detailed_analyze_launch_failures
Analyze failed tests in Zebrunner launches to identify root causes, group similar errors, and generate Jira tickets with recommendations for efficient debugging.
Instructions
🚀 Analyze failed tests WITHOUT linked issues in a launch with grouping, statistics, and recommendations. Automatically analyzes all tests if ≤10, otherwise first 10 (use offset/limit for more). Use filterType: 'all' to include tests with issues. Supports pagination and screenshot analysis. NEW: Jira format with smart grouping - creates combined tickets for similar errors! 💡 TIP: Can be auto-invoked from Zebrunner launch URLs like: https://workspace.zebrunner.com/projects/PROJECT/automation-launches/LAUNCH_ID
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| testRunId | Yes | Launch ID / Test Run ID (e.g., 120806) | |
| projectKey | No | Project key (e.g., 'MCP') - alternative to projectId | |
| projectId | No | Project ID - alternative to projectKey | |
| filterType | No | Filter: 'without_issues' = only tests without linked Jira tickets (DEFAULT), 'all' = all failed tests | without_issues |
| includeScreenshotAnalysis | No | Download and analyze screenshots with AI for each test (increases analysis time) | |
| screenshotAnalysisType | No | Screenshot analysis type if enabled | detailed |
| format | No | Output format: 'detailed' = full analysis, 'summary' = condensed, 'jira' = ready for Jira tickets with smart grouping | summary |
| jiraDetailLevel | No | Jira detail level: 'basic' = fast (no deep analysis), 'full' = comprehensive with deep analysis (DEFAULT, slower but thorough) | full |
| executionMode | No | Execution mode: sequential (safe), parallel (fast), or batches (balanced) | sequential |
| batchSize | No | Batch size if executionMode is 'batches' (default: 5) | |
| offset | No | Pagination offset - start from test N (e.g., 0 for first 20, 20 for next 20) | |
| limit | No | Number of tests to analyze (default: 20, max recommended: 30) |