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>
16 lines
551 B
HTML
16 lines
551 B
HTML
<!doctype html>
|
|
<html><head><meta charset="utf-8"><title>Cart</title></head>
|
|
<body>
|
|
<h1>Your Cart</h1>
|
|
<ul id="items"></ul>
|
|
<div id="total">Total: $0</div>
|
|
<p><a href="shop.html">Back to shop</a></p>
|
|
<script>
|
|
var cart = JSON.parse(localStorage.getItem('cart') || '[]');
|
|
document.getElementById('items').innerHTML =
|
|
cart.map(function(i){ return '<li>' + i.n + ' $' + i.p + '</li>'; }).join('');
|
|
var total = cart.reduce(function(s, i){ return s + i.p; }, 0);
|
|
document.getElementById('total').textContent = 'Total: $' + total;
|
|
</script>
|
|
</body></html>
|