mirror of
https://github.com/HKUDS/nanobot.git
synced 2026-08-10 14:28:38 +03:00
95160a304d
Adds two opt-in agent tools for controlling a computer: - computer_use: pixel-based (screenshot + mouse/keyboard) via a desktop (pyautogui) or browser (playwright) backend. - browser: DOM/accessibility-based web automation (act by element ref), reliable across ANY tool-calling model, not just vision/CU-trained ones. Core enabler in the runner: a tool may return image content blocks, which are split out and delivered to the model as a follow-up user message (_split_tool_result_media), so screenshots reach any vision provider (e.g. via OpenRouter/openai-compat) without provider-specific code. Both tools are OFF by default (tools.computerUse.enable / tools.browser.enable), are not exposed to subagents, and the browser tool supports an allowed_domains allowlist. Heavy deps (pyautogui/pillow/playwright) are an optional [computer-use] extra. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
11 lines
301 B
HTML
11 lines
301 B
HTML
<!doctype html>
|
|
<html><head><meta charset="utf-8"><title>Dashboard</title></head>
|
|
<body>
|
|
<h1 id="welcome"></h1>
|
|
<p>You are signed in.</p>
|
|
<script>
|
|
var u = new URLSearchParams(location.search).get('user') || '';
|
|
document.getElementById('welcome').textContent = 'Welcome ' + u;
|
|
</script>
|
|
</body></html>
|