Repository navigation
Federate flydsl-kernel-trace-analysis from ROCm/FlyDSL - #274
Merged
Merged
Conversation
johnl-amd
force-pushed
the
federate-flydsl-kernel-authoring
branch
from
October 19, 2026 08:40
bbe3ff7 to
420856a
Compare
johnl-amd
force-pushed
the
federate-flydsl-kernel-trace-analysis
branch
from
October 19, 2026 08:40
5f5a38e to
cfe5c34
Compare
Picks up ROCm/FlyDSL#1322, which tells the skill to run the bundled pmc_l2_analyzer.py rather than recompute its metrics inline. That was the one behavioral expectation failing here (12/13); upstream scored 13/13 on three consecutive runs with the fix.
danielholanda
marked this pull request as ready for review
October 26, 2026 21:47
…kernel-trace-analysis
danielholanda
changed the base branch from
federate-flydsl-kernel-authoring
to
main
October 26, 2026 22:10
…l-trace-analysis Co-authored-by: Cursor <cursoragent@cursor.com> # Conflicts: # .github/federation.json
danielholanda
approved these changes
Oct 26, 2026
danielholanda
left a comment
danielholanda
left a comment
Collaborator
There was a problem hiding this comment.
Looks good and passing all tests!
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Vendors
flydsl-kernel-trace-analysisfromROCm/FlyDSL, adding it to the federation source that #273 introduces.Upstream the skill folder is
kernel-trace-analysis, so the entry carriesas: flydsl-kernel-trace-analysisto keep the catalog name Felix used in #267 and #270. The importer rewrites thename:field in the vendored copy to match.This supersedes #267 and #270, which were closed pending FlyDSL #1304 and #1305. Both merged on Oct 18, so the upstream skill now carries its own skill card, evals and offline fixtures. Original work is Felix Li's.
Stacked on #273 and based on its branch, since both skills share one
ROCm/FlyDSLblock infederation.json. Draft until that merges, then I'll rebase ontomain.One follow-up for the FlyDSL side rather than here: the skill description ends with
Usage: /kernel-trace-analysis <cmd>, which is the upstream name. Installed from the catalog the skill isflydsl-kernel-trace-analysis, so that line will point users at a command they don't have. Worth fixing upstream, where the nightly import will pick it up.The README catalog row is deliberately not here. Every row links to
blob/main/skills/<name>/SKILL.md, which 404s on the external-reference check until the skill is actually onmain. Same split as #248 then #255: the row follows in a separate PR once this merges.Behavioral evals are failing, and it looks like a skill issue rather than a flake
Two runs, both 12/13, but failing a different expectation each time, and both of the same kind: the agent did not invoke the bundled script as prescribed.
flydsl-trace-offline-hotspotsflydsl-trace-offline-pmchotspot_analyzer.pyinto two invocations instead of one combining--kerneland source detailscripts/pmc_l2_analyzer.pywith the required flagsSo
SKILL.mddoes not pin the agent to running the bundled scripts with the given flags, and roughly one expectation of that class misses per run, landing on whichever case rolls badly. Worth tightening upstream in FlyDSL, where the nightly import will pick it up, rather than patching the vendored copy here.For contrast, #273 went green on a re-run, so the authoring skill's single miss does look like judge nondeterminism.
Testing
federate_skills.py --only flydsl-kernel-trace-analysis: vendors at6245f9b.publish.shthencheck.sh: 0 errors, 13 skills, Cursor and Codex manifests up to date.