debug-distributed
Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.
Guide for debugging distributed training issues in AReaL. Use when user encounters hangs, wrong results, OOM, or communication errors.
Guide for adding a new model to the Archon engine. Use when user wants to add support for a new HuggingFace model architecture in ArchonEngine.
Audit generated Excel reports by enumerating populated output rows, exposing formulas, and checking that each subtotal range includes all visible detail rows.
Generate structured PDF checklists and reports with tables, sections, and scoring criteria using Python libraries
Generate spreadsheet, diagram, and PDF report as a cohesive deliverable set with iteration budgeting per component
Step-by-step audio production with per-stem verification, timing alignment, and incremental quality gates
End-to-end audio production workflow with stems, effects, archiving, and verification
Build complex Excel files through staged, verifiable steps with intermediate CSV outputs for debugging
Systematic debugging workflow for python-pptx presentation generation
Unified workflow that delegates failed web searches to shell_agent for resilient data gathering, then applies anchored spreadsheet proof gates for verified Excel output
Dashboard panel component pattern for aggregator/summary panels that accept pushed partial data updates via updateData(), defer rendering until first data arrives, and incrementally re-render metrics without re-fetching — ideal for panels that synthesize data already fetched by other panels.
Implement efficient virtual scrolling for rendering large lists with DOM recycling, chunk-based rendering, and performance optimizations
Handle cascading data retrieval tool failures by falling back to embedded knowledge generation
Identify and classify agent failures occurring before execution starts
Identify and handle pre-execution agent failures occurring before any iterations or tool usage
Systematic document generation with unicode sanitization, engine fallback chain, and explicit error diagnosis
Document generation with direct pandoc/ReportLab execution (lightweight default) and optional shell_agent fallback for complex scenarios
Robust document generation with engine fallback chain, error diagnostics, and Python alternatives
Fallback workflow for multi-format document generation when shell_agent encounters errors
Robust PowerPoint generation with shell_agent primary approach and python-pptx fallback, including working directory verification and inline error debugging
Resilient PowerPoint generation with shell_agent primary path and python-pptx fallback
Delegate web search tasks to shell_agent when direct search_web tool fails, using its retry mechanism and multi-step capabilities for resilient data gathering