agent-runtime-framework/workflows/comparative-plan.yaml

name: comparative-plan
version: 1
description: "3-way comparative planning: two models plan independently, cross-review, then synthesize"

params:
  required:
    task_description:
      type: string
      description: "What to plan — the task or feature to design"
    project_id:
      type: string
      description: "Target project identifier"
  optional:
    model_a:
      type: string
      default: null
      description: "Override model A endpoint (auto-selected from registry if omitted)"
    model_b:
      type: string
      default: null
      description: "Override model B endpoint (auto-selected from registry if omitted)"
    best_practices:
      type: list
      default:
        - api-design
        - spec-driven-development
        - test-driven-development
        - security-architecture
      description: "Best practice topics to review against"
    repo:
      type: string
      default: null
      description: "Git repo URL to clone for context (optional)"

nodes:
  plan_a:
    name: "Plan A"
    prompt: |
      Create a detailed implementation plan for the following task:

      {{ task_description }}

      ## Instructions
      - Follow spec-driven development methodology
      - Structure your plan with: Overview, Phases, Files to create/modify, Test strategy, Dependencies
      - Be specific about data models, API contracts, and interfaces
      - Consider security, error handling, and edge cases
      - Write your final plan to /workspace/project/output.md
    harness: planning/v1
    requirements:
      min_scores:
        complexity: 7
        spec_adherence: 8

  plan_b:
    name: "Plan B"
    prompt: |
      Create a detailed implementation plan for the following task:

      {{ task_description }}

      ## Instructions
      - Follow spec-driven development methodology
      - Structure your plan with: Overview, Phases, Files to create/modify, Test strategy, Dependencies
      - Be specific about data models, API contracts, and interfaces
      - Consider security, error handling, and edge cases
      - Write your final plan to /workspace/project/output.md
    harness: planning/v1
    requirements:
      min_scores:
        complexity: 7
        spec_adherence: 8

  review_a_of_b:
    name: "Review: A reviews B's plan"
    depends_on: [plan_a, plan_b]
    prompt: |
      You are reviewing an implementation plan against best practices.

      ## Best Practices to Check Against
      Read and apply these best practice topics: {{ best_practices | join(', ') }}

      ## Plan to Review
      The following plan was produced by another model. Review it critically.

      <<ARTIFACT:plan_b:output>>

      ## Instructions
      1. Read each relevant best practice file from /best-practices/
      2. Check the plan against each practice
      3. List specific, numbered improvement points
      4. For each point, cite which best practice it violates or could better follow
      5. Be concrete — say what should change, not just that something is wrong

      Write your review to /workspace/project/output.md
    harness: planning/v1
    requirements:
      min_scores:
        spec_adherence: 8

  review_b_of_a:
    name: "Review: B reviews A's plan"
    depends_on: [plan_a, plan_b]
    prompt: |
      You are reviewing an implementation plan against best practices.

      ## Best Practices to Check Against
      Read and apply these best practice topics: {{ best_practices | join(', ') }}

      ## Plan to Review
      The following plan was produced by another model. Review it critically.

      <<ARTIFACT:plan_a:output>>

      ## Instructions
      1. Read each relevant best practice file from /best-practices/
      2. Check the plan against each practice
      3. List specific, numbered improvement points
      4. For each point, cite which best practice it violates or could better follow
      5. Be concrete — say what should change, not just that something is wrong

      Write your review to /workspace/project/output.md
    harness: planning/v1
    requirements:
      min_scores:
        spec_adherence: 8

  synthesize:
    name: "Synthesize final plan"
    depends_on: [review_a_of_b, review_b_of_a]
    prompt: |
      You are synthesizing a final implementation plan from two competing plans and their cross-reviews.

      ## Original Task
      {{ task_description }}

      ## Plan A
      <<ARTIFACT:plan_a:output>>

      ## Plan B
      <<ARTIFACT:plan_b:output>>

      ## Review of Plan B (by the model that wrote Plan A)
      <<ARTIFACT:review_a_of_b:output>>

      ## Review of Plan A (by the model that wrote Plan B)
      <<ARTIFACT:review_b_of_a:output>>

      ## Instructions
      1. Identify the strongest elements from each plan
      2. Address all improvement points raised in both reviews
      3. Synthesize a single, improved plan that combines the best of both
      4. Structure: Overview, Phases, Files, Test strategy, Dependencies
      5. Flag any unresolved disagreements between the reviews

      Write the final synthesized plan to /workspace/project/output.md
    harness: planning/v1
    requirements:
      min_scores:
        complexity: 8
        spec_adherence: 9
        creativity: 7

scoring:
  type: comparative_review
  reviews:
    - review_node: review_a_of_b
      scored_model_node: plan_b
      dimension: spec_adherence
    - review_node: review_b_of_a
      scored_model_node: plan_a
      dimension: spec_adherence
  method: fewer_improvement_points_wins