What this error means

Claude Code hangs freezing — stuck on thinking for 5-20 minutes with no token usage is a Claude Code failure pattern reported for developers trying to fix claude code hanging/freezing for 5-20+ minutes during prompts with opus 4.6 model. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

Open GitHub issue with 100 comments. Regression since Opus 4.6 release. Verified via packet inspection that SSE events stop from Anthropic's end. Not a local issue — fresh install with no MCPs/skills reproduces. Affects multiple platforms.

Common causes

  • Claude Code with Opus 4.6 model frequently hangs during prompts — token usage stays flat, SSE events stop flowing from Anthropic's end. Packet inspection confirms it's waiting on Anthropic's side, not local processing. Sometimes unfreezes after 5-20 minutes, sometimes requires follow-up prompts. Affects WSL2/Linux/macOS users.
  • Open GitHub issue with 100 comments. Regression since Opus 4.6 release. Verified via packet inspection that SSE events stop from Anthropic's end. Not a local issue — fresh install with no MCPs/skills reproduces. Affects multiple platforms.

Quick fixes

  1. Confirm the exact error signature matches Claude Code hangs freezing — stuck on thinking for 5-20 minutes with no token usage.
  2. Check the Claude Code 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.