hansjone/oclaw
1
0
Fork 0
mirror of https://github.com/hansjone/oclaw.git synced 2026-10-20 11:13:26 +08:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: multimodal image clients, workspaces, Tushare skill, test fixes

Browse source 
- Replace monolithic image_message_client with HTTP/OCR/legacy modules; tighten OpenAI transport + tool schemas for multimodal downgrade to OCR specialist path.
- Add image/stock workspace prompts (META/SOUL/ROLE_SYSTEM); register experts; tweak specialist agent/direct loop/query_image_attachment.
- Add bundled runtime/skills/tushare-finance (references, api_client, SKILL metadata).
- Document OCR-related env vars; admin chat tweaks; README; weixin_install Ensure-OfficialPluginRuntimeDeps helper.
- Tests: multimodal downgrade + OCR coverage, strict tool pairing in attachment replay guard, workspace contract skips _internal/_system dirs, router/trace/prompt guards.

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
oliver 2026-05-10 04:41:42 +08:00
parent 6307ade480
commit d1bcc4debe
266 changed files with 57024 additions and 839 deletions
Download patch file Download diff file Expand all files Collapse all files

155
runtime/skills/tushare-finance/reference/接口文档/每日筹码及胜率.md Normal file
View file

@ -0,0 +1,155 @@
# 每日筹码及胜率
**文档ID**: 293
**原始链接**: https://tushare.pro/document/2?doc_id=293
---
## 每日筹码及胜率
接口：cyq_perf描述：获取A股每日筹码平均成本和胜率情况，每天18~19点左右更新，数据从2018年开始来源：Tushare社区限量：单次最大5000条，可以分页或者循环提取积分：5000积分每天20000次，10000积分每天200000次，15000积分每天不限总量
输入参数
<table>
<thead>
<tr>
<th>名称</th>
<th>类型</th>
<th>必选</th>
<th>描述</th>
</tr>
</thead>
<tbody>
<tr>
<td>ts_code</td>
<td>str</td>
<td>Y</td>
<td>股票代码</td>
</tr>
<tr>
<td>trade_date</td>
<td>str</td>
<td>N</td>
<td>交易日期（YYYYMMDD）</td>
</tr>
<tr>
<td>start_date</td>
<td>str</td>
<td>N</td>
<td>开始日期</td>
</tr>
<tr>
<td>end_date</td>
<td>str</td>
<td>N</td>
<td>结束日期</td>
</tr>
</tbody>
</table>
输出参数
<table>
<thead>
<tr>
<th>名称</th>
<th>类型</th>
<th>默认显示</th>
<th>描述</th>
</tr>
</thead>
<tbody>
<tr>
<td>ts_code</td>
<td>str</td>
<td>Y</td>
<td>股票代码</td>
</tr>
<tr>
<td>trade_date</td>
<td>str</td>
<td>Y</td>
<td>交易日期</td>
</tr>
<tr>
<td>his_low</td>
<td>float</td>
<td>Y</td>
<td>历史最低价</td>
</tr>
<tr>
<td>his_high</td>
<td>float</td>
<td>Y</td>
<td>历史最高价</td>
</tr>
<tr>
<td>cost_5pct</td>
<td>float</td>
<td>Y</td>
<td>5分位成本</td>
</tr>
<tr>
<td>cost_15pct</td>
<td>float</td>
<td>Y</td>
<td>15分位成本</td>
</tr>
<tr>
<td>cost_50pct</td>
<td>float</td>
<td>Y</td>
<td>50分位成本</td>
</tr>
<tr>
<td>cost_85pct</td>
<td>float</td>
<td>Y</td>
<td>85分位成本</td>
</tr>
<tr>
<td>cost_95pct</td>
<td>float</td>
<td>Y</td>
<td>95分位成本</td>
</tr>
<tr>
<td>weight_avg</td>
<td>float</td>
<td>Y</td>
<td>加权平均成本</td>
</tr>
<tr>
<td>winner_rate</td>
<td>float</td>
<td>Y</td>
<td>胜率</td>
</tr>
</tbody>
</table>
接口用法
```
pro = ts.pro_api()
df = pro.cyq_perf(ts_code='600000.SH', start_date='20220101', end_date='20220429')
```
数据样例
```
ts_code trade_date his_low his_high cost_5pct cost_95pct weight_avg winner_rate
0 600000.SH 20220429 0.72 12.16 8.18 11.34 9.76 3.52
1 600000.SH 20220428 0.72 12.16 8.24 11.34 9.76 3.08
2 600000.SH 20220427 0.72 12.16 8.30 11.34 9.76 1.71
3 600000.SH 20220426 0.72 12.16 8.34 11.34 9.76 2.02
4 600000.SH 20220425 0.72 12.16 8.36 11.34 9.77 1.44
.. ... ... ... ... ... ... ... ...
72 600000.SH 20220110 0.72 12.16 8.60 11.36 9.89 7.62
73 600000.SH 20220107 0.72 12.16 8.60 11.36 9.89 7.59
74 600000.SH 20220106 0.72 12.16 8.60 11.36 9.89 3.92
75 600000.SH 20220105 0.72 12.16 8.60 11.36 9.89 5.65
76 600000.SH 20220104 0.72 12.16 8.60 11.36 9.89 3.93
```