chore: initial commit — unified project repo

Merged code repo (CompanionGuard-RL) into single project-level git.
Reorganized root: docs/, reference/, experiments/, tmp/active|archives/.
Gitignored: data/, checkpoints/, .venv, experiment logs, tmp/archives.

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

code/configs/detector_config.yaml

@@ -0,0 +1,51 @@
+model:
+  name: "hfl/chinese-macbert-large"
+  hidden_size: 1024
+  num_heads: 8
+  dropout: 0.1
+  use_lora: false
+
+data:
+  train_path: "data/processed/CompanionRisk-Bench/train.jsonl"
+  val_path:   "data/processed/CompanionRisk-Bench/dev.jsonl"
+  test_path:  "data/processed/CompanionRisk-Bench/test.jsonl"
+  max_persona_len:   128
+  max_context_len:   512
+  max_response_len:  256
+  max_history_turns: 5
+  num_workers: 0            # 0 for Windows (avoids multiprocessing issues); set to 4 on Linux
+
+training:
+  epochs: 10
+  per_gpu_batch_size: 16    # single GPU: 16; 4 GPUs: use 32 (effective 128)
+  gradient_accumulation_steps: 2   # effective_batch = 16 × 1 GPU × 2 = 32
+  lr: 2e-5
+  warmup_steps: 100
+  weight_decay: 0.01
+  gradient_clip: 1.0
+  eval_steps: 100           # global steps between validation runs
+  mixed_precision: "bf16"   # RTX 5090: bf16; RTX 30xx/40xx: fp16; CPU-only: no
+  seed: 42
+
+loss_weights:
+  binary:  1.0
+  level:   1.0
+  primary: 1.0
+  fine:    1.0     # 下次训练建议提升到 2.0，配合 fine_training 选项
+
+# Fine-grained label training options（下次训练时开启，当前 best.pt 不受影响）
+fine_training:
+  use_pos_weight: false   # 改为 true 开启 pos_weight（下次训练）
+  risky_only:     false   # 改为 true 开启（下次训练）
+
+evaluation:
+  binary_threshold: 0.5
+  fine_threshold:   0.4
+
+logging:
+  project:   "CompanionGuard-RL"
+  run_name:  "detector-macbert-v1"
+  use_wandb: false          # set true if wandb is configured
+
+output:
+  checkpoint_dir: "checkpoints/detector"