feat: initial CompanionGuard-RL framework

Two-module pipeline for AI companion safety:
- Module B: context-aware risk detector with CrossAttention fusion
- Module C: PPO-based adaptive intervention policy

Includes CompanionRisk Taxonomy (10 primary + 14 fine-grained labels),
dataset generation/annotation pipeline, training scripts, and eval suite.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.gitignore

@@ -0,0 +1,35 @@
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+.eggs/
+
+# Virtual environments
+.venv/
+venv/
+env/
+
+# Data (raw and processed — do not commit large datasets)
+data/raw/
+data/processed/
+
+# Model checkpoints
+checkpoints/
+
+# Experiment outputs
+experiments/eval_results.json
+wandb/
+
+# Editor
+.idea/
+.vscode/
+*.swp
+
+# OS
+.DS_Store
+Thumbs.db
+
+# API keys
+.env
+*.env