test(benchmarks): add concept-search tasks

Browse Source

Three tasks whose target code shares no vocabulary with the prompt, run in a
repository with generated distractor modules.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

...

This commit is contained in:

Julian lechnerandClaude Opus 5.5 committed 2026-10-01 13:27:56 +02:00

1 parent a8f6f01f2f

commit 00a44f50b0

19 files changed

+106

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

scripts/benchmarks/tasks/12-search-transient-retry/repo/app/__init__.py

Whitespace-only changes.