name: email-triage-env
version: "1.0.0"
description: >
  An email triage and response environment where an agent reads inbox emails,
  assigns priority labels (urgent/normal/low), drafts professional replies,
  archives junk, and flags ambiguous messages for human review.

tasks:
  - id: task1
    name: Inbox Prioritisation
    difficulty: easy
    description: >
      Read 5 emails and label each as urgent, normal, or low priority.
    max_steps: 20
    reward:
      type: incremental
      max: 1.0
      per_correct_label: 0.2

  - id: task2
    name: Draft a Reply
    difficulty: medium
    description: >
      Given a customer complaint email, draft a professional reply that
      addresses all stated issues without fabricating facts.
    max_steps: 10
    reward:
      type: checklist
      max: 1.0
      criteria:
        - addresses_all_issues: 0.3
        - professional_tone: 0.3
        - correct_recipient_subject: 0.2
        - no_fabricated_facts: 0.2

  - id: task3
    name: Full Triage Pipeline
    difficulty: hard
    description: >
      10-email inbox: prioritise all, draft replies for urgent emails,
      archive junk, flag ambiguous emails for human review.
    max_steps: 60
    reward:
      type: holistic
      max: 1.0
      penalties:
        destructive_action: -0.1
        loop_action: -0.05

environment:
  language: python
  entry_point: server/app.py
  port: 7860
  health_check: /health
  state_endpoint: /state
  reset_endpoint: /reset
  step_endpoint: /step

inference:
  entry_point: inference.py
  model: llama-3.3-70b-versatile

resources:
  cpu: 2
  memory_gb: 4
  gpu: false