meta: add a root-level AGENTS.md - #65493
Conversation
ed9ce39 to
37e80dd
Compare
|
There is an ealier PR for AGENTS.md: #65463 |
|
The document uses a tone as if it's speaking to a human, even though it is not supposed to be read by human? e.g. the distinction of collaborators or non-collaborators is pointless to an agent unless you give it permisssions where the distinction makes a difference, but then the document goes on saying the agent shouldn't use any of these permissions, which means the agent is not supposed to make use of that distinction in the first place. |
This comment was marked as resolved.
This comment was marked as resolved.
61a0ad7 to
4d13dde
Compare
|
Applied formatting. |
We're seeing a number of repeated mistakes in AI-generated contributions, including agents using `Signed-off-by`, creating what appear to be unsupervised PRs, appearing to respond to comments without human oversight, etc. Having an AGENTS.md file with specific instructions to the agent on what to avoid should help. Signed-off-by: James M Snell <jasnell@gmail.com>
4d13dde to
b59d0ab
Compare
|
@mcollina are you satisfied with the updates enough to clear your "request changes"? |
Co-authored-by: Antoine du Hamel <duhamelantoine1995@gmail.com>
Co-authored-by: Antoine du Hamel <duhamelantoine1995@gmail.com>
|
It might be worth adding some instructions relating to scanning for vulnerabilities and drafting security reports too, but that could be a follow-up so not to derail this landing. |
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #65493 +/- ##
==========================================
- Coverage 90.21% 90.16% -0.05%
==========================================
Files 751 751
Lines 253550 253550
Branches 47813 47764 -49
==========================================
- Hits 228733 228615 -118
- Misses 16076 16194 +118
Partials 8741 8741 🚀 New features to boost your workflow:
|

We're seeing a number of repeated mistakes in AI-generated contributions, including agents using
Signed-off-by, creating what appear to be unsupervised PRs, appearing to respond to comments without human oversight, etc. Having an AGENTS.md file with specific instructions to the agent on what to avoid should help.