Conversation
theihor
force-pushed
the
agent
branch
14 times, most recently
from
f7688c0 to
e47bec8
Compare
theihor
force-pushed
the
agent
branch
3 times, most recently
from
5149ddb to
68b20c0
Compare
Implement a new experimental CI workflow that uses AI to investigate CI test failures and come up with improvements to the BPF CI system. The underlying environment is basically the same as we use for AI code review workflows: Claude Code has access to the Linux repository, semcode database [1] (with --lore), as well as CI source code and configs and various dependencies and tools. The AI is then instructed to explore recent CI failures, lore discussions and code changes and select a single issue for investigation (see `ci/claude/bpf-ci-agent.md` for the full prompt). AI may also suggest a code change addressing the issue. The results are then posted as GitHub issues in kernel-patches/vmtest for human evaluation. If it's good, it may be submitted to the mailing list (with the full disclosure, of course). If it's bad the issue can be closed and ignored. [1] https://github.com/facebookexperimental/semcode Signed-off-by: Ihor Solodrai <ihor.solodrai@linux.dev>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Implement a new experimental CI workflow that uses AI to investigate
CI test failures and come up with improvements to the BPF CI system.
The underlying environment is basically the same as we use for AI code
review workflows: Claude Code has access to the Linux repository,
semcode database [1] (with --lore), as well as CI source code and
configs and various dependencies and tools.
The AI is then instructed to explore recent CI failures, lore
discussions and code changes and select a single issue for
investigation (see
ci/claude/bpf-ci-agent.mdfor the fullprompt). AI may also suggest a code change addressing the issue.
The results are then posted as GitHub issues in kernel-patches/vmtest
for human evaluation. If it's good, it may be submitted to the mailing
list (with the full disclosure, of course). If it's bad the issue can
be closed and ignored.
Signed-off-by: Ihor Solodrai ihor.solodrai@linux.dev