get_debug_evidence
Retrieve comprehensive failure evidence for a failing test: flake verdict, failure signatures, regression boundary, and downloadable artifacts like traces and screenshots in one call.
Instructions
Start every failing-test investigation here. One call returns the whole cheap tier of the evidence ladder: the computed flake verdict with its per-attempt failure signatures, the regression boundary (the last run this test passed and the first it failed), and download links for every stored artifact — trace, screenshots, and the expected/actual/diff images on a visual failure. Read all of it before forming a hypothesis. The verdict says whether the failure repeats, never why, so it rules fixes out rather than pointing at a cause; the boundary turns "why does this fail" into "what changed between these two runs", which is a far smaller question. Artifact links are minutes-scale: download what you need immediately, and call this again to mint fresh ones rather than treating an expired link as a missing artifact.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | Response shape. "md" is markdown, and markedly cheaper for the same content. | |
| maxLength | No | Cap the markdown length. Applies to format="md" only; anything cut is announced in the output. JSON is never truncated, because a cut payload would not parse and would read as a complete one. | |
| projectId | Yes | Project ID (e.g. project_<id>) | |
| testrun_id | No | Run scope. Omit to use the most recently started run carrying this case. | |
| testcase_id | No | The case's pw_test_id. | |
| testcase_name | No | Full test title. Required for the regression boundary — prefer it when known. | |
| suite_file_path | No | Spec file path — only needed when the title is shared across files. | |
| include_instructions | No | Default true. The procedure and the trace runbook are identical on every call and about half the response — set false on repeat calls once you have read them. |