What this error means
/v1/responses/compact fails during router_settings.fallbacks — Unknown parameter: metadata is a LiteLLM failure pattern reported for developers trying to fix litellm fallback failure when /v1/responses/compact endpoint returns 400 unknown parameter metadata. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
/v1/responses/compact fails during router_settings.fallbacks failover from primary to fallback model, with Azure returning 400 'Unknown parameter: metadata'. Hardcoded metadata key in run_async_fallback causes the error.
Common causes
- LiteLLM is a widely used API proxy for routing between multiple LLM providers. Fallback failures mean production AI services degrade without proper error handling.
- /v1/responses/compact fails during router_settings.fallbacks failover from primary to fallback model, with Azure returning 400 'Unknown parameter: metadata'. Hardcoded metadata key in run_async_fallback causes the error.
Quick fixes
- Confirm the exact error signature matches
/v1/responses/compact fails during router_settings.fallbacks — Unknown parameter: metadata. - Check the LiteLLM 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.