name: dev-env-debugger
version: 1.0.0
description: >
  An OpenEnv environment where an AI agent debugs a broken multi-service
  development stack. The agent must read logs, inspect configs, fix
  environment variables, and restart services to restore a healthy state.

tags:
  - openenv
  - devops
  - debugging
  - real-world
  - multi-service

author: Ajinkya
license: MIT

environment:
  reset_endpoint: /reset
  step_endpoint: /step
  state_endpoint: /state
  tasks_endpoint: /tasks
  grader_endpoint: /grader
  baseline_endpoint: /baseline

tasks:
  - id: task1
    name: Single Service Fault
    difficulty: easy
    description: One service down due to a single misconfigured environment variable.

  - id: task2
    name: Multi-Fault Diagnosis
    difficulty: medium
    description: Two services failing due to independent faults. Partial credit per fault fixed.

  - id: task3
    name: Cascading Failure Debug
    difficulty: hard
    description: Root cause fault causing cascading failures with misleading error messages.

  - id: task4
    name: Triple Fault Storm
    difficulty: hard
    description: Three simultaneous independent faults across all services. Agent must triage and fix all three.

  - id: task5
    name: Silent Misconfiguration
    difficulty: expert
    description: Two faults with no obvious error logs. Agent must inspect env vars proactively, not rely on logs.

observation_space:
  type: object
  fields:
    step: integer
    services: object  # map of service name → {status, port}
    last_action_result: object  # {success: bool, message: string}
    available_actions: array
    done: boolean

action_space:
  type: object
  fields:
    type: string  # read_logs | inspect_env | edit_env | restart_service | run_healthcheck | submit
    service: string  # optional — api | worker | database | proxy
    key: string      # optional — env var key (edit_env only)
    value: string    # optional — env var value (edit_env only)

reward:
  min: -0.5
  max: 1.0
  shaped: true
  description: >
    Partial rewards for correct diagnostic actions and service recovery.
    Penalties for redundant actions and submitting while unhealthy.

baseline:
  model: gpt-4o-mini
  expected_scores:
    task1: 0.85
    task2: 0.60
    task3: 0.35