Repository navigation
fix(harness): warn when URL-base skill is fetched with only SKILL.md - #2697
Conversation
PR Summary by QodoWarn when URL-based skill fetch only downloads SKILL.md Description
Diagram
High-Level Assessment
Files changed (6)
|
6a50f82 to
b738b25
Compare
Site previewPreview: https://42a8cb2b-site.fullsend-ai.workers.dev Commit: |
|
🤖 Finished Review · ✅ Success · Started 2:56 PM UTC · Completed 3:07 PM UTC |
Code Review by Qodo
1. No warnings in lock --all
|
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
Looks good to me Labels: PR modifies skill fetching behavior in the harness composition layer Previous runLooks good to me Previous run (2)Looks good to me Labels: PR modifies harness composition and CLI lock/run commands |
b738b25 to
bcad7c7
Compare
|
🤖 Finished Review · ✅ Success · Started 3:18 PM UTC · Completed 3:26 PM UTC |
ralphbean
left a comment
There was a problem hiding this comment.
LGTM. One minor note inline.
Address PR fullsend-ai#2690 review feedback: fetchBaseSkill only fetches SKILL.md, silently losing companion files (sub-agents, scripts, meta-prompts). Emit a warning on the Dependency so CLI surfaces it during lock/run. Also strengthen lock_test.go assertions to verify all 3 deps (base, agent, skill) instead of only deps[0]. Signed-off-by: Greg Allen <gallen@redhat.com> Signed-off-by: Claude Opus 4.6 <noreply@anthropic.com> Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com> Signed-off-by: Greg Allen <gallen@redhat.com>
bcad7c7 to
6392001
Compare
|
🤖 Finished Review · ✅ Success · Started 4:07 PM UTC · Completed 4:16 PM UTC |
|
🤖 Finished Retro · ✅ Success · Started 4:36 PM UTC · Completed 4:43 PM UTC |
Retro: PR #2697 — warn when URL-based skill fetch only downloads SKILL.mdVerdict: Workflow went well. No new proposals — existing issues already cover the one identified inefficiency. Timeline
What went well
Inefficiency noted (already tracked)
Autonomy readiness noteThe review agent's approval aligned with the human reviewer's verdict. The only human-added value was a subjective wording improvement on a user-facing warning message — not a correctness or architecture issue. This class of change (adding a new field + propagating it through existing patterns + test coverage) is a good candidate for higher review autonomy. |
Summary
Addresses review feedback on #2690:
fetchBaseSkillonly fetchesSKILL.md, silently losing companion files (sub-agents, scripts, meta-prompts). Now attaches a warning to theDependencyso CLI emits it duringfullsend lockandfullsend run, guiding users to use forge-format URLs for multi-file skills.lock_test.goasserted onlydeps[0]after bumping count to 3 — now verifies Field, URL, and Type for all 3 deps (base, agent, skill).Warningfield throughharness.Dependency→resolve.Dependency→ CLI output.Test plan
internal/harnesstests pass (including new warning assertions onTestFetchBaseSkill_OnlySKILLMDFetched,TestFetchBaseSkill_PartialIndexHit, cache-hit path)internal/clitests pass (including strengthenedTestRunLock_URLBaseOnlyDeps)🤖 Generated with Claude Code