feat: add keyboard command for raw keyboard input (#521)

Adds `keyboard type` and `keyboard insertText` subcommands that
operate on the currently focused element without requiring a selector.

Essential for contenteditable editors (Lexical, ProseMirror, CodeMirror,
Monaco) where `type <selector>` doesn't trigger the editor's internal
event pipeline (beforeinput/DOM mutation).

- `keyboard type <text>` — page.keyboard.type() with real keystrokes
- `keyboard insertText <text>` — page.keyboard.insertText()

Note: `keyboard press` intentionally omitted — the existing top-level
`press` command already operates on current focus.

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
Provi
2026-02-23 09:44:08 -06:00
committed by GitHub
co-authored by Claude Opus 4.6
parent f10f3f6425
commit ad6e206a90
9 changed files with 186 additions and 5 deletions
+32
View File
@@ -263,6 +263,38 @@ pub fn parse_command(args: &[String], flags: &Flags) -> Result<Value, ParseError
})?;
Ok(json!({ "id": id, "action": "keyup", "key": key }))
}
"keyboard" => {
let sub = rest.first().ok_or_else(|| ParseError::MissingArguments {
context: "keyboard".to_string(),
usage: "keyboard <type|inserttext> <text>",
})?;
match *sub {
"type" => {
let text: String = rest[1..].join(" ");
if text.is_empty() {
return Err(ParseError::MissingArguments {
context: "keyboard type".to_string(),
usage: "keyboard type <text>",
});
}
Ok(json!({ "id": id, "action": "keyboard", "subaction": "type", "text": text }))
}
"inserttext" | "insertText" => {
let text: String = rest[1..].join(" ");
if text.is_empty() {
return Err(ParseError::MissingArguments {
context: "keyboard inserttext".to_string(),
usage: "keyboard inserttext <text>",
});
}
Ok(json!({ "id": id, "action": "keyboard", "subaction": "insertText", "text": text }))
}
_ => Err(ParseError::UnknownSubcommand {
subcommand: sub.to_string(),
valid_options: &["type", "inserttext"],
}),
}
}
// === Scroll ===
"scroll" => {
+43
View File
@@ -713,6 +713,11 @@ Global Options:
Examples:
agent-browser type "#search" "hello"
agent-browser type @e2 "additional text"
See Also:
For typing into contenteditable editors (Lexical, ProseMirror, etc.)
without a selector, use 'keyboard type' instead:
agent-browser keyboard type "# My Heading"
"##
}
"hover" => {
@@ -926,6 +931,42 @@ Examples:
agent-browser keyup Control
"##
}
"keyboard" => {
r##"
agent-browser keyboard - Raw keyboard input (no selector needed)
Usage: agent-browser keyboard <subcommand> <text>
Sends keyboard input to whatever element currently has focus.
Unlike 'type' which requires a selector, 'keyboard' operates on
the current focus essential for contenteditable editors like
Lexical, ProseMirror, CodeMirror, and Monaco.
Subcommands:
type <text> Type text character-by-character with real
key events (keydown, keypress, keyup per char)
inserttext <text> Insert text without key events (like paste)
Note: For key combos (Enter, Control+a), use the 'press' command
directly it already operates on the current focus.
Global Options:
--json Output as JSON
--session <name> Use specific session
Examples:
agent-browser keyboard type "Hello, World!"
agent-browser keyboard type "# My Heading"
agent-browser keyboard inserttext "pasted content"
Use Cases:
# Type into a Lexical/ProseMirror contenteditable editor:
agent-browser click "[contenteditable]"
agent-browser keyboard type "# My Heading"
agent-browser press Enter
agent-browser keyboard type "Some paragraph text"
"##
}
// === Scroll ===
"scroll" => {
@@ -1958,6 +1999,8 @@ Core Commands:
type <sel> <text> Type into element
fill <sel> <text> Clear and fill
press <key> Press key (Enter, Tab, Control+a)
keyboard type <text> Type text with real keystrokes (no selector)
keyboard inserttext <text> Insert text without key events
hover <sel> Hover element
focus <sel> Focus element
check <sel> Check checkbox