openenv.yaml

name: debugops
version: "1.0.0"
description: >
  DebugOps — an AI Incident Response environment where an agent acts as an
  on-call SRE to diagnose and resolve production system failures using
  noisy logs, degraded metrics, and multi-step fix sequences.

observation_space:
  type: dict
  fields:
    services:
      type: dict
      description: "Per-service health status: api, db, cache → healthy | degraded"
    logs:
      type: list[str]
      description: "System log lines (may contain noise and red herrings)"
    metrics:
      type: dict
      fields:
        latency:    { type: float, description: "Latency in ms" }
        error_rate: { type: float, description: "Error rate 0.0–1.0" }
        cpu:        { type: float, description: "CPU utilisation %" }
    time_step:
      type: int
      description: "Steps elapsed in the current episode"

action_space:
  type: discrete
  actions:
    - restart_api
    - restart_db
    - restart_cache
    - scale_up
    - noop

tasks:
  - name: simple
    description: "Single-service failure; 2-step fix; 15-step budget."
    module: tasks.task_simple
    max_steps: 15
    difficulty: low

  - name: multi_service
    description: "Two services degrade simultaneously; 12-step budget; extra latency penalty."
    module: tasks.task_multi_service
    max_steps: 12
    difficulty: medium

  - name: critical
    description: "Memory-leak root cause with misleading logs; SLA penalty; 10-step budget."
    module: tasks.task_critical
    max_steps: 10
    difficulty: high

grader:
  module: grader.grader
  function: evaluate_episode
  score_range: [0.0, 1.0]
  deterministic: true

baseline:
  module: agent.baseline
  function: act
  description: "Heuristic agent using log-keyword matching and metric thresholds."

inference:
  script: inference.py
  env_vars:
    - API_BASE_URL
    - MODEL_NAME
    - HF_TOKEN

required_env:
  - name: API_BASE_URL
    description: "OpenAI-compatible LLM endpoint"
    default: "https://router.huggingface.co/v1"
  - name: MODEL_NAME
    description: "Model identifier"
    default: "Qwen/Qwen2.5-72B-Instruct"
  - name: HF_TOKEN
    description: "HuggingFace / OpenAI API key"
    required: true