# RLM Divide-and-Conquer Example
# Semantic chunking pipeline for large document analysis
# Based on OpenProse example 41-rlm-divide-conquer
#
# Pattern: chunker → analyzer → synthesizer pipeline
# Use when: input is too large for single-pass analysis

version: "1.0.0"

root_task:
  node_id: "task-dc00000"
  depth: 0
  prompt: "Analyze the entire codebase for API endpoint documentation completeness"
  decomposition_strategy: map-reduce
  merge_strategy: summarize
  chunking_strategy: semantic-boundary
  batch_size: 25

  children:
    # Phase 1: Chunker identifies semantic boundaries
    - node_id: "task-chunk01"
      parent_id: "task-dc00000"
      depth: 1
      prompt: |
        Scan the codebase and identify all API endpoint files.
        Group them by module/domain into 4-8 semantic chunks.
        Each chunk should contain related endpoints (auth, users, billing, etc.).
        Output a JSON manifest of chunks with file lists.
      preferred_model: haiku
      context:
        type: filtered
        source: "retrieved_documents"
        filters:
          file_patterns: ["src/**/*.ts", "src/**/*.js"]
      status: pending

    # Phase 2: Parallel analyzers process each chunk
    - node_id: "task-anlz001"
      parent_id: "task-dc00000"
      depth: 1
      prompt: |
        For each endpoint in this chunk:
        1. Extract the route, method, and handler
        2. Check if JSDoc/TSDoc exists
        3. Check if OpenAPI spec references it
        4. Rate documentation completeness (0-100)
        Output structured findings per endpoint.
      preferred_model: sonnet
      decomposition_strategy: parallel
      context:
        type: slice
        source: "parent_result"
      status: pending

    # Phase 3: Synthesizer merges chunk results
    - node_id: "task-synth01"
      parent_id: "task-dc00000"
      depth: 1
      prompt: |
        Synthesize all chunk analyses into a single documentation
        completeness report. Include:
        - Overall coverage percentage
        - Top 10 undocumented endpoints by importance
        - Module-by-module breakdown
        - Specific recommendations for each gap
      preferred_model: sonnet
      context:
        type: full
        source: "parent_result"
      quality_gate:
        min_score: 85
        scoring_criteria: "Completeness of coverage, accuracy of gap identification, actionability of recommendations"
        scorer_model: sonnet
        max_iterations: 3
        fallback: return_best
      status: pending

  status: pending

metadata:
  tree_id: "tree-divconq0"
  root_prompt: "Codebase API documentation completeness analysis"
  max_depth: 2
  total_nodes: 4
  execution_mode: logged

# Notes:
# - Chunker uses Haiku (simple file grouping task)
# - Analyzers use Sonnet (moderate code analysis)
# - Synthesizer uses Sonnet with quality gate (final deliverable)
# - semantic-boundary chunking respects module boundaries
# - batch_size: 25 means analyzer processes up to 25 endpoints per sub-agent
# - Parallel analyzers run independently per chunk