iomgaa
75d7cffd27
按任务书 12 实现 src/flow：从账本现算下一步的纯函数、主循环、恢复入口、派模型任务和跑正式运行两个共用动作、冻结配置、基线、第零轮三个研究者阶段和入口分配，走到第 1 轮时停下。materials 导出 finalEntries、加 researcherId 和 StudyRecord。 审阅采纳两条：研究编号本机已用过时冻结前报错；docker run 没启动时写完结果就停下，不在本进程里无限起新编号。 eval/ 新增第零轮检验：起研究命令行、回放假模型、检验用 Jev 客户端、六问质量评估、16-real-1 回放、杀进程与两份同时跑。tsc 与 depcruise 也检查 eval/，新增 eval 只经 index.ts 用正式代码的规则。 Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
34 lines
1.0 KiB
JSON
34 lines
1.0 KiB
JSON
{
|
|
"studyId": "r0-eval",
|
|
"task": "tasks/circle_packing",
|
|
"models": {
|
|
"researchers": [
|
|
{ "provider": "iomgaa", "model": "glm-5.3", "thinking": "medium" },
|
|
{ "provider": "iomgaa", "model": "glm-5.3", "thinking": "medium" },
|
|
{ "provider": "iomgaa", "model": "glm-5.3", "thinking": "medium" }
|
|
],
|
|
"experimenter": { "provider": "iomgaa", "model": "glm-5.3", "thinking": "medium" },
|
|
"verifier": { "provider": "iomgaa", "model": "glm-5.3", "thinking": "medium" },
|
|
"jev": "jev-latest"
|
|
},
|
|
"proposalLimit": 1,
|
|
"batchLimit": 2,
|
|
"runs": 13,
|
|
"factorLimit": 3,
|
|
"maxRepairs": 1,
|
|
"lightChecks": { "maxCount": 2, "seconds": 5 },
|
|
"promptDir": "prompts",
|
|
"devEntry": false,
|
|
"flow": {
|
|
"preset": "full",
|
|
"roundZero": { "enabled": true, "discussions": 2 },
|
|
"firstPrediction": true,
|
|
"critique": true,
|
|
"ablation": { "enabled": true, "cellRule": "valueMinusCost" },
|
|
"batchRule": "bestExpected",
|
|
"openReserve": 0.1,
|
|
"knowledgeUse": 0.5,
|
|
"decay": 0.5
|
|
}
|
|
}
|