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/电影周度票房.md

@@ -0,0 +1,125 @@
+# 电影周度票房
+
+**文档ID**: 114
+**原始链接**: https://tushare.pro/document/2?doc_id=114
+
+---
+
+## 电影周度票房
+
+接口：bo_weekly描述：获取周度票房数据数据更新：本周更新上一周数据数据历史： 数据从2008年第一周开始，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（每周一日期，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>avg_price</td>
+<td>float</td>
+<td>Y</td>
+<td>平均票价</td>
+</tr>
+<tr>
+<td>week_amount</td>
+<td>float</td>
+<td>Y</td>
+<td>当周票房（万）</td>
+</tr>
+<tr>
+<td>total</td>
+<td>float</td>
+<td>Y</td>
+<td>累计票房（万）</td>
+</tr>
+<tr>
+<td>list_day</td>
+<td>int</td>
+<td>Y</td>
+<td>上映天数</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>up_ratio</td>
+<td>float</td>
+<td>Y</td>
+<td>环比变化 （%）</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_weekly(date='20181008')
+```
+
+数据示例
+
+```
+    date      name  avg_price  week_amount    total  list_day  p_pc  \
+0  20181008  无双       36.0      25640.0  93705.0        15    12   
+1  20181008  影       36.0      10277.0  55406.0        15     8   
+2  20181008  找到你       32.0       9318.0  15234.0        10    11   
+3  20181008  李茶的姑妈       35.0       5823.0  57263.0        15     6   
+4  20181008  胖子行动队       34.0       3875.0  23683.0        15     7   
+5  20181008  嗝嗝老师       30.0       2917.0   2941.0         3    10   
+6  20181008  悲伤逆流成河       34.0       2475.0  33532.0        24     7   
+7  20181008  超能泰坦       30.0       1202.0   1202.0         3     4   
+8  20181008  阿凡提之奇缘历险       34.0        675.0   7251.0        14     5   
+```