coding-assistants: simplify attribution
Subsystems (3)
Jonathan Corbet
maintainerPATCH 1/1 coding-assistants: simplify attribution
As suggested by Christian, I have applied his patch to a branch and simplified the changelog, see below.
I'm nervous about applying it still because I don't think it's my role to set this sort of policy; I really want to feel that there is a consensus behind it. So there's some additional CCs here because I would like to hear from some folks:
- This policy document originally came out of the TAB; is the TAB (on CC) OK with this change?
- At least one maintainer (on CC) have said that they currently strip Assisted-by tags out of patches before applying them, a practice that would seem to undermine the whole policy. Would this change be sufficient to end that practice?
Thanks,
jon
From c31aa376a355e3b84b9e87ae1dbe19b394d4c82c Mon Sep 17 00:00:00 2001
From: Christian Brauner <[email protected]>
Date: Wed, 1 Jul 2026 17:54:48 +0200
Subject: [PATCH] coding-assistants: simplify attribution
The requirement to identify specific models used in the Assisted-by tag provides free advertising to proprietary software companies while adding little or no useful information. Change the requirement to simply:
to capture the fact that an LLM was used without tracking which one.
Message-ID: <[email protected]>
--- Documentation/process/coding-assistants.rst | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)
Documentation/process/coding-assistants.rst +2 -6
@@ -43,12 +43,8 @@ When AI tools contribute to kernel development, proper attribution helps track the evolving role of AI in the development process. Contributions should include an Assisted-by tag in the following format:: - Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2] + Assisted-by: LLM [TOOL1] [TOOL2] -Where: - -* ``AGENT_NAME`` is the name of the AI tool or framework -* ``MODEL_VERSION`` is the specific model version used * ``[TOOL1] [TOOL2]`` are optional specialized analysis tools used (e.g., coccinelle, sparse, smatch, clang-tidy)
@@ -56,4 +52,4 @@ Basic development tools (git, gcc, make, editors) should not be listed. Example:: - Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparse
Signature · 1 line
2.55.0
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 2 lines · Jonathan Corbet
Documentation/process/coding-assistants.rst +1
-1- Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparse
I've been playing with this a bit, and it's pretty easy to teach the agent to add a few tag-like notes as to how exactly it was used, e.g.:
https://git.kernel.org/pub/scm/utils/b4/b4.git/commit/?id=018b87444d32eb2ffee7cb25f0785e54aa35f7bf
This has:
| Assisted-by: LLM [design, codegen, tests]
It tells us a bit more about *how* the LLM was used, without introducing the advertisement or pinning exact models.
This format should allow for multiple tool usage:
| Assisted-by: LLM [triage, tests], coccinelle
I don't suggest this is included in this version, but it *is* fairly straightforward to add to AGENTS.md and tells reviewers just how exactly the LLM was used.
-K
Mauro Carvalho Chehab
Reviewed-byQuoted 16 lines · On Wed, 22 Jul 2026 16:48:03 -0400 Konstantin Ryabitsev <[email protected]>…
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 2 lines · Jonathan Corbet
Documentation/process/coding-assistants.rst +1
-1- Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparseI've been playing with this a bit, and it's pretty easy to teach the agent to add a few tag-like notes as to how exactly it was used, e.g.:
https://git.kernel.org/pub/scm/utils/b4/b4.git/commit/?id=018b87444d32eb2ffee7cb25f0785e54aa35f7bfThis has:
| Assisted-by: LLM [design, codegen, tests]
It tells us a bit more about *how* the LLM was used, without introducing the advertisement or pinning exact models.
Quoted 7 lines
This format should allow for multiple tool usage:
| Assisted-by: LLM [triage, tests], coccinelle
I don't suggest this is included in this version, but it *is* fairly straightforward to add to AGENTS.md and tells reviewers just how exactly the LLM was used.
I'm fine with either way.
Regards,
Mauro
Quoted 16 lines · Konstantin Ryabitsev
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 2 lines · Jonathan Corbet
Documentation/process/coding-assistants.rst +1
-1- Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparseI've been playing with this a bit, and it's pretty easy to teach the agent to add a few tag-like notes as to how exactly it was used, e.g.:
https://git.kernel.org/pub/scm/utils/b4/b4.git/commit/?id=018b87444d32eb2ffee7cb25f0785e54aa35f7bfThis has:
| Assisted-by: LLM [design, codegen, tests]
It tells us a bit more about *how* the LLM was used, without introducing the advertisement or pinning exact models.
Quoted 7 lines
This format should allow for multiple tool usage:
| Assisted-by: LLM [triage, tests], coccinelle
I don't suggest this is included in this version, but it *is* fairly straightforward to add to AGENTS.md and tells reviewers just how exactly the LLM was used.
I think perhaps this should be a follow-up (this stuff is so fraught that I am super-glad to see Christian's suggestion fly through and want to take gains iteratively on this :), but completely agree.
David suggested something like:
So I think we're kinda aligned on that?
Probably worth keeping the 'what it did' bit fuzzy.
Quoted 2 lines
-K
--
Cheers, Lorenzo
Quoted 29 lines · Lorenzo Stoakes (ARM)
Quoted 16 lines · Konstantin Ryabitsev
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 2 lines · Jonathan Corbet
Documentation/process/coding-assistants.rst +1
-1- Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparseI've been playing with this a bit, and it's pretty easy to teach the agent to add a few tag-like notes as to how exactly it was used, e.g.:
https://git.kernel.org/pub/scm/utils/b4/b4.git/commit/?id=018b87444d32eb2ffee7cb25f0785e54aa35f7bfThis has:
| Assisted-by: LLM [design, codegen, tests]
It tells us a bit more about *how* the LLM was used, without introducing the advertisement or pinning exact models.
Quoted 7 lines
This format should allow for multiple tool usage:
| Assisted-by: LLM [triage, tests], coccinelle
I don't suggest this is included in this version, but it *is* fairly straightforward to add to AGENTS.md and tells reviewers just how exactly the LLM was used.
I think perhaps this should be a follow-up (this stuff is so fraught that I am super-glad to see Christian's suggestion fly through and want to take gains iteratively on this :), but completely agree.
Quoted 5 lines
David suggested something like:
Assisted-by LLM # < what it actually did in the patch >So I think we're kinda aligned on that?
Once the patch from Christian is upstream I can follow up with some changes. I was holding that back for now until there is agreement on the LLM part.
Signature · 3 lines
Cheers, David
Quoted 29 lines
Op 04-08-2026 10:10 CEST schreef Lorenzo Stoakes (ARM) <[email protected]>:
Quoted 16 lines · Konstantin Ryabitsev
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 2 lines · Jonathan Corbet
Documentation/process/coding-assistants.rst +1
-1- Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparseI've been playing with this a bit, and it's pretty easy to teach the agent to add a few tag-like notes as to how exactly it was used, e.g.:
https://git.kernel.org/pub/scm/utils/b4/b4.git/commit/?id=018b87444d32eb2ffee7cb25f0785e54aa35f7bfThis has:
| Assisted-by: LLM [design, codegen, tests]
It tells us a bit more about *how* the LLM was used, without introducing the advertisement or pinning exact models.
Quoted 7 lines
This format should allow for multiple tool usage:
| Assisted-by: LLM [triage, tests], coccinelle
I don't suggest this is included in this version, but it *is* fairly straightforward to add to AGENTS.md and tells reviewers just how exactly the LLM was used.
Quoted 8 lines
I think perhaps this should be a follow-up (this stuff is so fraught that I am super-glad to see Christian's suggestion fly through and want to take gains iteratively on this :), but completely agree.
David suggested something like:
Assisted-by LLM # < what it actually did in the patch >
We should have some format to explain what the assistant was used for, but not sure if a single line after the tag is going to cut it. I agree it is the most simple, but I have personally used an LLM for a patch where the explanation of what exactly it was put to do would have been very hard to fit in a format like this without significant loss of information.
So, maybe below the ---? I guess that most maintainers don't want this kind of explanation to be part of the commit message (or maybe they do?)
Best,
Jori.
Quoted 38 lines · Jori Koolstra
Quoted 29 lines
Op 04-08-2026 10:10 CEST schreef Lorenzo Stoakes (ARM) <[email protected]>:
Quoted 16 lines · Konstantin Ryabitsev
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 2 lines · Jonathan Corbet
Documentation/process/coding-assistants.rst +1
-1- Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparseI've been playing with this a bit, and it's pretty easy to teach the agent to add a few tag-like notes as to how exactly it was used, e.g.:
https://git.kernel.org/pub/scm/utils/b4/b4.git/commit/?id=018b87444d32eb2ffee7cb25f0785e54aa35f7bfThis has:
| Assisted-by: LLM [design, codegen, tests]
It tells us a bit more about *how* the LLM was used, without introducing the advertisement or pinning exact models.
Quoted 7 lines
This format should allow for multiple tool usage:
| Assisted-by: LLM [triage, tests], coccinelle
I don't suggest this is included in this version, but it *is* fairly straightforward to add to AGENTS.md and tells reviewers just how exactly the LLM was used.
Quoted 8 lines
I think perhaps this should be a follow-up (this stuff is so fraught that I am super-glad to see Christian's suggestion fly through and want to take gains iteratively on this :), but completely agree.
David suggested something like:
Assisted-by LLM # < what it actually did in the patch >
Quoted 8 lines
We should have some format to explain what the assistant was used for, but not sure if a single line after the tag is going to cut it. I agree it is the most simple, but I have personally used an LLM for a patch where the explanation of what exactly it was put to do would have been very hard to fit in a format like this without significant loss of information.
So, maybe below the ---? I guess that most maintainers don't want this kind of explanation to be part of the commit message (or maybe they do?)
I think best to keep discussion of this to the follow up patch to avoid the usual combinatorial thread explosion on this topic :)
Quoted 3 lines
Best,
Jori.
--
Cheers, Lorenzo
Quoted 62 lines · Jonathan Corbet via groups.linuxfoundation.org
As suggested by Christian, I have applied his patch to a branch and simplified the changelog, see below.
I'm nervous about applying it still because I don't think it's my role to set this sort of policy; I really want to feel that there is a consensus behind it. So there's some additional CCs here because I would like to hear from some folks:
- This policy document originally came out of the TAB; is the TAB (on CC) OK with this change?
- At least one maintainer (on CC) have said that they currently strip Assisted-by tags out of patches before applying them, a practice that would seem to undermine the whole policy. Would this change be sufficient to end that practice?
Thanks,
jon
From
c31aa376a355e3b84b9e87ae1dbe19b394d4c82cMon Sep 17 00:00:00 2001
From: Christian Brauner <[email protected]>
Date: Wed, 1 Jul 2026 17:54:48 +0200
Subject: [PATCH] coding-assistants: simplify attributionThe requirement to identify specific models used in the Assisted-by tag provides free advertising to proprietary software companies while adding little or no useful information. Change the requirement to simply:
Assisted-by LLMto capture the fact that an LLM was used without tracking which one.
Signed-off-by Christian Brauner (Amutable) <[email protected]>Reviewed-by Lorenzo Stoakes (ARM) <[email protected]>Reviewed-by Jeff Layton <[email protected]>Reviewed-by Jori Koolstra <[email protected]>Message-ID: <[email protected]>
Signed-off-by Jonathan Corbet <[email protected]>--- Documentation/process/coding-assistants.rst | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)Documentation/process/coding-assistants.rst +1
-5@@ -43,12 +43,8 @@ When AI tools contribute to kernel development, proper attribution helps track the evolving role of AI in the development process. Contributions should include an Assisted-by tag in the following format:: - Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2] + Assisted-by: LLM [TOOL1] [TOOL2] -Where: - -* ``AGENT_NAME`` is the name of the AI tool or framework -* ``MODEL_VERSION`` is the specific model version used * ``[TOOL1] [TOOL2]`` are optional specialized analysis tools used (e.g., coccinelle, sparse, smatch, clang-tidy)
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 5 lines
Documentation/process/coding-assistants.rst +1
-1@@ -56,4 +52,4 @@ Basic development tools (git, gcc, make, editors) should not be listed. Example:: - Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparse
LGTM
Signature · 3 lines
Cheers, David
Jonathan Corbet
maintainerQuoted 8 lines · Jonathan Corbet
As suggested by Christian, I have applied his patch to a branch and simplified the changelog, see below.
I'm nervous about applying it still because I don't think it's my role to set this sort of policy; I really want to feel that there is a consensus behind it. So there's some additional CCs here because I would like to hear from some folks:
Quoted 8 lines
- This policy document originally came out of the TAB; is the TAB (on CC) OK with this change?
- At least one maintainer (on CC) have said that they currently strip Assisted-by tags out of patches before applying them, a practice that would seem to undermine the whole policy. Would this change be sufficient to end that practice?
So I was not overwhelmed by responses :) I'm going to take silence for assent in this case and send the patch through.
Thanks,
jon
Miguel Ojeda
Acked-byQuoted 3 lines · Jonathan Corbet via groups.linuxfoundation.org
So I was not overwhelmed by responses :) I'm going to take silence for assent in this case and send the patch through.
On the TAB side, we didn't meet since it was sent, but yeah, it doesn't look like there are strong opinions against this.
Personally, I think it is fine either way (e.g. someone could argue the advertising could help open models and harnesses etc.).
The patch removes the "Where:", not sure if that is intentional.
Thanks!
Cheers,
Miguel
Quoted 62 lines · Jonathan Corbet
As suggested by Christian, I have applied his patch to a branch and simplified the changelog, see below.
I'm nervous about applying it still because I don't think it's my role to set this sort of policy; I really want to feel that there is a consensus behind it. So there's some additional CCs here because I would like to hear from some folks:
- This policy document originally came out of the TAB; is the TAB (on CC) OK with this change?
- At least one maintainer (on CC) have said that they currently strip Assisted-by tags out of patches before applying them, a practice that would seem to undermine the whole policy. Would this change be sufficient to end that practice?
Thanks,
jon
From
c31aa376a355e3b84b9e87ae1dbe19b394d4c82cMon Sep 17 00:00:00 2001
From: Christian Brauner <[email protected]>
Date: Wed, 1 Jul 2026 17:54:48 +0200
Subject: [PATCH] coding-assistants: simplify attributionThe requirement to identify specific models used in the Assisted-by tag provides free advertising to proprietary software companies while adding little or no useful information. Change the requirement to simply:
Assisted-by LLMto capture the fact that an LLM was used without tracking which one.
Signed-off-by Christian Brauner (Amutable) <[email protected]>Reviewed-by Lorenzo Stoakes (ARM) <[email protected]>Reviewed-by Jeff Layton <[email protected]>Reviewed-by Jori Koolstra <[email protected]>Message-ID: <[email protected]>
Signed-off-by Jonathan Corbet <[email protected]>--- Documentation/process/coding-assistants.rst | 8 ++------ 1 file changed, 2 insertions(+), 6 deletions(-)Documentation/process/coding-assistants.rst +1
-5@@ -43,12 +43,8 @@ When AI tools contribute to kernel development, proper attribution helps track the evolving role of AI in the development process. Contributions should include an Assisted-by tag in the following format:: - Assisted-by: AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2] + Assisted-by: LLM [TOOL1] [TOOL2] -Where: - -* ``AGENT_NAME`` is the name of the AI tool or framework -* ``MODEL_VERSION`` is the specific model version used * ``[TOOL1] [TOOL2]`` are optional specialized analysis tools used (e.g., coccinelle, sparse, smatch, clang-tidy)
Documentation/process/coding-assistants.rst Basic development tools (git, gcc, make, editors) should not be listed. · line 55
Quoted 5 lines
Documentation/process/coding-assistants.rst +1
-1@@ -56,4 +52,4 @@ Basic development tools (git, gcc, make, editors) should not be listed. Example:: - Assisted-by: Claude:claude-3-opus coccinelle sparse + Assisted-by: LLM coccinelle sparse
One thing that needs to be changed in conjunction with this is checkpatch.pl. When I try to use the new format, I get:
● a9b9b7e55379: btrfs: pre-allocate delayed dir index for non-overwrite rename
● checkpatch.pl: :2036: WARNING: Assisted-by expects 'AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]' format
This patch fixes it for me, but I'm not sure it's restrictive enough. Jon, feel free to fold this into the Documentation patch, or I can send it separately if this seems right.
-----------------------8<-------------------------
[PATCH] checkpatch.pl: adapt to new Assisted-by: format
--- scripts/checkpatch.pl | 7 ++++--- 1 file changed, 4 insertions(+), 3 deletions(-)
scripts/checkpatch.pl +4 -3
@@ -3124,11 +3124,12 @@ sub process { } } - # Assisted-by uses AGENT_NAME:MODEL_VERSION format, not email + # Assisted-by uses a free-form value (e.g. "LLM"), not an + # email address, so skip the email format checks below. if ($sign_off =~ /^Assisted-by:/i) { - if ($email !~ /^\S+:\S+/) { + if ($email =~ /^\s*$/) { WARN("BAD_SIGN_OFF", - "Assisted-by expects 'AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]' format\n" . $herecurr); + "Assisted-by requires a value\n" . $herecurr); } next; }
Signature · 1 line
2.55.0
Jonathan Corbet
maintainerQuoted 9 lines · Jeff Layton
One thing that needs to be changed in conjunction with this is checkpatch.pl. When I try to use the new format, I get:
●
a9b9b7e55379: btrfs: pre-allocate delayed dir index for non-overwrite rename
● checkpatch.pl: :2036: WARNING: Assisted-by expects 'AGENT_NAME:MODEL_VERSION [TOOL1] [TOOL2]' formatThis patch fixes it for me, but I'm not sure it's restrictive enough. Jon, feel free to fold this into the Documentation patch, or I can send it separately if this seems right.
I'd say send it separately, probably with a copy to Joe Perches...
Thanks,
jon