@ui-tars/sdk
Version:
A powerful cross-platform(ANY device/platform) toolkit for building GUI automation agents for UI-TARS
78 lines (69 loc) • 2.93 kB
JavaScript
/**
* Copyright (c) 2025 Bytedance, Inc. and its affiliates.
* SPDX-License-Identifier: Apache-2.0
*/
const MAX_SNAPSHOT_ERR_CNT = 10;
const DEFAULT_FACTORS = [
1000,
1000
];
const MAX_PIXELS = 1058400;
const SYSTEM_PROMPT = `You are a GUI agent. You are given a task and your action history, with screenshots. You need to perform the next action to complete the task.
## Output Format
\`\`\`
Thought: ...
Action: ...
\`\`\`
## Action Space
click(start_box='[x1, y1, x2, y2]')
left_double(start_box='[x1, y1, x2, y2]')
right_single(start_box='[x1, y1, x2, y2]')
drag(start_box='[x1, y1, x2, y2]', end_box='[x3, y3, x4, y4]')
hotkey(key='')
type(content='') #If you want to submit your input, use "\\n" at the end of \`content\`.
scroll(start_box='[x1, y1, x2, y2]', direction='down or up or right or left')
wait() #Sleep for 5s and take a screenshot to check for any changes.
finished()
call_user() # Submit the task and call the user when the task is unsolvable, or when you need the user's help.
## Note
- Write a small plan and finally summarize your next action (with its target element) in one sentence in \`Thought\` part.
## User Instruction
`;
const SYSTEM_PROMPT_TEMPLATE = `You are a GUI agent. You are given a task and your action history, with screenshots. You need to perform the next action to complete the task.
## Output Format
\`\`\`
Thought: ...
Action: ...
\`\`\`
## Action Space
{{action_spaces_holder}}
## Note
- Write a small plan and finally summarize your next action (with its target element) in one sentence in \`Thought\` part.
## User Instruction
`;
const DEFAULT_ACTION_SPACES = `
click(start_box='[x1, y1, x2, y2]')
left_double(start_box='[x1, y1, x2, y2]')
right_single(start_box='[x1, y1, x2, y2]')
drag(start_box='[x1, y1, x2, y2]', end_box='[x3, y3, x4, y4]')
hotkey(key='')
type(content='') #If you want to submit your input, use "\\n" at the end of \`content\`.
scroll(start_box='[x1, y1, x2, y2]', direction='down or up or right or left')
wait() #Sleep for 5s and take a screenshot to check for any changes.
finished()
call_user() # Submit the task and call the user when the task is unsolvable, or when you need the user's help.
`;
const DEFAULT_CONTEXT = {
logger: console,
factors: DEFAULT_FACTORS,
systemPrompt: SYSTEM_PROMPT
};
var constants_INTERNAL_ACTION_SPACES_ENUM = /*#__PURE__*/ function(INTERNAL_ACTION_SPACES_ENUM) {
INTERNAL_ACTION_SPACES_ENUM["CALL_USER"] = "call_user";
INTERNAL_ACTION_SPACES_ENUM["MAX_LOOP"] = "max_loop";
INTERNAL_ACTION_SPACES_ENUM["ERROR_ENV"] = "error_env";
INTERNAL_ACTION_SPACES_ENUM["FINISHED"] = "finished";
return INTERNAL_ACTION_SPACES_ENUM;
}({});
export { DEFAULT_ACTION_SPACES, DEFAULT_CONTEXT, DEFAULT_FACTORS, constants_INTERNAL_ACTION_SPACES_ENUM as INTERNAL_ACTION_SPACES_ENUM, MAX_PIXELS, MAX_SNAPSHOT_ERR_CNT, SYSTEM_PROMPT, SYSTEM_PROMPT_TEMPLATE };
//# sourceMappingURL=constants.mjs.map