figmar/BrowserSkill
1
0
Fork 0
mirror of https://github.com/Tencent/BrowserSkill.git synced 2026-09-10 13:01:23 +08:00
Code Issues Packages Projects Releases Wiki Activity

feat(vom): vom can distinguish important canvas area

Browse Source
This commit is contained in:
Ljy-0827
2026-09-08 10:54:33 +08:00
parent 3c5f838c56
commit ff1216526d
23 changed files with 861 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
apps/extension/src/tools/__tests__/interaction.test.ts
+23
View File
@@ -123,6 +123,29 @@ describe("handleClick", () => {
expect(fake.cdp.send).not.toHaveBeenCalled();
});
it("rejects screenshot-only visual surface refs before issuing CDP calls", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");
ctx.refStore.set("e3", 1234, {
tabId: 4,
kind: "surface",
capabilities: ["screenshot"],
});
const fake = makeFakeCdp({});
const res = await handleClick(
sm,
{ session_id: "aa11", ref: "@e3" },
{ cdp: fake.cdp, tabsApi: fake.tabsApi },
);
expect(res).toMatchObject({
code: "permission_denied",
data: { reason: "ref_capability_denied", required_capability: "interact" },
});
expect(fake.cdp.send).not.toHaveBeenCalled();
});
it("clicks by ref, computes the quad centre, dispatches three mouse events", async () => {
const sm = new SessionManager({ agentWindow: fakeAgentWindow([100]) });
const ctx = await sm.start("aa11");