test(scenario): cover multi-image page generation end to end

The read_image poisoning fix had no end-to-end guard because scenarios could only send text. Add an upload_images step that renders and uploads visually distinct images, let chat steps attach them the same way the WeChat channel does, and assert the generated page actually embeds every upload. Co-authored-by: Cursor <cursoragent@cursor.com>
2026-08-22 10:50:23 +08:00
parent ef4ce12bbf
commit b93c92a3e2
6 changed files with 212 additions and 2 deletions
@@ -50,6 +50,16 @@ node --test tkmind-proxy.test.mjs chat-image-turn-scope.test.mjs wechat-mp.test.
 npm run verify:h5-session-patches
 ```

+端到端（需本地 Portal 8081 + goosed）：
+
+```bash
+node scripts/run-scenario-test.mjs --scenario image-theme-page
+```
+
+该场景上传 4 张几何图、要求做成主题页面，断言页面生成、公网 200、4 张图全部嵌入，
+并禁止回复里出现 `unknown variant`。2026-08-22 首次通过时会话内 `read_image` 调用为 0、
+持久化工具图片块为 0，工具序列是 `load_skill → write_file → read_file`。
+
 ## 相关代码与用例

 | 位置 | 作用 |