Skip to main content

Overview

The fix-flaky-test tool retrieves insights and historical failure analysis about a flaky test. This tool allows AI assistants to access investigation results and apply fixes directly in your development environment. For more information, see Autofix Flaky Tests. Return Type: Structured analysis data with fix recommendations. Structure: metadata, summary, facts

Parameters

Required Parameters

You must also provide either investigationId or testCaseId.

Optional Parameters

Setting createNewInvestigation to true starts a new investigation, which counts against your repository’s and your test’s monthly investigation limits. Retrieving an existing investigation by investigationId or testCaseId does not.

Getting Parameter Values

If your AI assistant doesn’t have direct access to Git information, use these commands: Get repository name:
Look for the repository name in the output (e.g., trunk-io/trunk from git@github.com:trunk-io/trunk.git)

Usage Examples

With Test ID

Create New Investigation

With Existing Investigation

Error Handling