agent-browser-priv 0.27.3-priv.4 → 0.27.3-priv.6

package/README.md

@@ -76,9 +76,9 @@ Detects your installation method (npm, Homebrew, or Cargo) and runs the appropri
 
 ### Requirements
 
-- **Patchright backend** - Run `agent-browser install` to install Patchright and its browser artifacts for the default local backend.
+- **Patchright backend** - Run `agent-browser install` to install pinned Patchright and its browser artifacts for the default local backend. Requires Node.js and npm for install and runtime launch.
 - **Chrome backend** - Use `agent-browser install chrome` to download Chrome from [Chrome for Testing](https://developer.chrome.com/blog/chrome-for-testing/) for `--backend chrome`. Existing Chrome, Brave, Playwright, and Puppeteer installations are detected automatically.
-- **Node.js 24+ and pnpm 11+** - Only needed when building from source.
+- **Node.js 24+ and pnpm 11+** - pnpm is only needed when building from source; Node.js is also needed by the default Patchright backend.
 - **Rust** - Only needed when building from source (see From Source above).
 
 ## Quick Start
@@ -115,6 +115,7 @@ agent-browser find role button click --name "Submit"
 ```bash
 agent-browser open                    # Launch browser (no navigation); stays on about:blank
 agent-browser open <url>              # Launch + navigate to URL (aliases: goto, navigate)
+agent-browser open --wait-until none <url>  # Return immediately after navigation is sent
 agent-browser click <sel>             # Click element (--new-tab to open in new tab)
 agent-browser dblclick <sel>          # Double-click element
 agent-browser focus <sel>             # Focus element
@@ -782,6 +783,11 @@ Patchright is used only to launch the local Chrome-compatible browser and expose
 CDP on localhost. It does not solve CAPTCHA, Turnstile, or other human
 verification pages; preserve those pages for human handoff.
 
+The default Patchright backend honors `--proxy`, `--proxy-bypass`,
+`--user-agent`, `--ignore-https-errors`, `--download-path`, and custom launch
+args. Remote-debugging address and port args are reserved by agent-browser and
+are forced to localhost.
+
 ## Observability Dashboard
 
 Monitor agent-browser sessions in real time with a local web dashboard showing a live viewport and command activity feed.
@@ -1260,7 +1266,7 @@ Connect to `ws://localhost:9223` to receive frames and send input:
 agent-browser uses a client-daemon architecture:
 
 1. **Rust CLI** - Parses commands, communicates with daemon
-2. **Rust Daemon** - Pure Rust daemon using direct CDP, no Node.js required
+2. **Rust Daemon** - Rust daemon using direct CDP. The default Patchright backend uses a small Node.js host to launch Patchright; `--backend chrome` remains the pure Rust local launcher.
 
 The daemon starts automatically on first command and persists between commands for fast subsequent operations. To auto-shutdown the daemon after a period of inactivity, set `AGENT_BROWSER_IDLE_TIMEOUT_MS` (value in milliseconds). When set, the daemon closes the browser and exits after receiving no commands for the specified duration.
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-browser-priv",
-  "version": "0.27.3-priv.4",
+  "version": "0.27.3-priv.6",
   "description": "Browser automation CLI for AI agents",
   "type": "module",
   "packageManager": "pnpm@11.1.3",

package/skill-data/core/SKILL.md

@@ -14,6 +14,10 @@ launcher when that lane behaves better for a target. Accessibility-tree
 snapshots with compact `@eN` refs let agents interact with pages in ~200-400
 tokens instead of parsing raw HTML.
 
+The default Patchright backend requires Node.js at runtime; `agent-browser
+install` installs pinned Patchright browser artifacts. The `--backend chrome`
+lane remains the pure Rust local Chrome launcher.
+
 Do not add CAPTCHA solving, Turnstile solving, proxy rotation policy, or
 production stealth defaults. If a challenge remains, classify it and preserve
 artifacts for human handoff.
@@ -26,6 +30,7 @@ web pages — see [When to load another skill](#when-to-load-another-skill).
 
 ```bash
 agent-browser open <url>        # 1. Open a page
+agent-browser open --wait-until none <url>  # Send nav and return immediately
 agent-browser snapshot -i       # 2. See what's on it (interactive elements only)
 agent-browser click @e3         # 3. Act on refs from the snapshot
 agent-browser snapshot -i       # 4. Re-snapshot after any page change
@@ -421,6 +426,7 @@ and [references/authentication.md](references/authentication.md).
 --backend <name>        # local backend: patchright (default), chrome
 --profile <name|path>   # use a Chrome profile (login state survives)
 --headers <json>        # HTTP headers scoped to the URL's origin
+--wait-until <state>    # navigation wait: none, domcontentloaded, load, networkidle
 --proxy <url>           # proxy server
 --state <path>          # load saved auth state from JSON
 --session-name <name>   # auto-save/restore session state by name

package/skill-data/core/references/commands.md

@@ -9,6 +9,7 @@ agent-browser open            # Launch browser (no navigation); stays on about:b
                               # Pair with `network route`, `cookies set --curl`, or
                               # `addinitscript` to stage state before the first navigation.
 agent-browser open <url>      # Launch + navigate (aliases: goto, navigate)
+agent-browser open --wait-until none <url>  # Send navigation and return immediately
                               # Supports: https://, http://, file://, about:, data://
                               # Auto-prepends https:// if no protocol given
 agent-browser back            # Go back
@@ -310,9 +311,11 @@ agent-browser --session <name> ...    # Isolated browser session
 agent-browser --json ...              # JSON output for parsing
 agent-browser --headed ...            # Show browser window (not headless)
 agent-browser --cdp <port> ...        # Connect via Chrome DevTools Protocol
+agent-browser --backend <name> ...    # Local backend: patchright (default), chrome
 agent-browser -p <provider> ...       # Cloud browser provider (--provider)
 agent-browser --proxy <url> ...       # Use proxy server
 agent-browser --proxy-bypass <hosts>  # Hosts to bypass proxy
+agent-browser --wait-until <state>    # Navigation wait: none, domcontentloaded, load, networkidle
 agent-browser --headers <json> ...    # HTTP headers scoped to URL's origin
 agent-browser --executable-path <p>   # Custom browser executable
 agent-browser --extension <path> ...  # Load browser extension (repeatable)

package/skill-data/core/references/proxy-support.md

@@ -1,6 +1,6 @@
 # Proxy Support
 
-Proxy configuration for geo-testing, rate limiting avoidance, and corporate environments.
+Proxy configuration for controlled egress, geo-testing, and corporate environments.
 
 **Related**: [commands.md](commands.md) for global options, [SKILL.md](../SKILL.md) for quick start.
 
@@ -37,6 +37,11 @@ export HTTPS_PROXY="http://proxy.example.com:8080"
 agent-browser open https://example.com
 ```
 
+The default Patchright backend and the built-in Chrome backend both honor
+`--proxy` and `--proxy-bypass`. Patchright receives these settings through its
+persistent-context launch options; Chrome receives them as Chromium launch
+arguments.
+
 ## Authenticated Proxy
 
 For proxies requiring authentication:
@@ -100,37 +105,6 @@ for proxy in "${PROXIES[@]}"; do
 done
 ```
 
-### Rotating Proxies for Scraping
-
-```bash
-#!/bin/bash
-# Rotate through proxy list to avoid rate limiting
-
-PROXY_LIST=(
-    "http://proxy1.example.com:8080"
-    "http://proxy2.example.com:8080"
-    "http://proxy3.example.com:8080"
-)
-
-URLS=(
-    "https://site.com/page1"
-    "https://site.com/page2"
-    "https://site.com/page3"
-)
-
-for i in "${!URLS[@]}"; do
-    proxy_index=$((i % ${#PROXY_LIST[@]}))
-    export HTTP_PROXY="${PROXY_LIST[$proxy_index]}"
-    export HTTPS_PROXY="${PROXY_LIST[$proxy_index]}"
-
-    agent-browser open "${URLS[$i]}"
-    agent-browser get text body > "output-$i.txt"
-    agent-browser close
-
-    sleep 1  # Polite delay
-done
-```
-
 ### Corporate Network Access
 
 ```bash
@@ -191,4 +165,4 @@ export NO_PROXY="*.cdn.com,*.static.com"  # Direct CDN access
 2. **Set NO_PROXY appropriately** - Avoid routing local traffic through proxy
 3. **Test proxy before automation** - Verify connectivity with simple requests
 4. **Handle proxy failures gracefully** - Implement retry logic for unstable proxies
-5. **Rotate proxies for large scraping jobs** - Distribute load and avoid bans
+5. **Keep challenge pages intact** - If a bot or human-verification page remains, preserve artifacts for human handoff instead of bypassing it