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

- 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>

runtime/skills/tushare-finance/reference/接口文档/港股通每日成交统计.md

@@ -0,0 +1,127 @@
+# 港股通每日成交统计
+
+**文档ID**: 196
+**原始链接**: https://tushare.pro/document/2?doc_id=196
+
+---
+
+## 港股通每日成交统计
+
+接口：ggt_daily描述：获取港股通每日成交信息，数据从2014年开始限量：单次最大1000，总量数据不限制积分：用户积2000积分可调取，5000积分以上频次相对较高，请自行提高积分，具体请参阅积分获取办法
+
+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>trade_date</td>
+<td>str</td>
+<td>N</td>
+<td>交易日期 （格式YYYYMMDD，下同。支持单日和多日输入）</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>trade_date</td>
+<td>str</td>
+<td>Y</td>
+<td>交易日期</td>
+</tr>
+<tr>
+<td>buy_amount</td>
+<td>float</td>
+<td>Y</td>
+<td>买入成交金额（亿元）</td>
+</tr>
+<tr>
+<td>buy_volume</td>
+<td>float</td>
+<td>Y</td>
+<td>买入成交笔数（万笔）</td>
+</tr>
+<tr>
+<td>sell_amount</td>
+<td>float</td>
+<td>Y</td>
+<td>卖出成交金额（亿元）</td>
+</tr>
+<tr>
+<td>sell_volume</td>
+<td>float</td>
+<td>Y</td>
+<td>卖出成交笔数（万笔）</td>
+</tr>
+</tbody></table>
+接口示例
+
+```
+
+pro = ts.pro_api()
+
+#获取单日全部统计
+df = pro.ggt_daily(trade_date='20190625')
+
+#获取多日统计信息
+df = pro.ggt_daily(trade_date='20190925,20180924,20170925')
+
+#获取时间段统计信息
+df = pro.ggt_daily(start_date='20180925', end_date='20190925)
+```
+
+数据示例
+
+```
+    trade_date  buy_amount  buy_volume  sell_amount  sell_volume
+0     20190925       31.22        5.54        27.07         4.55
+1     20190924       37.69        5.53        39.14         6.13
+2     20190923       26.69        4.43        31.50         5.01
+3     20190920       35.62        6.16        33.41         5.49
+4     20190919       31.80        5.83        29.34         5.24
+5     20190918       26.58        5.27        28.93         6.14
+6     20190917       29.92        5.76        32.70         6.30
+7     20190916       44.19        7.78        50.91         8.97
+8     20190910       30.79        6.04        32.89         5.99
+9     20190909       35.48        7.01        34.05         6.44
+10    20190906       39.46        6.98        29.47         6.07
+11    20190905       57.00       10.46        37.84         7.31
+12    20190904       49.68        8.43        43.17         6.17
+13    20190903       33.44        6.46        23.18         4.73
+14    20190902       43.02        6.91        28.06         5.64
+15    20190830       35.94        6.51        26.58         6.10
+16    20190829       39.11        6.89        24.95         4.60
+17    20190828       39.04        7.46        27.54         5.09
+18    20190827       44.36        9.44        23.12         4.84
+19    20190826       55.89        9.23        22.58         4.40
+20    20190823       33.91        6.28        18.83         4.66
+21    20190822       38.21        7.38        19.00         4.38
+22    20190821       35.38        6.42        20.39         3.77
+```