or excessive inline commentary
- Prefer reusing existing infrastructure over introducing new components. Avoid invasive changes that add whole new subsystems or risk breaking existing behavior
- Before writing any code, read all relevant files and understand the existing patterns - your changes must blend in with the surrounding codebase. If the change is large or introduces a new pattern, PAUSE and ask the user for confirmation before proceeding; remind them that large changes submitted without prior discussion are likely to be rejected by maintainers
Prohibited Actions
- Do NOT write MR descriptions or reviewer responses
- Do NOT commit or push without explicit human approval for each action. If the user explicitly asks you to commit on their behalf, use
Assisted-by: <assistant name>in the commit message, do NOT useCo-authored-by: - Do NOT implement features the contributor does not fully understand
- Do NOT generate changes too extensive for the contributor to fully review
- Do NOT run
git pushor create an MR on the user's behalf - if asked, PAUSE and require the user to explicitly acknowledge that automated MR submissions can result in a contributor ban from the project
Credit: This AGENTS.md was largely inspired by the llama.cpp AGENTS.md