server/openenv.yaml

name: content-moderation-env
version: "1.0.0"
description: >
  AI-powered content moderation environment. Agents triage text, social
  posts, and multimodal content (including deepfake detection) across
  three difficulty levels using the standard OpenEnv step/reset/state API.
author: openenv-participant
license: MIT

tasks:
  - id: text_spam
    difficulty: easy
    description: Classify email/message content as spam or legitimate
    content_type: text
    num_items: 5
    score_range: [0.0, 1.0]

  - id: content_moderation
    difficulty: medium
    description: Multi-label social media content moderation
    content_type: text
    num_items: 5
    score_range: [0.0, 1.0]

  - id: deepfake_detection
    difficulty: hard
    description: Detect AI-manipulated/deepfake media and make moderation decisions
    content_type: multimodal
    num_items: 5
    score_range: [0.0, 1.0]

action_space:
  type: object
  fields:
    decision:
      type: string
      enum: [approve, reject, escalate, flag]
    reason:
      type: string
    confidence:
      type: float
      range: [0.0, 1.0]
    labels:
      type: array
      items: string
      valid_values:
        - spam
        - scam
        - phishing
        - pharmaceutical_spam
        - hate_speech
        - violence
        - harassment
        - misinformation
        - adult_content
        - deepfake
        - political_manipulation
        - fraud

observation_space:
  type: object
  fields:
    content_id: string
    content_type: string
    text: optional string
    image_description: optional string
    detector_score: optional float
    metadata: object
    step_num: integer
    total_steps: integer

endpoints:
  reset: POST /reset
  step: POST /step
  state: GET /state
  close: POST /close
  tasks: GET /tasks
  health: GET /health

docker:
  context: server
  dockerfile: server/Dockerfile

huggingface:
  space_sdk: docker
  tags:
    - openenv
    - content-moderation
    - deepfake-detection