fix: keep Cua foreground actions on the target window

This commit is contained in:
chenmingxuan committed 2026-10-18 21:02:49 +08:00
1 parent 889a951c9b
commit 6de0b1b276
13 files changed
+327 -31

No files matched your search

+36 -7
View File
@@ -235,7 +235,7 @@
"type": "integer"
},
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -275,7 +275,7 @@
"additionalProperties": false,
"properties": {
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -341,7 +341,7 @@
"additionalProperties": false,
"properties": {
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -380,7 +380,7 @@
"additionalProperties": false,
"properties": {
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -426,7 +426,7 @@
"additionalProperties": false,
"properties": {
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -485,7 +485,7 @@
"type": "string"
},
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -598,7 +598,7 @@
"type": "integer"
},
"delivery_mode": {
"description": "background (default) avoids raising the window; unsupported input is refused. Use foreground for Chromium/Brave keyboard input and scrolling within task scope. Inspect the returned state before retrying an uncertain action.",
"description": "background does not activate the window. foreground uses Cua bring_to_front before input and leaves the target foreground for subsequent rendering and evidence; it does not switch back to the user's previous app after each action.",
"enum": [
"background",
"foreground"
@@ -635,5 +635,34 @@
"readOnlyHint": false,
"idempotentHint": false
}
},
{
"name": "bring_to_front",
"description": "Activate the exact authorized window and leave it foreground across observations and actions. Use when a background browser body is blank or its page tree is missing. This changes the user foreground; it does not navigate, refresh, or repeat any business action. Read the returned fresh screenshot before continuing.",
"inputSchema": {
"type": "object",
"required": [
"pid",
"window_id"
],
"properties": {
"pid": {
"type": "integer",
"minimum": 1,
"maximum": 4294967295
},
"window_id": {
"type": "integer",
"minimum": 1
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": true,
"openWorldHint": false
}
}
]