test(task): lock in markdown subagent descriptions#29377
Conversation
Add a regression case for anomalyco#27831 so markdown-defined subagents keep their frontmatter description when the Task tool builds its subagent list. This protects the already-correct config plumbing on dev from falling back to the generic manual-only text again. Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai>
|
This PR doesn't fully meet our contributing guidelines and PR template. What needs to be fixed:
Please edit this PR description to address the above within 2 hours, or it will be automatically closed. If you believe this was flagged incorrectly, please let a maintainer know. |
|
The following comment was made by an LLM, it may be inaccurate: Potential Related PR Found:
Why it's related: This PR appears to cover similar territory—testing markdown frontmatter description propagation for agents. PR #29377 focuses on the Task tool description rendering, while #28086 appears to test the Agent.list() path. They may be addressing complementary aspects of the same issue (#27831) or one could be a predecessor/related fix. I recommend checking if PR #28086 is already merged and whether it addresses the regression test needs or if they cover different test scenarios. |
|
This pull request has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window. Feel free to open a new pull request that follows our guidelines. |
Summary
Why
Issue #27831 reports that markdown-defined subagents can fall back to a generic manual-only description in the Task tool even when description is present in frontmatter. On current dev, the production code path already preserves that field, but there was no regression coverage for the markdown-defined agent path.
Closes #27831
Verification