recursive-decomposition

# Recursive Decomposition Guidelines ## References Consult these resources as needed: - ./references/rlm-strategies.md -- Detailed decomposition patterns from the RLM paper - ./references/cost-analysis.md -- When to apply recursive vs. direct approaches - ./references/codebase-analysis.md -- Full walkthrough of codebase-wide analysis - ./references/document-aggregation.md -- Multi-document information extraction ## Core Principles **CRITICAL: Treat inputs as environmental variables, not immediate context.** Most tasks fail when context is overloaded. Instead of loading entire contexts into the processing window, treat inputs as **environmental variables** accessible through code execution. Decompose problems recursively, process segments independently, and aggregate results programmatically. **Progressive Disclosure**: Load information only when necessary. Start high-level to map the territory, then dive deep into specific areas. ### When Recursive Decomposition is Required - Tasks involving 10+ files - Input exceeding ~50k tokens where single-prompt context is insufficient - Multi-hop questions requiring evidence from multiple scattered sources - Codebase-wide pattern analysis or migration planning ### When Direct Processing Works - Small contexts (<30k tokens) - Single file analysis - Linear complexity tasks with manageable inputs ## Operational Rules - Always identify the search space size first. - Always use `grep` or `glob` before `view_fil...