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_server.yaml

@@ -0,0 +1,54 @@
+model:
+  name: "/root/siton-data-740d234e02d749f08fe5347b0c74c49f/zsy/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: 4            # Linux server: 4 workers; Windows: use 0
+
+training:
+  epochs: 10
+  per_gpu_batch_size: 16    # 4 GPUs × 16 × accum 2 = effective batch 128
+  gradient_accumulation_steps: 2
+  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 native bf16
+  seed: 42
+
+loss_weights:
+  binary:  1.0
+  level:   1.0
+  primary: 1.0
+  fine:    2.0     # ↑ 2.0: 加强细粒度标签损失权重（配合 fine_training 开启）
+
+# Fine-grained label training options（下次训练时开启，当前 best.pt 不受影响）
+# 两项均开启可显著改善 fine_macro_f1：
+#   use_pos_weight: 对 Romanticization/CoRumination 等稀有标签设置 ~25 倍正样本权重
+#   risky_only:     只在 y_risk=1 的样本上计算 fine loss，避免 safe 样本教模型预测全负
+fine_training:
+  use_pos_weight: true    # ✓ 开启：对稀有 fine 标签设置 pos_weight（max 30）
+  risky_only:     true    # ✓ 开启：只在 y_risk=1 样本上计算 fine loss
+
+evaluation:
+  binary_threshold: 0.5
+  fine_threshold:   0.4
+
+logging:
+  project:   "CompanionGuard-RL"
+  run_name:  "detector-macbert-4gpu"
+  use_wandb: false
+
+output:
+  checkpoint_dir: "checkpoints/detector"