What this error means

httpx.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read) is a Anthropic API failure pattern reported for developers trying to fix anthropic sdk remoteprotocolerror streaming drop on long code_execution responses. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.

Why this happens

claude-opus-4-6 with code-execution + skills betas. 38 content blocks streamed before drop. Stream died mid-text_editor_code_execution.input_json_delta at 20 bytes. Previous tool_use had ~42KB input. Connection closed by server during active byte transfer.

Common causes

  • Streaming requests to /v1/messages with code_execution + skills consistently drop mid-stream. Server closes connection while actively sending content_block_delta events. Each retry costs full input + partial output tokens. No idle timeout — server FIN arrives during active data transfer.
  • claude-opus-4-6 with code-execution + skills betas. 38 content blocks streamed before drop. Stream died mid-text_editor_code_execution.input_json_delta at 20 bytes. Previous tool_use had ~42KB input. Connection closed by server during active byte transfer.

Quick fixes

  1. Confirm the exact error signature matches httpx.RemoteProtocolError: peer closed connection without sending complete message body (incomplete chunked read).
  2. Check the Anthropic API 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.