# RLM Self-Refine Example
# Quality-gated iterative refinement loop
# Based on OpenProse example 40-rlm-self-refine
#
# Pattern: evaluator + refiner loop that iterates until quality threshold met
# Use when: output quality matters more than speed (security analysis, research synthesis)

version: "1.0.0"

root_task:
  node_id: "task-refine00"
  depth: 0
  prompt: "Produce a comprehensive security analysis of the authentication module"
  decomposition_strategy: sequential
  merge_strategy: best-of-n

  # Quality gate enforces iterative refinement
  quality_gate:
    min_score: 85
    scoring_criteria: |
      Completeness: all auth flows covered (login, register, reset, token refresh).
      Accuracy: vulnerabilities correctly identified with OWASP references.
      Actionability: each finding has a concrete remediation step.
      Clarity: non-security engineers can understand the report.
    scorer_model: sonnet
    max_iterations: 5
    fallback: return_best

  children:
    - node_id: "task-draft001"
      parent_id: "task-refine00"
      depth: 1
      prompt: "Draft initial security analysis covering all authentication flows"
      preferred_model: sonnet
      context:
        type: filtered
        source: "file:src/auth/**/*.ts"
        filters:
          file_patterns: ["*.ts"]
      status: pending

    - node_id: "task-eval0001"
      parent_id: "task-refine00"
      depth: 1
      prompt: |
        Evaluate the security analysis against these criteria:
        - Are all auth flows covered?
        - Are OWASP references accurate?
        - Does each finding have a remediation step?
        - Is the language clear for non-specialists?
        Score 0-100 and provide specific improvement feedback.
      preferred_model: sonnet
      context:
        type: summary
        source: "parent_result"
      status: pending

    - node_id: "task-refn0001"
      parent_id: "task-refine00"
      depth: 1
      prompt: |
        Refine the security analysis based on evaluator feedback.
        Address each specific issue raised. Do not remove existing
        correct content — only improve weak areas.
      preferred_model: sonnet
      context:
        type: full
        source: "parent_result"
      status: pending

  status: pending

metadata:
  tree_id: "tree-selfref0"
  root_prompt: "Security analysis with quality-gated refinement"
  max_depth: 1
  total_nodes: 4
  execution_mode: logged

# Notes:
# - The quality_gate on the root node drives the loop: evaluate → refine → re-evaluate
# - Scorer uses Sonnet (cost-efficient for rubric evaluation)
# - Drafter uses Sonnet (good enough for initial pass)
# - After 5 iterations without reaching 85, returns best attempt
# - Iteration history is preserved for analysis