What this error means
API Error: Stream idle timeout — partial response received is a Claude Code failure pattern reported for developers trying to fix claude code 'stream idle timeout — partial response received' error during tool calls and code generation. 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 183 comments. Error occurs between tool calls when requesting code plans. Affects Opus model on Claude Code 2.1.92+. Regression from 2.1.90. Exact error string available for SEO targeting.
Common causes
- Claude Code with Opus model intermittently fails mid-conversation with stream idle timeout errors, losing partial responses. This disrupts active development workflows, especially during multi-step agentic tasks. A regression since version 2.1.90. 183+ comments confirm widespread impact.
- Open GitHub issue with 183 comments. Error occurs between tool calls when requesting code plans. Affects Opus model on Claude Code 2.1.92+. Regression from 2.1.90. Exact error string available for SEO targeting.
Quick fixes
- Confirm the exact error signature matches
API Error: Stream idle timeout — partial response received. - Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
- 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
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- 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.