What this error means

toolRunner drops defaultHeaders on follow-up requests (breaks proxy/gateway setups) is a Anthropic API failure pattern reported for developers trying to fix custom headers (e.g. cloudflare ai gateway auth) being dropped during anthropic sdk tool-use loop. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

GitHub issue #922 (created 2026-02-22, 5 comments). client.messages.toolRunner does not forward defaultHeaders on subsequent API calls during the tool-use loop. Breaks Cloudflare AI Gateway's unified billing (cf-aig-authorization header lost). First call works, follow-ups fail.

Common causes

  • Developers using the Anthropic TypeScript SDK with proxy/gateway setups (Cloudflare AI Gateway, custom auth proxies) lose custom headers after the first API call in the tool-use loop, causing authentication failures and broken billing tracking
  • GitHub issue #922 (created 2026-02-22, 5 comments). client.messages.toolRunner does not forward defaultHeaders on subsequent API calls during the tool-use loop. Breaks Cloudflare AI Gateway's unified billing (cf-aig-authorization header lost). First call works, follow-ups fail.

Quick fixes

  1. Confirm the exact error signature matches toolRunner drops defaultHeaders on follow-up requests (breaks proxy/gateway setups).
  2. Check the Anthropic API account, local tool state, and provider configuration involved in the failing workflow.
  3. Verify the account session, API key, provider settings, and environment where the failing tool is running.

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.