fix(agent): solve_challenge authorization covers its child's coordinate steps
With only a browser.solve_challenge grant, the vision child run was denied browser.click_at, so the loop stopped after the first screenshot (REAL-2 task 4). Steps inside a run spawned by solve_challenge are now allowed; ancestors' allowlist and step budget still apply. Needs image rebuild. Co-Authored-By: Claude Opus 5.5 <[email protected]>
This commit is contained in:
1 parent
bd0e011748
commit
7dc7b1c5fa
3 files changed
+38
-1
No files matched your search
@@ -136,7 +136,7 @@ execute 类需要持续授权(`automation_grant`)或审批。元素引用只来
|
||||
- **证据**:每次截图(含动作后的截图)写 480 像素宽的 JPEG 缩略图到 `DATA_DIR/tmp/evidence/<id>.jpg`(0600,7 天后清理);
|
||||
能力输出只给引用 `evidence/<id>.jpg`,随工具结果摘要进 `agent_run_event`。图片数据不进 JSON 文本、不进操作账本。
|
||||
- **授权**:`click_at / type_at / scroll / solve_challenge` 由 `browser.interact` 的持续授权覆盖(也可单独授权);
|
||||
父会话白名单里有 `browser.solve_challenge` 即覆盖子流程用到的截图与坐标能力。坐标动作按调用区分幂等键,崩溃恢复不重放。
|
||||
父会话白名单里有 `browser.solve_challenge` 即覆盖子流程用到的截图与坐标能力;授权同理,solve_challenge 通过授权后,子流程(`spawn_reason = browser.solve_challenge`)内的坐标动作不再单独要持续授权。坐标动作按调用区分幂等键,崩溃恢复不重放。
|
||||
- 交给模型的截图参数可在 `browser_provider.config` 调:`screenshotMaxWidth`(≤1280)、`screenshotFormat`(`jpeg` / `png`)、
|
||||
`screenshotQuality`(20–95)。
|
||||
|
||||
|
||||
Reference in new issue
Block a user