<feed xmlns='http://www.w3.org/2005/Atom'>
<title>packages/AGENTS.md, branch master</title>
<subtitle>Mirror of packages feed</subtitle>
<id>https://git-03.infra.openwrt.org/feed/packages/atom?h=master</id>
<link rel='self' href='https://git-03.infra.openwrt.org/feed/packages/atom?h=master'/>
<link rel='alternate' type='text/html' href='https://git-03.infra.openwrt.org/feed/packages/'/>
<updated>2026-11-16T11:47:32Z</updated>
<entry>
<title>CONTRIBUTING: explain the AI policy in more detail</title>
<updated>2026-11-16T11:47:32Z</updated>
<author>
<name>Josef Schlehofer</name>
</author>
<published>2026-11-04T22:40:34Z</published>
<link rel='alternate' type='text/html' href='https://git-03.infra.openwrt.org/feed/packages/commit/?id=b72ddf2f67418600fdabfa05faa78c5c9d2da600'/>
<id>urn:sha1:b72ddf2f67418600fdabfa05faa78c5c9d2da600</id>
<content type='text'>
The AI policy in CONTRIBUTING.md is short on purpose, but its review
left open questions: how to disclose LLM use, whether a tool may add
Signed-off-by, how LLM-assisted changes are tested and how the
project's own review bot fits in.

Answer them in a new AI_POLICY.md, linked from the policy section, and
summarize the rules for coding agents in AGENTS.md. The short policy
also says that untested pull requests opened in bulk are closed, and
the PR template asks what the LLM was used for.

Two general rules are added as well. OpenWrt integration files such as
the init script and the UCI config live in files/ and are not installed
from the upstream archive, so that they are reviewed here and can be
fixed with a PKG_RELEASE bump. Explanations stay in proportion to the
change.

Signed-off-by: Josef Schlehofer &lt;pepe.schlehofer@gmail.com&gt;
</content>
</entry>
</feed>
