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/电影月度票房.md

@@ -0,0 +1,126 @@
+# 电影月度票房
+
+**文档ID**: 113
+**原始链接**: https://tushare.pro/document/2?doc_id=113
+
+---
+
+## 电影月度票房
+
+接口：bo_monthly描述：获取电影月度票房数据数据更新：本月更新上一月数据数据历史： 数据从2008年1月1日开始，超过10年历史数据。数据权限：用户需要至少500积分才可以调取，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>date</td>
+<td>str</td>
+<td>Y</td>
+<td>日期（每月1号，格式YYYYMMDD）</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>date</td>
+<td>str</td>
+<td>Y</td>
+<td>日期</td>
+</tr>
+<tr>
+<td>name</td>
+<td>str</td>
+<td>Y</td>
+<td>影片名称</td>
+</tr>
+<tr>
+<td>list_date</td>
+<td>str</td>
+<td>Y</td>
+<td>上映日期</td>
+</tr>
+<tr>
+<td>avg_price</td>
+<td>float</td>
+<td>Y</td>
+<td>平均票价</td>
+</tr>
+<tr>
+<td>month_amount</td>
+<td>float</td>
+<td>Y</td>
+<td>当月票房（万）</td>
+</tr>
+<tr>
+<td>list_day</td>
+<td>int</td>
+<td>Y</td>
+<td>月内天数</td>
+</tr>
+<tr>
+<td>p_pc</td>
+<td>int</td>
+<td>Y</td>
+<td>场均人次</td>
+</tr>
+<tr>
+<td>wom_index</td>
+<td>float</td>
+<td>Y</td>
+<td>口碑指数</td>
+</tr>
+<tr>
+<td>m_ratio</td>
+<td>float</td>
+<td>Y</td>
+<td>月度占比（%）</td>
+</tr>
+<tr>
+<td>rank</td>
+<td>int</td>
+<td>Y</td>
+<td>排名</td>
+</tr>
+</tbody></table>
+接口使用
+
+```
+pro = ts.pro_api()
+#或者
+#pro = ts.pro_api('your token')
+
+df = pro.bo_monthly(date='20180901')
+```
+
+数据示例
+
+```
+                date       name   list_date  avg_price  month_amount  list_day  p_pc  \
+0   20180901  碟中谍6：全面瓦解  2018-08-31       37.0      104316.0        30    14   
+1   20180901  反贪风暴3          2018-09-14       36.0       40473.0        17    11   
+2   20180901  黄金兄弟           2018-09-21       35.0       23242.0        10    14   
+3   20180901  蚁人2：黄蜂女现身  2018-08-24       35.0       14641.0        30     8   
+4   20180901  悲伤逆流成河       2018-09-21       34.0       14054.0        10    14   
+5   20180901  阿尔法：狼伴归途   2018-09-07       34.0       11298.0        24     7   
+6   20180901  江湖儿女           2018-09-21       34.0        5373.0        10     8   
+7   20180901  快把我哥带走       2018-08-17       32.0        5365.0        30     7   
+8   20180901  镰仓物语           2018-09-14       32.0        4509.0        17     6   
+9   20180901  大闹西游           2018-09-22       34.0        3419.0         9    10   
+```