llm-quant/app/data/prompt_templates/department_base@1.1.0.json
2025-10-06 15:13:19 +08:00

31 lines
1.8 KiB
JSON
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

{
"department_base": {
"name": "部门基础模板",
"description": "审慎分析骨架(数据校验强化版)",
"template": "部门:{title}\n股票代码{ts_code}\n交易日{trade_date}\n\n【角色定位】\n- 角色说明:{description}\n- 行动守则:{instruction}\n\n【数据校验】\n1. 逐条确认提供的数据是否符合 expected schema缺失项需记录在 `risks`。\n2. 如出现冲突数据,请在 `signals` 中说明解决思路,并指出最可信的来源。\n\n【数据边界】\n- 可用字段:\n{data_scope}\n- 核心特征:\n{features}\n- 市场背景:\n{market_snapshot}\n- 追加数据:\n{supplements}\n\n【分析步骤】\n1. 评估数据完整度,必要时建议补充 `fetch_data` 的具体调用参数。\n2. 基于量化证据拆分 2-3 个关键支撑与潜在风险,注明对应字段。\n3. 提炼操作建议并给出可执行的风险对冲或观察指标。\n\n【输出要求】\n仅返回一个 JSON 对象,不要添加额外文本:\n{\n \"action\": \"BUY|BUY_S|BUY_M|BUY_L|SELL|HOLD\",\n \"confidence\": 0-1 之间的小数,\n \"summary\": \"一句话结论\",\n \"signals\": [\"字段+现象\", \"...\"],\n \"risks\": [\"字段+风险\", \"...\"]\n}\n如需说明未完成的数据请求请在 `risks` 中补充。",
"variables": [
"title",
"ts_code",
"trade_date",
"description",
"instruction",
"data_scope",
"features",
"market_snapshot",
"supplements"
],
"max_length": 4000,
"required_context": [
"ts_code",
"trade_date",
"features",
"market_snapshot"
],
"version": "1.1.0",
"metadata": {
"label": "quality_guard",
"notes": "强调数据校验与风险映射。"
},
"activate": false
}
}