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>

scripts/annotate_data.py

@@ -0,0 +1,81 @@
+"""
+Step 2: LLM judge pre-annotation.
+
+Usage:
+  python scripts/annotate_data.py --input data/raw/generated.jsonl \
+                                   --output data/processed/annotated.jsonl \
+                                   --config configs/data_generation.yaml
+"""
+
+import argparse
+import json
+import yaml
+import random
+from pathlib import Path
+from src.data.llm_judge import LLMJudge
+from src.data.dataset import load_jsonl
+
+
+def split_dataset(samples, train_ratio=0.8, val_ratio=0.1, seed=42):
+    random.seed(seed)
+    random.shuffle(samples)
+    n = len(samples)
+    n_train = int(n * train_ratio)
+    n_val = int(n * val_ratio)
+    return (
+        samples[:n_train],
+        samples[n_train: n_train + n_val],
+        samples[n_train + n_val:],
+    )
+
+
+def save_jsonl(samples, path):
+    Path(path).parent.mkdir(parents=True, exist_ok=True)
+    with open(path, "w", encoding="utf-8") as f:
+        for s in samples:
+            f.write(json.dumps(s, ensure_ascii=False) + "\n")
+    print(f"Saved {len(samples)} samples → {path}")
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--input", required=True)
+    parser.add_argument("--output", default="data/processed/annotated.jsonl")
+    parser.add_argument("--config", default="configs/data_generation.yaml")
+    parser.add_argument("--skip-annotation", action="store_true",
+                        help="Skip LLM annotation (use existing labels)")
+    args = parser.parse_args()
+
+    with open(args.config) as f:
+        cfg = yaml.safe_load(f)
+
+    samples = load_jsonl(args.input)
+    print(f"Loaded {len(samples)} samples from {args.input}")
+
+    if not args.skip_annotation:
+        judge = LLMJudge(
+            api_type=cfg["api"]["type"],
+            model=cfg["annotation"]["judge_model"],
+        )
+        samples = judge.annotate_batch(samples, output_path=args.output)
+    else:
+        save_jsonl(samples, args.output)
+
+    split_cfg = cfg.get("split", {"train": 0.8, "val": 0.1, "test": 0.1, "seed": 42})
+    train, val, test = split_dataset(
+        samples,
+        train_ratio=split_cfg["train"],
+        val_ratio=split_cfg["val"],
+        seed=split_cfg.get("seed", 42),
+    )
+
+    base = Path(args.output).parent
+    save_jsonl(train, base / "train.jsonl")
+    save_jsonl(val, base / "val.jsonl")
+    save_jsonl(test, base / "test.jsonl")
+
+    print(f"Split: train={len(train)}, val={len(val)}, test={len(test)}")
+
+
+if __name__ == "__main__":
+    main()