spec_version: "1.0"
name: "rag_optimizer"
environment:
  name: "RAG Optimizer"
  description: "RAG pipeline optimization benchmark. Agents resolve pricing conflicts, route metadata tags, and splinter monolithic content blobs."
  version: "1.0.0"
  dockerfile: "Dockerfile"
  endpoints:
    reset: "/reset"
    step: "/step/{session_id}"
    state: "/state/{session_id}"
tasks:
  - id: easy
    name: "Contamination Purging"
    description: "Purge contradictory or low-value documents so retrieval surfaces clean, high-signal references."
    reward_range: [0.01, 0.99]
    grader: "rag_optimizer.server.grader:grade_easy"
  - id: medium
    name: "Syntactic Splintering"
    description: "Break down the monolithic onboarding blob into multiple granular chunks."
    reward_range: [0.01, 0.99]
    grader: "rag_optimizer.server.grader:grade_medium"
  - id: hard
    name: "Duplicate Purge"
    description: >
      Multi-doc deduplication for framework drift. KB contains 3 overlapping
      FastAPI routing docs: two legacy variants with incorrect @app.route()
      guidance and one correct current doc using @app.get()/@app.post() and
      Pydantic v2, plus distractors. Agent must delete noisy legacy docs so
      retrieval surfaces the correct current doc at rank 1. Reward improves
      continuously as noise is removed; no binary metadata gate.
    reward_range: [0.01, 0.99]
    grader: "rag_optimizer.server.grader:grade_hard"
agent:
  inference_entrypoint: "inference.py"
  requirements: "requirements.txt"