draco437/mirage

How draco437/mirage works

MIRAGE is a prototype adaptive social-skills platform: a therapist manages children and sessions, a Unity VR client streams session signals, and backend analysis can adapt the scene while reporting live results. The principal path runs from session telemetry through feature extraction, engagement inference and adaptation rules to Unity; therapists can also review analytics and override settings. The React entry point shown is still the Create React App placeholder, so it does not substantiate a dashboard UI. Some backend links are supported by the source index or module documentation rather than complete excerpts.

Main entry points: tasks.py Analysis Tasks · consumers.py Session Consumers · views.py REST API · routing.py WebSocket Routes

Components 18

Therapist API

REST API backend/core/views.py
Request Validation backend/core/serializers.py
Web App Placeholder frontend/src/App.js

Session Runtime

WebSocket Auth backend/core/auth.py
WebSocket Routes backend/core/routing.py
Session Consumers backend/core/consumers.py

Adaptive Analysis

Analysis Tasks backend/ml_engine/tasks.py
Feature Extraction backend/ml_engine/features.py
Emotion Model backend/ml_engine/emotion_model.py
Engagement Model backend/ml_engine/engagement_model.py
Adaptation Rules backend/ml_engine/adaptation_rules.py
Signal Fusion backend/ml_engine/fusion.py
Signal Definitions backend/ml_engine/signals.py

Session Data

MongoDB backend/db.py

Model Training

Synthetic Data backend/ml_training/generate_synthetic.py
Engagement Training backend/ml_training/train_engagement_rf.py

Other components

Therapist
Unity VR Client

Connections 22

Therapist → REST API: manages sessions backend/core/views.py
REST API → Request Validation: validates requests backend/core/views.py
REST API → MongoDB: reads and writes backend/core/views.py
Unity VR Client → WebSocket Routes: opens session socket backend/core/routing.py
WebSocket Routes → Session Consumers: routes packets backend/core/routing.py
Session Consumers → WebSocket Auth: checks connection auth
Session Consumers → Request Validation: validates packets backend/core/consumers.py
Session Consumers → MongoDB: stores session events backend/core/consumers.py
Session Consumers → Analysis Tasks: triggers analysis backend/ml_engine/tasks.py
Analysis Tasks → MongoDB: reads and writes readings backend/ml_engine/tasks.py
Analysis Tasks → Emotion Model: predicts emotion backend/ml_engine/tasks.py
Analysis Tasks → Feature Extraction: builds window features backend/ml_engine/tasks.py
Analysis Tasks → Engagement Model: predicts engagement backend/ml_engine/tasks.py
Analysis Tasks → Adaptation Rules: decides scene changes backend/ml_engine/tasks.py
Analysis Tasks → Unity VR Client: pushes scene settings backend/ml_engine/tasks.py
Analysis Tasks → Therapist: pushes live updates backend/ml_engine/tasks.py
REST API → Therapist: returns analytics backend/core/views.py
Therapist → WebSocket Routes: opens dashboard socket backend/core/routing.py
Signal Fusion → Signal Definitions: uses signals backend/ml_engine/fusion.py
Synthetic Data → Feature Extraction: uses feature schema backend/ml_training/generate_synthetic.py
Engagement Training → Synthetic Data: uses generated data backend/ml_training/train_engagement_rf.py
Engagement Training → Feature Extraction: uses feature schema backend/ml_training/train_engagement_rf.py

Drawn by GitDiagram on November 12, 2026 from the repository's file tree, README and source files. Read as Markdown ·