fnosp/fnos-dsh/browser-automation

Browser Automation

CRITICAL RULES — VIOLATIONS WILL BREAK THE WORKFLOW:

1. Never run midscene commands in the background. Each command must run synchronously so you can read its output (especially screenshots) before deciding the next action. Background execution breaks the screenshot-analyze-act loop.

2. Run only one midscene command at a time. Wait for the previous command to finish, read the screenshot, then decide the next action. Never chain multiple commands together.

3. Allow enough time for each command to complete. Midscene commands involve AI inference and screen interaction, which can take longer than typical shell commands. A typical command needs about 1 minute; complex act commands may need even longer.

4. Always report task results before finishing. After completing the automation task, you MUST proactively summarize the results to the user — including key data found, actions completed, screenshots taken, and any relevant findings. Never silently end after the last automation step; the user expects a complete response in a single interaction.

Automate web browsing using npx -y @midscene/web@1. By default, launches a headless Chrome via Puppeteer that persists across CLI calls — no session loss between commands. Also supports CDP mode and Bridge mode to connect to an existing Chrome browser.

What act Can Do

Inside a single act call in the browser, Midscene can click, right-click, double-click, hover, type or clear text, press keys, scroll, drag, long-press, and continue through multi-step page flows based on what is currently visible. When touch input is enabled, it can also handle swipe- or pinch-style interactions on touch-oriented pages.

When to Use

This skill has three modes. Choose based on the user's intent:

Mode Selection Guide

CDP vs Bridge: Both control the user's real Chrome with login sessions preserved. CDP only needs a Chrome setting toggle; Bridge needs a Chrome Extension installed. If the user doesn't specify, prefer CDP mode as it has fewer prerequisites.

Precheck: detect available CDP target

Before using CDP mode, run a quick precheck to verify Chrome's remote debugging port is reachable. This avoids long timeouts when the user hasn't enabled remote debugging.

# CDP precheck (port 9222, 2s timeout) — returns "101" if Chrome is listening for DevTools
curl -s --max-time 2 -o /dev/null -w "%{http_code}" -H "Upgrade: websocket" -H "Connection: Upgrade" -H "Sec-WebSocket-Version: 13" -H "Sec-WebSocket-Key: dGhlIHNhbXBsZSBub25jZQ==" http://127.0.0.1:9222/devtools/browser

How to use the precheck result:

• Returns 101 → CDP mode is available, use --cdp
• Fails (curl exit 7 or HTTP 000) → Chrome is not running with remote debugging enabled. Start Chrome with --remote-debugging-port=9222, wait 2-3 seconds, then re-run the precheck. If it still fails, fall back to Puppeteer mode (or use Bridge mode if the Midscene Chrome Extension is installed).

Bridge mode has no usable precheck. Despite port 3766 being involved, the bridge server is started by the CLI (npx ... --bridge connect opens 3766 itself); the extension is the client that hooks in. Checking 3766 before the CLI runs always returns nothing. Just run --bridge connect directly — its first log line (waiting for bridge to connect... → one client connected) tells you whether the extension picked it up.

Prerequisites

Midscene requires models with strong visual grounding capabilities. The following environment variables must be configured — either as system environment variables or in a .env file in the current working directory (Midscene loads .env automatically):

MIDSCENE_MODEL_API_KEY="your-api-key"
MIDSCENE_MODEL_NAME="model-name"
MIDSCENE_MODEL_BASE_URL="https://..."
MIDSCENE_MODEL_FAMILY="family-identifier"

Example: Gemini (Gemini-3-Flash)

MIDSCENE_MODEL_API_KEY="your-google-api-key"
MIDSCENE_MODEL_NAME="gemini-3-flash"
MIDSCENE_MODEL_BASE_URL="https://generativelanguage.googleapis.com/v1beta/openai/"
MIDSCENE_MODEL_FAMILY="gemini"

Example: Qwen 3.5

MIDSCENE_MODEL_API_KEY="your-aliyun-api-key"
MIDSCENE_MODEL_NAME="qwen3.5-plus"
MIDSCENE_MODEL_BASE_URL="https://dashscope.aliyuncs.com/compatible-mode/v1"
MIDSCENE_MODEL_FAMILY="qwen3.5"
MIDSCENE_MODEL_REASONING_ENABLED="false"
# If using OpenRouter, set:
# MIDSCENE_MODEL_API_KEY="your-openrouter-api-key"
# MIDSCENE_MODEL_NAME="qwen/qwen3.5-plus"
# MIDSCENE_MODEL_BASE_URL="https://openrouter.ai/api/v1"

Example: Doubao Seed 2.0 Lite

MIDSCENE_MODEL_API_KEY="your-doubao-api-key"
MIDSCENE_MODEL_NAME="doubao-seed-2-0-lite"
MIDSCENE_MODEL_BASE_URL="https://ark.cn-beijing.volces.com/api/v3"
MIDSCENE_MODEL_FAMILY="doubao-seed"

Commonly used models: Doubao Seed 2.0 Lite, Qwen 3.5, Zhipu GLM-4.6V, Gemini-3-Pro, Gemini-3-Flash.

If the model is not configured, ask the user to set it up. See Model Configuration for supported providers.

CDP Mode (Connect to Existing Browser)

Use CDP mode to control the user's existing Chrome browser. The default CDP endpoint is ws://127.0.0.1:9222/devtools/browser (port 9222 is Chrome's standard remote debugging port). If the user specifies a different port, replace 9222 accordingly.

Add --cdp <ws-endpoint> to every command:

npx -y @midscene/web@1 connect --cdp ws://127.0.0.1:9222/devtools/browser --url https://example.com
npx -y @midscene/web@1 act --cdp ws://127.0.0.1:9222/devtools/browser --prompt "click the button"
npx -y @midscene/web@1 take_screenshot --cdp ws://127.0.0.1:9222/devtools/browser
npx -y @midscene/web@1 disconnect --cdp ws://127.0.0.1:9222/devtools/browser

Custom HTTP Headers in CDP Mode

When the user needs custom request headers in CDP mode, such as routing requests to a PPE environment, pass each header through a separate --extra-http-header 'Name:Value' option. Repeat the option to send multiple headers. Use the exact header names and values supplied by the user; do not guess environment names or authentication values.

npx -y @midscene/web@1 connect \
  --cdp ws://127.0.0.1:9222/devtools/browser \
  --extra-http-header 'x-use-ppe:1' \
  --extra-http-header 'x-tt-env:ppe_example' \
  --url https://example.com
 
npx -y @midscene/web@1 act \
  --cdp ws://127.0.0.1:9222/devtools/browser \
  --extra-http-header 'x-use-ppe:1' \
  --extra-http-header 'x-tt-env:ppe_example' \
  --prompt "click the button"

Each CLI command creates a new CDP session. Repeat every required --extra-http-header 'Name:Value' option on each CDP command that may issue requests, including connect, act, and assert. Split each entry at the first colon, so values may contain additional colons. The headers are applied before connect --url navigates, so the initial document request includes them. Do not print header values in task summaries, and avoid putting sensitive authentication values directly in shell history.

Important notes for CDP mode

• The browser is managed externally — disconnect releases the connection but does NOT close the browser. There is no close command in CDP mode.
• In CDP mode, connect --url navigates the existing active tab instead of opening a new tab.
• connect without --url attaches to the current active tab without navigating.
• If connection fails, ask the user to enable remote debugging: open chrome://inspect in Chrome and turn on "Allow remote debugging".

Bridge Mode (Connect via Chrome Extension)

Use Bridge mode when the user explicitly mentions "bridge", "extension", or has the Midscene Chrome Extension installed. Add --bridge to every command:

npx -y @midscene/web@1 --bridge connect --url https://example.com
npx -y @midscene/web@1 --bridge act --prompt "click the button"
npx -y @midscene/web@1 --bridge take_screenshot
npx -y @midscene/web@1 --bridge disconnect

Important notes for Bridge mode

• The user must have Chrome (or any Chromium-based browser that supports Chrome extensions, e.g. Edge, Arc, Dia) open with the Midscene Extension installed and enabled.
• Install the extension from Chrome Web Store: https://chromewebstore.google.com/detail/midscenejs/gbldofcpkknbggpkmbdaefngejllnief
• Handshake direction: the CLI is the server (listens on 127.0.0.1:3766); the extension is the client that connects to it. The "Listening" status shown in the extension panel means "ready to connect to a CLI", not that the extension itself opened a port. Practically: launch --bridge connect first; the extension will hook in within a second or two.
• Active tab must be a normal web page. The extension cannot operate chrome://, chrome-extension://, the Chrome Web Store, or other privileged URLs. If the active tab is one of those, the CLI will return Cannot access a chrome:// URL. Ask the user to switch to a regular http(s):// tab before reconnecting.
• File upload permission: local file uploads in Bridge mode require the Midscene extension's "Allow access to file URLs" permission. Ask the user to open chrome://extensions, find Midscene, click "Details", enable the switch, then switch back to the target http(s):// tab before reconnecting. If upload fails with a permission or Not allowed error, check this first.
• connect without --url attaches to the current active tab; connect --url <href> navigates that tab. The CLI does not open new tabs in bridge mode.
• disconnect only closes the CLI-side bridge connection, not the browser or tabs.
• If the extension is not installed, guide the user to install it or suggest switching to CDP mode instead.
• See the Bridge Mode documentation.

Commands

Connect to a Web Page

npx -y @midscene/web@1 connect --url https://example.com

Take Screenshot

npx -y @midscene/web@1 take_screenshot

After taking a screenshot, read the saved image file to understand the current page state before deciding the next action.

Perform Action

Use act to interact with the page and get the result. It autonomously handles all UI interactions internally — clicking, typing, scrolling, hovering, waiting, and navigating — so you should give it complex, high-level tasks as a whole rather than breaking them into small steps. Describe what you want to do and the desired effect in natural language:

# specific instructions
npx -y @midscene/web@1 act --prompt "click the Login button and fill in the email field with 'user@example.com'"
npx -y @midscene/web@1 act --prompt "scroll down and click the Submit button"
 
# or target-driven instructions
npx -y @midscene/web@1 act --prompt "click the country dropdown and select Japan"

Upload Files