fix(docs-eval): tolerate nested artifact layout in CI executor#1001
Open
alexluong wants to merge 1 commit into
Open
fix(docs-eval): tolerate nested artifact layout in CI executor#1001alexluong wants to merge 1 commit into
alexluong wants to merge 1 commit into
Conversation
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
The docs-agent-eval job (run 29858282052) failed with
no .ts file foundeven though both scenarios passed scoring: the scenario-02 agent laid out its quickstart as atypescript/subproject, andexecute-ci-artifacts.shonly globs the run-dir root. Agent file layout is nondeterministic, so root-only discovery flakes.pick_sh/pick_tsnow fall back to a recursive search (node_modules pruned,.d.tsskipped, quickstart names preferred, sorted so the pick is deterministic), and install/execute run from the picked file's directory so a nestedpackage.jsonand.envstash apply. The smoke test writes its TS project undertypescript/to keep the nested path covered, and the agent prompt template now tells quick-path runs to write files directly in the working directory — that lowers drift; the executor change is what removes the failure mode.Verified by replaying the failed run's downloaded artifact through the executor: unpatched reproduces
no .ts file found; patched pickstypescript/outpost-quickstart.tsand proceeds to execution.🤖 Generated with Claude Code