run_deep_dive
Diagnose a GitHub Actions workflow run to find why it was slow or failed. Compare jobs and steps against recent medians, identify regressions, failing tests, and include failing step logs.
Instructions
Deep-dive one workflow run: why was it slow, or why did it fail? Job waterfall (queue vs execution), every job and step compared against the workflow's own recent medians, named step regressions; failed runs lead with the failing job and step, name the failing tests (30+ test frameworks recognized), and inline the failing step's log tail (needs a token).
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"repo": "<repo>"
},
"name": "run_deep_dive"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| run | No | Run ID, full run URL, or "latest" (default "latest") | |
| repo | Yes | Repository as owner/name | |
| log_tail | No | Lines of the failing step's log to include per failed job (default 20, 0 = off; needs a token) |