| name | testRunner |
| description | "Parallel test runner across the given directories." |
Run tests for each of the following directories — launch all test runners in parallel, one independent agent per directory:
$ARGUMENTS
CRITICAL EXECUTION RULE — follow this EXACTLY:
- Launch one
tests-runner agent per directory using run_in_background: true, all in parallel. Pass the directory path to each agent so it knows which test suite to run.
- After launching, your response MUST END IMMEDIATELY. Write a brief message telling the user the agents were launched and that you will report when they finish — then STOP. Do NOT add any more tool calls.
- Do NOT poll, retry, resume, or call any tool after launching the agents. The main thread must be completely idle until the automatic completion notifications arrive.
- Only when ALL agents have completed (via automatic notifications), summarize the results to the user.