<feed xmlns='http://www.w3.org/2005/Atom'>
<title>staging/stintel/.github/llm-review-rules.md, branch master</title>
<subtitle>Staging tree of Stijn Tintel</subtitle>
<id>https://git.openwrt.org/openwrt/staging/stintel/atom?h=master</id>
<link rel='self' href='https://git.openwrt.org/openwrt/staging/stintel/atom?h=master'/>
<link rel='alternate' type='text/html' href='https://git.openwrt.org/openwrt/staging/stintel/'/>
<updated>2026-05-01T18:12:18Z</updated>
<entry>
<title>github: extend LLM review rules with three new categories</title>
<updated>2026-05-01T18:12:18Z</updated>
<author>
<name>Hauke Mehrtens</name>
</author>
<published>2026-05-01T16:02:22Z</published>
<link rel='alternate' type='text/html' href='https://git.openwrt.org/openwrt/staging/stintel/commit/?id=0bef7411885e9f6e4d4f4224ec4a94565396010f'/>
<id>urn:sha1:0bef7411885e9f6e4d4f4224ec4a94565396010f</id>
<content type='text'>
Tightened from real bot reviews:

- Patch regeneration: spell out which make ... refresh command
  to recommend for each patch directory class, so the bot stops
  suggesting git format-patch for quilt-managed patches.
- Backports / cherry-picks: a backport's diff should match the
  upstream commit on main verbatim; flag only deviations and
  the missing (cherry picked from commit &lt;sha&gt;) trailer, not
  pre-existing style issues.
- New device support: require Hardware specification, Flash
  instructions, and MAC address layout sections in the commit
  message that introduces a new device. Two reference commits
  (986ca4c887f4, a2dcbd79a446) named so the bot can sample the
  expected shape.

Co-Authored-By: Claude Opus 4.7 (1M context) &lt;noreply@anthropic.com&gt;
Link: https://github.com/openwrt/openwrt/pull/23184
Signed-off-by: Hauke Mehrtens &lt;hauke@hauke-m.de&gt;
</content>
</entry>
<entry>
<title>github: add LLM PR review wrapper and rules</title>
<updated>2026-05-01T15:14:58Z</updated>
<author>
<name>Hauke Mehrtens</name>
</author>
<published>2026-04-26T14:37:12Z</published>
<link rel='alternate' type='text/html' href='https://git.openwrt.org/openwrt/staging/stintel/commit/?id=af3cbd4013a2c8c82450e4a4b21a73d28ab4cda2'/>
<id>urn:sha1:af3cbd4013a2c8c82450e4a4b21a73d28ab4cda2</id>
<content type='text'>
Drop-in wrapper that calls the reusable LLM review workflows in
openwrt/actions-shared-workflows. Triggers on pull_request_target
(incl. PRs from forks), a nightly cron (03:00 UTC), and manual
workflow_dispatch with a max_prs input override.

A detect-kernels pre-step builds the extra_repos list at workflow
runtime: it reads target/linux/generic/kernel-* in the base branch
to derive gregkh/linux:v&lt;X.Y.Z&gt; tags for each currently-targeted
kernel, then appends u-boot/u-boot:master. The list updates
automatically when kernel versions are bumped; the routine clones
only the entries actually needed for a given diff.

The bundled .github/llm-review-rules.md teaches the bot two
project-specific deprecations to flag even when other in-tree files
still use the legacy form:

  - LED label syntax `label = "&lt;color&gt;:&lt;function&gt;";` --&gt;
    `color = &lt;LED_COLOR_ID_*&gt;;` + `function = "&lt;func&gt;";`
  - `mediatek,mtd-eeprom` for MAC sourcing --&gt;
    `nvmem-cells` + `nvmem-cell-names = "mac-address";`

Repository settings need LLM_ROUTINE_ID_PR / LLM_ROUTINE_TOKEN_PR
and the *_NIGHTLY counterparts populated before the workflow can
fire. See openwrt/actions-shared-workflows/docs/llm-review-setup.md
for the full setup procedure.

Co-Authored-By: Claude Opus 4.7 &lt;noreply@anthropic.com&gt;
Link: https://github.com/openwrt/openwrt/pull/23105
Signed-off-by: Hauke Mehrtens &lt;hauke@hauke-m.de&gt;
</content>
</entry>
</feed>
