#!/bin/bash
# 任务2a 主循环：6 模型 × verify，串行执行
# 分批：batch1 = DS-Flash, DS-Pro, GLM-5.3（先出代表结果）
# 需在 evalharness 环境下运行。凭据走环境变量，不再硬编码：
#   export FP_API_KEY=sk-xxxx    # 或复用 OPENAI_API_KEY
cd "$(dirname "$0")"

run_one() {
  local mode=$1 model=$2 ref=$3 name=$4
  local key="${FP_API_KEY:-${OPENAI_API_KEY:-}}"
  local api="${FP_API_URL:-https://api.vectron.meta-stone.com/v1}"
  local eb="${FP_EXTRA_BODY:-{\"chat_template_kwargs\":{\"enable_thinking\":false}}}"
  if [ -z "$key" ]; then echo "ERROR: 未设置 FP_API_KEY/OPENAI_API_KEY，跳过 $name" >&2; return 1; fi
  mkdir -p /tmp/bfd/$name
  echo "=== START $name $mode $(date +%H:%M) ==="
  python3 run_fp_fusion.py --api-url "$api" --model "$model" \
    --mode "$mode" --d-samples 25 --baseline-samples 5 --timeout 90 \
    --d-concurrency 1 --text-concurrency 1 \
    --api-key "$key" --extra-body "$eb" --reference "$ref" \
    --report-path /tmp/bfd/$name/${mode}.json > /tmp/bfd/$name/${mode}.log 2>&1
  echo "=== END $name $mode exit=$? $(date +%H:%M) ==="
}

R="$(pwd)/references"

run_one verify DeepSeek/DeepSeek-V4-Flash      $R/deepseek_v4_flash_fusion_reference.json     deepseek_v4_flash
run_one verify DeepSeek/DeepSeek-V4-Pro        $R/deepseek_v4_pro_fusion_reference.json       deepseek_v4_pro
run_one verify ZhipuAi/GLM-5.3                 $R/glm53_fusion_reference.json                glm_53
run_one verify DeepSeek/DeepSeek-V4-Flash-0731 $R/deepseek_v4_flash_0731_fusion_reference.json deepseek_v4_flash_0731
run_one verify ZhipuAi/GLM-5.2                 $R/glm52_vectron_fusion_reference.json        glm_52
run_one verify MoonshotAi/Kimi-K3              $R/kimi_k3_fusion_reference.json              kimi_k3