What this error means

Browser Use broken: no node_repl/js or no Codex IAB backend discovered is a Codex failure pattern reported for developers trying to fix codex desktop browser use not working after update — node repl execution tool not exposed. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

After Codex Desktop update on macOS, Browser Use feature broken. In-app browser open on local dev server, but Browser Use commands fail because Node REPL execution tool not exposed. Tool discovery for mcp__node_repl fails. Affects macOS users specifically.

Common causes

  • Codex Desktop is OpenAI's AI coding IDE. Browser Use is a key feature for web automation tasks. After an update, the main thread can no longer discover the Node REPL execution tool (mcp__node_repl), breaking browser automation workflows that developers rely on for testing and scraping.
  • After Codex Desktop update on macOS, Browser Use feature broken. In-app browser open on local dev server, but Browser Use commands fail because Node REPL execution tool not exposed. Tool discovery for mcp__node_repl fails. Affects macOS users specifically.

Quick fixes

  1. Confirm the exact error signature matches Browser Use broken: no node_repl/js or no Codex IAB backend discovered.
  2. Check the Codex account, local tool state, and provider configuration involved in the failing workflow.
  3. Compare the failing environment with a known working setup, then change one configuration value at a time.

Platform/tool-specific checks

  • Verify the command, editor, extension, or API client that produced the error.
  • Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
  • Avoid deleting credentials, local model data, or project settings until the failing scope is clear.

Step-by-step troubleshooting

  1. Capture the exact error message and the command, editor action, or request that triggered it.
  2. Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
  3. Review the source evidence below and compare it with your environment.
  4. Apply one change at a time and rerun the smallest failing action.
  5. Keep the working fix documented for the team or deployment environment.

How to prevent it

  • Keep provider/tool configuration documented.
  • Record non-secret diagnostics such as tool version, provider name, model name, and command path.
  • Add a lightweight check before CI or production workflows depend on the tool.