agent-browser 0.23.0 → 0.23.1

package/README.md

@@ -70,7 +70,7 @@ Detects your installation method (npm, Homebrew, or Cargo) and runs the appropri
 
 ### Requirements
 
-- **Chrome** - Run `agent-browser install` to download Chrome from [Chrome for Testing](https://developer.chrome.com/blog/chrome-for-testing/) (Google's official automation channel). No Playwright or Node.js required for the daemon.
+- **Chrome** - Run `agent-browser install` to download Chrome from [Chrome for Testing](https://developer.chrome.com/blog/chrome-for-testing/) (Google's official automation channel). Existing Chrome, Brave, Playwright, and Puppeteer installations are detected automatically. No Playwright or Node.js required for the daemon.
 - **Rust** - Only needed when building from source (see From Source above).
 
 ## Quick Start
@@ -307,6 +307,8 @@ agent-browser dialog dismiss          # Dismiss
 agent-browser dialog status           # Check if a dialog is currently open
 ```
 
+By default, `alert` and `beforeunload` dialogs are automatically accepted so they never block the agent. `confirm` and `prompt` dialogs still require explicit handling. Use `--no-auto-dialog` (or `AGENT_BROWSER_NO_AUTO_DIALOG=1`) to disable automatic handling.
+
 When a JavaScript dialog is pending, all command responses include a `warning` field with the dialog type and message.
 
 ### Diff
@@ -332,6 +334,7 @@ agent-browser trace stop [path]       # Stop and save trace
 agent-browser profiler start          # Start Chrome DevTools profiling
 agent-browser profiler stop [path]    # Stop and save profile (.json)
 agent-browser console                 # View console messages (log, error, warn, info)
+agent-browser console --json          # JSON output with raw CDP args for programmatic access
 agent-browser console --clear         # Clear console
 agent-browser errors                  # View page errors (uncaught JavaScript exceptions)
 agent-browser errors --clear          # Clear errors
@@ -594,6 +597,7 @@ This is useful for multimodal AI models that can reason about visual layout, unl
 | `--confirm-actions <list>` | Action categories requiring confirmation (or `AGENT_BROWSER_CONFIRM_ACTIONS` env) |
 | `--confirm-interactive` | Interactive confirmation prompts; auto-denies if stdin is not a TTY (or `AGENT_BROWSER_CONFIRM_INTERACTIVE` env) |
 | `--engine <name>` | Browser engine: `chrome` (default), `lightpanda` (or `AGENT_BROWSER_ENGINE` env) |
+| `--no-auto-dialog` | Disable automatic dismissal of `alert`/`beforeunload` dialogs (or `AGENT_BROWSER_NO_AUTO_DIALOG` env) |
 | `--config <path>` | Use a custom config file (or `AGENT_BROWSER_CONFIG` env) |
 | `--debug` | Debug output |
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "agent-browser",
-  "version": "0.23.0",
+  "version": "0.23.1",
   "description": "Headless browser automation CLI for AI agents",
   "type": "module",
   "files": [
@@ -28,7 +28,7 @@
   "bugs": {
     "url": "https://github.com/vercel-labs/agent-browser/issues"
   },
-  "homepage": "https://github.com/vercel-labs/agent-browser#readme",
+  "homepage": "https://agent-browser.dev",
   "devDependencies": {
     "@changesets/cli": "^2.29.8"
   },

package/scripts/windows-debug/provision.sh

@@ -0,0 +1,220 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+INSTANCE_FILE="$SCRIPT_DIR/.instance"
+NAME_PREFIX="agent-browser-debug"
+INSTANCE_TYPE="${INSTANCE_TYPE:-t3.xlarge}"
+
+if [[ -f "$INSTANCE_FILE" ]]; then
+  echo "Error: Instance already provisioned. See $INSTANCE_FILE"
+  echo "Run ./scripts/windows-debug/start.sh to start it, or delete .instance to re-provision."
+  exit 1
+fi
+
+REGION=$(aws configure get region 2>/dev/null || echo "")
+if [[ -z "$REGION" ]]; then
+  echo "Error: No AWS region configured. Run: aws configure set region us-east-1"
+  exit 1
+fi
+
+echo "Provisioning Windows debug instance in $REGION..."
+
+# --- IAM Role for SSM ---
+ROLE_NAME="${IAM_ROLE_NAME:-$NAME_PREFIX-ssm-role}"
+PROFILE_NAME="${INSTANCE_PROFILE_NAME:-$NAME_PREFIX-instance-profile}"
+
+if aws iam get-instance-profile --instance-profile-name "$PROFILE_NAME" &>/dev/null; then
+  echo "Instance profile $PROFILE_NAME already exists, reusing."
+else
+  echo "Instance profile $PROFILE_NAME not found. Creating IAM resources..."
+
+  if ! aws iam get-role --role-name "$ROLE_NAME" &>/dev/null; then
+    echo "Creating IAM role: $ROLE_NAME"
+    if ! aws iam create-role \
+      --role-name "$ROLE_NAME" \
+      --assume-role-policy-document '{
+        "Version": "2012-10-17",
+        "Statement": [{
+          "Effect": "Allow",
+          "Principal": {"Service": "ec2.amazonaws.com"},
+          "Action": "sts:AssumeRole"
+        }]
+      }' \
+      --no-cli-pager; then
+
+      echo ""
+      echo "Error: Failed to create IAM role (see error above)."
+      echo ""
+      echo "Ask an IAM admin to create the following, then re-run with:"
+      echo "  INSTANCE_PROFILE_NAME=<name> ./scripts/windows-debug/provision.sh"
+      echo ""
+      echo "What the admin needs to create:"
+      echo "  1. IAM Role: $ROLE_NAME"
+      echo "     - Trusted entity: EC2 (ec2.amazonaws.com)"
+      echo "     - Attached policy: AmazonSSMManagedInstanceCore"
+      echo "  2. Instance Profile: $PROFILE_NAME"
+      echo "     - With the above role added to it"
+      echo ""
+      echo "Or run these commands with an account that has iam:CreateRole permission:"
+      echo ""
+      echo "  aws iam create-role --role-name $ROLE_NAME \\"
+      echo "    --assume-role-policy-document '{\"Version\":\"2012-10-17\",\"Statement\":[{\"Effect\":\"Allow\",\"Principal\":{\"Service\":\"ec2.amazonaws.com\"},\"Action\":\"sts:AssumeRole\"}]}'"
+      echo ""
+      echo "  aws iam attach-role-policy --role-name $ROLE_NAME \\"
+      echo "    --policy-arn arn:aws:iam::aws:policy/AmazonSSMManagedInstanceCore"
+      echo ""
+      echo "  aws iam create-instance-profile --instance-profile-name $PROFILE_NAME"
+      echo ""
+      echo "  aws iam add-role-to-instance-profile \\"
+      echo "    --instance-profile-name $PROFILE_NAME --role-name $ROLE_NAME"
+      exit 1
+    fi
+
+    aws iam attach-role-policy \
+      --role-name "$ROLE_NAME" \
+      --policy-arn arn:aws:iam::aws:policy/AmazonSSMManagedInstanceCore
+  else
+    echo "IAM role $ROLE_NAME already exists."
+  fi
+
+  echo "Creating instance profile: $PROFILE_NAME"
+  aws iam create-instance-profile --instance-profile-name "$PROFILE_NAME" --no-cli-pager
+  aws iam add-role-to-instance-profile \
+    --instance-profile-name "$PROFILE_NAME" \
+    --role-name "$ROLE_NAME"
+  echo "Waiting for instance profile propagation..."
+  sleep 10
+fi
+
+# --- Security Group (no inbound rules) ---
+VPC_ID=$(aws ec2 describe-vpcs --filters "Name=isDefault,Values=true" --query "Vpcs[0].VpcId" --output text)
+if [[ "$VPC_ID" == "None" || -z "$VPC_ID" ]]; then
+  echo "Error: No default VPC found. Create one with: aws ec2 create-default-vpc"
+  exit 1
+fi
+
+SG_NAME="$NAME_PREFIX-sg"
+SG_ID=$(aws ec2 describe-security-groups \
+  --filters "Name=group-name,Values=$SG_NAME" "Name=vpc-id,Values=$VPC_ID" \
+  --query "SecurityGroups[0].GroupId" --output text 2>/dev/null || echo "None")
+
+if [[ "$SG_ID" == "None" || -z "$SG_ID" ]]; then
+  echo "Creating security group: $SG_NAME"
+  SG_ID=$(aws ec2 create-security-group \
+    --group-name "$SG_NAME" \
+    --description "agent-browser Windows debug instance (SSM only, no inbound)" \
+    --vpc-id "$VPC_ID" \
+    --query "GroupId" --output text)
+
+  # Revoke default egress isn't needed; SSM requires outbound HTTPS.
+  # No inbound rules -- SSM uses outbound connections only.
+else
+  echo "Security group $SG_NAME ($SG_ID) already exists, reusing."
+fi
+
+# --- AMI (latest Windows Server 2022) ---
+AMI_ID=$(aws ssm get-parameter \
+  --name "/aws/service/ami-windows-latest/Windows_Server-2022-English-Full-Base" \
+  --query "Parameter.Value" --output text)
+echo "Using AMI: $AMI_ID (Windows Server 2022)"
+
+# --- UserData bootstrap script ---
+USERDATA_FILE=$(mktemp)
+trap "rm -f $USERDATA_FILE" EXIT
+
+cat > "$USERDATA_FILE" <<'PWSH'
+<powershell>
+$ErrorActionPreference = "Continue"
+$logFile = "C:\bootstrap.log"
+
+function Log($msg) {
+    $ts = Get-Date -Format "yyyy-MM-dd HH:mm:ss"
+    "$ts  $msg" | Tee-Object -FilePath $logFile -Append
+}
+
+Log "--- Bootstrap starting ---"
+
+# Install Git
+Log "Installing Git..."
+$gitInstaller = "$env:TEMP\git-installer.exe"
+Invoke-WebRequest -Uri "https://github.com/git-for-windows/git/releases/download/v2.47.1.windows.2/Git-2.47.1.2-64-bit.exe" -OutFile $gitInstaller
+Start-Process -FilePath $gitInstaller -ArgumentList "/VERYSILENT /NORESTART /NOCANCEL /SP- /CLOSEAPPLICATIONS /RESTARTAPPLICATIONS /COMPONENTS=`"icons,ext\reg\shellhere,assoc,assoc_sh`"" -Wait
+$env:PATH = "C:\Program Files\Git\cmd;$env:PATH"
+[Environment]::SetEnvironmentVariable("PATH", "C:\Program Files\Git\cmd;$([Environment]::GetEnvironmentVariable('PATH', 'Machine'))", "Machine")
+Log "Git installed: $(git --version)"
+
+# Install Rust
+Log "Installing Rust..."
+$rustupInit = "$env:TEMP\rustup-init.exe"
+Invoke-WebRequest -Uri "https://win.rustup.rs/x86_64" -OutFile $rustupInit
+Start-Process -FilePath $rustupInit -ArgumentList "-y --default-toolchain stable" -Wait
+$env:PATH = "$env:USERPROFILE\.cargo\bin;$env:PATH"
+[Environment]::SetEnvironmentVariable("PATH", "$env:USERPROFILE\.cargo\bin;$([Environment]::GetEnvironmentVariable('PATH', 'Machine'))", "Machine")
+Log "Rust installed: $(rustc --version)"
+
+# Install MSVC build tools (required for Rust on Windows)
+Log "Installing Visual Studio Build Tools..."
+$vsInstaller = "$env:TEMP\vs_buildtools.exe"
+Invoke-WebRequest -Uri "https://aka.ms/vs/17/release/vs_buildtools.exe" -OutFile $vsInstaller
+Start-Process -FilePath $vsInstaller -ArgumentList "--quiet --wait --norestart --nocache --add Microsoft.VisualStudio.Workload.VCTools --includeRecommended" -Wait
+Log "Build tools installed."
+
+# Clone repo
+Log "Cloning agent-browser..."
+git clone https://github.com/vercel-labs/agent-browser.git C:\agent-browser
+Set-Location C:\agent-browser
+Log "Repo cloned."
+
+# Build CLI
+Log "Building agent-browser CLI..."
+cargo build --release --manifest-path cli\Cargo.toml
+Log "Build complete."
+
+# Install Chrome
+Log "Installing Chrome via agent-browser..."
+.\cli\target\release\agent-browser.exe install
+Log "Chrome installed."
+
+Log "--- Bootstrap complete ---"
+</powershell>
+PWSH
+
+# --- Launch instance ---
+echo "Launching $INSTANCE_TYPE instance..."
+INSTANCE_ID=$(aws ec2 run-instances \
+  --image-id "$AMI_ID" \
+  --instance-type "$INSTANCE_TYPE" \
+  --iam-instance-profile "Name=$PROFILE_NAME" \
+  --security-group-ids "$SG_ID" \
+  --user-data "file://$USERDATA_FILE" \
+  --block-device-mappings '[{"DeviceName":"/dev/sda1","Ebs":{"VolumeSize":80,"VolumeType":"gp3"}}]' \
+  --tag-specifications "ResourceType=instance,Tags=[{Key=Name,Value=$NAME_PREFIX}]" \
+  --metadata-options "HttpTokens=required" \
+  --query "Instances[0].InstanceId" --output text)
+
+echo "Instance launched: $INSTANCE_ID"
+
+# Save instance config
+cat > "$INSTANCE_FILE" <<EOF
+INSTANCE_ID=$INSTANCE_ID
+REGION=$REGION
+EOF
+
+echo "Waiting for instance to enter running state..."
+aws ec2 wait instance-running --instance-ids "$INSTANCE_ID"
+echo "Instance is running."
+
+echo ""
+echo "Instance $INSTANCE_ID is booting and bootstrapping (Rust, Git, Chrome)."
+echo "Bootstrap takes ~15-20 minutes on first boot."
+echo ""
+echo "Check bootstrap progress:"
+echo "  ./scripts/windows-debug/run.sh \"Get-Content C:\\bootstrap.log\""
+echo ""
+echo "Once ready, sync your branch and start debugging:"
+echo "  ./scripts/windows-debug/sync.sh"
+echo "  ./scripts/windows-debug/run.sh \"cd C:\\agent-browser && cargo test\""
+echo ""
+echo "Stop when done to save costs:"
+echo "  ./scripts/windows-debug/stop.sh"

package/scripts/windows-debug/run.sh

@@ -0,0 +1,92 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+INSTANCE_FILE="$SCRIPT_DIR/.instance"
+
+if [[ ! -f "$INSTANCE_FILE" ]]; then
+  echo "Error: No instance provisioned. Run ./scripts/windows-debug/provision.sh first."
+  exit 1
+fi
+
+if [[ $# -eq 0 ]]; then
+  echo "Usage: ./scripts/windows-debug/run.sh \"<powershell-command>\""
+  echo ""
+  echo "Examples:"
+  echo "  ./scripts/windows-debug/run.sh \"cd C:\\agent-browser && cargo test\""
+  echo "  ./scripts/windows-debug/run.sh \"Get-Content C:\\bootstrap.log\""
+  echo "  ./scripts/windows-debug/run.sh \"cd C:\\agent-browser && cargo test e2e -- --ignored --test-threads=1\""
+  exit 1
+fi
+
+source "$INSTANCE_FILE"
+export AWS_DEFAULT_REGION="$REGION"
+
+COMMAND="$*"
+
+PARAMS_FILE=$(mktemp)
+trap "rm -f $PARAMS_FILE" EXIT
+
+python3 -c '
+import json, sys
+path_setup = "$env:PATH = \"$env:USERPROFILE\\.cargo\\bin;C:\\Program Files\\Git\\cmd;$env:PATH\""
+cmd = path_setup + "\n" + sys.argv[1]
+json.dump({"commands": [cmd]}, open(sys.argv[2], "w"))
+' "$COMMAND" "$PARAMS_FILE"
+
+COMMAND_ID=$(aws ssm send-command \
+  --instance-ids "$INSTANCE_ID" \
+  --document-name "AWS-RunPowerShellScript" \
+  --parameters "file://$PARAMS_FILE" \
+  --timeout-seconds 3600 \
+  --query "Command.CommandId" --output text)
+
+echo "Command sent (ID: $COMMAND_ID). Waiting..." >&2
+
+while true; do
+  RESULT=$(aws ssm get-command-invocation \
+    --command-id "$COMMAND_ID" \
+    --instance-id "$INSTANCE_ID" \
+    --output json 2>&1) || true
+
+  STATUS=$(echo "$RESULT" | python3 -c "
+import sys, json
+try:
+    print(json.loads(sys.stdin.read()).get('Status', 'Unknown'))
+except:
+    print('Pending')
+" 2>/dev/null)
+
+  case "$STATUS" in
+    Success)
+      echo "$RESULT" | python3 -c "
+import sys, json
+r = json.loads(sys.stdin.read())
+out = r.get('StandardOutputContent', '').rstrip()
+err = r.get('StandardErrorContent', '').rstrip()
+if out:
+    print(out)
+if err:
+    print(err, file=sys.stderr)
+"
+      exit 0
+      ;;
+    Failed|TimedOut|Cancelled)
+      echo "$RESULT" | python3 -c "
+import sys, json
+r = json.loads(sys.stdin.read())
+out = r.get('StandardOutputContent', '').rstrip()
+err = r.get('StandardErrorContent', '').rstrip()
+if out:
+    print(out)
+if err:
+    print(err, file=sys.stderr)
+"
+      echo "Command $STATUS." >&2
+      exit 1
+      ;;
+    *)
+      sleep 3
+      ;;
+  esac
+done

package/scripts/windows-debug/start.sh

@@ -0,0 +1,43 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+INSTANCE_FILE="$SCRIPT_DIR/.instance"
+
+if [[ ! -f "$INSTANCE_FILE" ]]; then
+  echo "Error: No instance provisioned. Run ./scripts/windows-debug/provision.sh first."
+  exit 1
+fi
+
+source "$INSTANCE_FILE"
+export AWS_DEFAULT_REGION="$REGION"
+
+STATE=$(aws ec2 describe-instances \
+  --instance-ids "$INSTANCE_ID" \
+  --query "Reservations[0].Instances[0].State.Name" --output text)
+
+if [[ "$STATE" == "running" ]]; then
+  echo "Instance $INSTANCE_ID is already running."
+else
+  echo "Starting instance $INSTANCE_ID..."
+  aws ec2 start-instances --instance-ids "$INSTANCE_ID" --no-cli-pager
+  echo "Waiting for running state..."
+  aws ec2 wait instance-running --instance-ids "$INSTANCE_ID"
+  echo "Instance is running."
+fi
+
+echo "Waiting for SSM agent connectivity..."
+for i in $(seq 1 30); do
+  SSM_STATUS=$(aws ssm describe-instance-information \
+    --filters "Key=InstanceIds,Values=$INSTANCE_ID" \
+    --query "InstanceInformationList[0].PingStatus" --output text 2>/dev/null || echo "None")
+  if [[ "$SSM_STATUS" == "Online" ]]; then
+    echo "SSM agent is online. Ready for commands."
+    echo "  ./scripts/windows-debug/run.sh \"your-command-here\""
+    exit 0
+  fi
+  sleep 10
+done
+
+echo "Warning: SSM agent not online after 5 minutes. The instance may still be booting."
+echo "Try again in a minute: ./scripts/windows-debug/run.sh \"hostname\""

package/scripts/windows-debug/stop.sh

@@ -0,0 +1,28 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+INSTANCE_FILE="$SCRIPT_DIR/.instance"
+
+if [[ ! -f "$INSTANCE_FILE" ]]; then
+  echo "Error: No instance provisioned. Nothing to stop."
+  exit 1
+fi
+
+source "$INSTANCE_FILE"
+export AWS_DEFAULT_REGION="$REGION"
+
+STATE=$(aws ec2 describe-instances \
+  --instance-ids "$INSTANCE_ID" \
+  --query "Reservations[0].Instances[0].State.Name" --output text)
+
+if [[ "$STATE" == "stopped" ]]; then
+  echo "Instance $INSTANCE_ID is already stopped."
+  exit 0
+fi
+
+echo "Stopping instance $INSTANCE_ID..."
+aws ec2 stop-instances --instance-ids "$INSTANCE_ID" --no-cli-pager
+echo "Waiting for stopped state..."
+aws ec2 wait instance-stopped --instance-ids "$INSTANCE_ID"
+echo "Instance stopped. No compute charges while stopped (storage only: ~$0.64/mo)."

package/scripts/windows-debug/sync.sh

@@ -0,0 +1,27 @@
+#!/usr/bin/env bash
+set -euo pipefail
+
+SCRIPT_DIR="$(cd "$(dirname "$0")" && pwd)"
+RUN="$SCRIPT_DIR/run.sh"
+
+BRANCH=$(git rev-parse --abbrev-ref HEAD 2>/dev/null || echo "main")
+REMOTE_URL=$(git remote get-url origin 2>/dev/null || echo "https://github.com/vercel-labs/agent-browser.git")
+
+echo "Syncing branch '$BRANCH' on Windows instance..."
+
+"$RUN" "
+cd C:\agent-browser
+git remote set-url origin '$REMOTE_URL'
+git fetch origin
+git checkout -B '$BRANCH' 'origin/$BRANCH'
+git log -1 --oneline
+"
+
+echo ""
+echo "Branch synced. Rebuilding..."
+
+"$RUN" "
+cd C:\agent-browser
+cargo build --release --manifest-path cli\Cargo.toml
+Write-Host 'Build complete.'
+"

package/skills/agent-browser/SKILL.md

@@ -6,7 +6,7 @@ allowed-tools: Bash(npx agent-browser:*), Bash(agent-browser:*)
 
 # Browser Automation with agent-browser
 
-The CLI uses Chrome/Chromium via CDP directly. Install via `npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`. Run `agent-browser install` to download Chrome. Run `agent-browser upgrade` to update to the latest version.
+The CLI uses Chrome/Chromium via CDP directly. Install via `npm i -g agent-browser`, `brew install agent-browser`, or `cargo install agent-browser`. Run `agent-browser install` to download Chrome. Existing Chrome, Brave, Playwright, and Puppeteer installations are detected automatically. Run `agent-browser upgrade` to update to the latest version.
 
 ## Core Workflow
 
@@ -184,7 +184,10 @@ agent-browser clipboard write "Hello, World!"     # Write text to clipboard
 agent-browser clipboard copy                      # Copy current selection
 agent-browser clipboard paste                     # Paste from clipboard
 
-# Dialogs (alert, confirm, prompt)
+# Dialogs (alert, confirm, prompt, beforeunload)
+# By default, alert and beforeunload dialogs are auto-accepted so they never block the agent.
+# confirm and prompt dialogs still require explicit handling.
+# Use --no-auto-dialog (or AGENT_BROWSER_NO_AUTO_DIALOG=1) to disable automatic handling.
 agent-browser dialog accept              # Accept dialog
 agent-browser dialog accept "my input"   # Accept prompt dialog with text
 agent-browser dialog dismiss             # Dismiss/cancel dialog

package/skills/agent-browser/references/commands.md

@@ -209,9 +209,12 @@ The `frame` command accepts:
 
 ## Dialogs
 
+By default, `alert` and `beforeunload` dialogs are automatically accepted so they never block the agent. `confirm` and `prompt` dialogs still require explicit handling. Use `--no-auto-dialog` to disable this behavior.
+
 ```bash
 agent-browser dialog accept [text]  # Accept dialog
 agent-browser dialog dismiss        # Dismiss dialog
+agent-browser dialog status         # Check if a dialog is currently open
 ```
 
 ## JavaScript