#!/bin/bash
# 小规模测试：验证新的rewrite prompt是否降低E/T
# 10 profiles × 10 sessions = 100 sessions

echo "$(date '+%H:%M:%S') 启动 rag_rewrite 小规模测试 (新prompt)..."

cd /workspace/personalization-user-model

python collaborativeagents/scripts/run_experiments.py \
    --methods rag_rewrite \
    --datasets math-hard,bigcodebench \
    --n-profiles 10 \
    --n-sessions 10 \
    --max-turns 10 \
    --use-vllm \
    --vllm-agent-url http://localhost:8003/v1 \
    --vllm-user-url http://localhost:8004/v1 \
    --use-batch-processing \
    --batch-size 4 \
    --parallel-profiles 10 \
    --profile-path collaborativeagents/data/complex_profiles_v2/profiles_200.jsonl \
    --output-dir collaborativeagents/results/test_new_rewrite_10x10

echo "$(date '+%H:%M:%S') 测试完成"

# 自动分析结果
python3 << 'ANALYZE'
import json
import numpy as np

result_path = "collaborativeagents/results/test_new_rewrite_10x10"
import glob
results_file = glob.glob(f"{result_path}/*/rag_rewrite/results.json")

if results_file:
    with open(results_file[0]) as f:
        data = json.load(f)
    
    enforcements = sum(r["metrics"]["enforcement_count"] for r in data)
    turns = sum(r["metrics"]["total_turns"] for r in data)
    successes = sum(1 for r in data if r["metrics"]["task_success"])
    
    print(f"\n=== 新Rewrite Prompt测试结果 ===")
    print(f"Sessions: {len(data)}")
    print(f"Success Rate: {100*successes/len(data):.1f}%")
    print(f"E/T: {enforcements/turns:.4f}")
    print(f"(对比旧rewrite E/T: 0.194)")
else:
    print("结果文件未找到")
ANALYZE