Browser Recover#

Automated recovery for OpenClaw browser environment failures.

Quick Start#

When a browser tool call fails, follow this workflow:

1. Detect: Check if error matches browser environment issues
2. Diagnose: Run scripts/check_state.sh to inspect current state
3. Recover: Run scripts/recover.sh to clean up
4. Retry: Execute the original browser operation ONCE
5. Report: If still fails, output error summary and STOP

Error Pattern Matching#

Error PatternLikely CauseRecovery ActionTarget closedStale CDP connectionrecover.sh --kill-processes``ECONNREFUSED on port 9222/18800Port conflictrecover.sh --clear-ports``timeout during browser.startLock file conflictrecover.sh --clear-locksMultiple chromium processesZombie processesrecover.sh --full``Profile in useStale lock filesrecover.sh --clear-locks

Recovery Scripts#

check_state.sh#

Diagnose browser environment without making changes.

Usage:

bash

bash scripts/check_state.sh

Output:

• Browser process count and PIDs
• Port usage status (9222, 18800, custom ports)
• Lock file locations
• Recommendation (clean or no action needed)

recover.sh#

Clean up stale browser resources.

Usage:

bash

# Full recovery (default)
bash scripts/recover.sh

# Specific actions
bash scripts/recover.sh --kill-processes
bash scripts/recover.sh --clear-ports
bash scripts/recover.sh --clear-locks

# Explicit full recovery
bash scripts/recover.sh --full

Actions:

1. Kills stale browser processes (chromium, chrome variants)
2. Clears port conflicts (9222, 18800, configured ports)
3. Removes lock files (SingletonLock, SingletonSocket, SingletonCookie)
4. Clears cache directories (Cache, Code Cache, GPUCache)
5. Waits 2 seconds for resources to release

Configuration:

• Reads ~/.openclaw/config/openclaw.json for browser settings
• Falls back to defaults if config not found
• See references/configuration.md for details

Retry Policy#

Session-level tracking:

• Maximum 2 recovery attempts per session
• Track failures to prevent infinite loops
• Stop after 2nd failure and escalate to human

Implementation:

text

Attempt 1: browser fails → diagnose → recover → retry → success ✓
Attempt 2: browser fails → diagnose → recover → retry → fails → STOP

When to stop:

• 2nd recovery in same session fails
• Error is not browser-environment related
• System-level issues detected (permissions, resources)
• User explicitly requests manual intervention

Safety Constraints#

DO:

• Only clean OpenClaw-managed browser instances
• Verify process ownership before killing
• Check profile path matches ~/.openclaw/browser
• Log all actions to stderr for OpenClaw to capture

DON'T:

• Kill user's personal browser processes
• Delete user profile directories ( ~/.config/chrome, etc.)
• Use kill -9 without verification
• Restart entire system
• Clean up other agents' browser instances without isolation

See references/safety.md for detailed guidelines.

Troubleshooting#

If recovery fails or behaves unexpectedly:

1. Run check_state.sh to diagnose
2. Check OpenClaw logs: ~/.openclaw/logs/
3. Verify configuration: ~/.openclaw/config/openclaw.json
4. Review references/troubleshooting.md
5. If unsure, escalate to human operator

Configuration#

Scripts automatically read OpenClaw config for:

• Browser debug port ( browser.debugPort)
• Profile directory ( browser.userDataDir)

See references/configuration.md for:

• Custom port configuration
• Multiple instance setup
• Platform-specific notes
• Environment variables

Example Workflow#

markdown

User: "Open https://example.com"
Assistant: [calls browser tool]
Error: "ECONNREFUSED on port 9222"

Assistant: Detected port conflict. Running recovery...
[runs check_state.sh]
[runs recover.sh --clear-ports]
[waits 2 seconds]
[retries browser tool]
Success: Browser opened https://example.com

Notes#

• All scripts log to stderr for OpenClaw to capture automatically
• No separate log files are created
• Scripts read OpenClaw config for browser settings
• Recovery is idempotent (safe to run multiple times)
• Maximum 2 recovery attempts per session to prevent loops