name: permanence
version: 1.1.0
spec_version: "0.1"
entry_point: permanence.openenv_env:PermanenceOpenEnv

description: >
  A reversibility-aware RL environment that trains LLMs to predict
  whether their actions are recoverable before taking them. Built on
  three operational-semantics simulators (filesystem, git, database)
  where R-levels (R1-R5) are derived from world state at execution
  time — not hardcoded tags. Agents must emit a <reversibility/> tag
  alongside each <action/>, and are scored on both task completion
  and prediction calibration.

author: chanikya
email: chanikyac01@gmail.com
huggingface_repo: chane335/permanence

tags:
  - openenv
  - world-modeling
  - long-horizon-planning
  - reinforcement-learning
  - agent-safety

type: chat

app:
  module: server.app
  object: app
  port: 7860

themes:
  primary: world_modeling
  secondary:
    - long_horizon_planning

tasks:
  - id: task_correction
    difficulty: 1
    description: Report error correction with irreversible external communication risk
    score_range: [0.0, 1.0]
  - id: task_conflict
    difficulty: 2
    description: Personnel conflict resolution with irreversible HR action risk
    score_range: [0.0, 1.0]
  - id: task_launch
    difficulty: 3
    description: Product launch decision with irreversible public commitment risk
    score_range: [0.0, 1.0]
  - id: task_crisis
    difficulty: 4
    description: Crisis response requiring mandatory irreversible action under time pressure
    score_range: [0.0, 1.0]
  - id: task_cascade
    difficulty: 5
    description: Multi-step resolution where premature action permanently locks all downstream steps
    score_range: [0.0, 1.0]
  - id: task_db_migration
    difficulty: 5
    description: Production schema migration with cascade mechanic grounded in real infrastructure operations (backup, dry-run, maintenance window, DDL apply, rollback, backfill, column drop)
    score_range: [0.0, 1.0]

environment:
  observation_type: text
  action_type: text
  multi_agent: false
  persistent_within_episode_state: true
  max_observation_tokens: 1800
  reward_range: [-0.5, 1.0]
  max_steps_per_episode: 15

reward_components:
  task_completion: 0.40
  prediction_accuracy: 0.30
  option_preservation: 0.20
  catastrophe_penalty: 0.10

training:
  recommended_model: meta-llama/Llama-3.2-3B-Instruct
  recommended_algorithm: grpo
  recommended_framework: unsloth
  episodes: 1500
  warmup_sft_episodes: 20
  gpu_hours: 7
  cost_usd: 20

novelty:
  - Within-episode persistent world state — no prior OpenEnv environment has this
  - R-level computed from world state at runtime, not static tag
  - Prediction accuracy as first-class reward component
  - Symmetric penalty on misclassification — over-caution punished equally to under-caution
  - Task 4 requires taking irreversible action correctly — proves no caution training