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
2026-08-28 15:02:39 +08:00
parent 7aaa5a2d01
commit 7701282897
23 changed files with 855 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
packages/dsh-plugin-browserskill/src/tools.ts
+6 -3
View File
@@ -497,7 +497,8 @@ export function registerTools(deps: ToolDeps): () => void {
? "Capture an indented aria-tree snapshot of the session's active tab. Interactive elements " +
"carry @eN refs for browser_click / browser_fill. Prefer browser_observe for a richer semantic view."
: "Produce a semantic VOM observation of the session's active tab (roles, states, perception " +
"probes) with @eN refs for browser_click / browser_fill. Read-only: never submits input.";
"probes) with @eN refs. Visual surface refs are screenshot-only; DOM refs support interaction. " +
"Read-only: never submits input.";
register(
defineTool({
name,
@@ -760,12 +761,14 @@ export function registerTools(deps: ToolDeps): () => void {
name: "browser_screenshot",
description:
"Capture a PNG screenshot of the session's active tab, or crop to a snapshot ref element. " +
"Returns the image itself when the deployment supports image input, otherwise a file path.",
"This is the supported operation for visual surface refs emitted by browser_observe. Returns " +
"the image itself when the deployment supports image input, otherwise a file path.",
parameters: {
session: SESSION_PARAM,
ref: {
type: "string",
description: "Snapshot ref (@e3) from the last snapshot/observe; crops to that element.",
description:
"Ref (@e3) from the last snapshot/observe; crops to that DOM element or visual surface.",
},
},
output: {