- Change core.info to core.debug for model responses in src/inference.ts
- Change core.info to core.debug for tool execution details in src/mcp.ts
- Change core.info to core.debug for custom header logging in src/helpers.ts
- Remove sensitive response previews from error messages in src/inference.ts
- Update tests to reflect changes from core.info to core.debug
This change adds support for custom HTTP headers in AI inference requests,
enabling integration with API Management platforms (Azure APIM, AWS API
Gateway, Kong, etc.) and custom request routing/tracking.
Features:
- New 'custom-headers' input supporting both YAML and JSON formats
- Auto-detection of input format for better UX
- Header name validation (alphanumeric, hyphens, underscores)
- Automatic masking of sensitive headers in logs
- Full backward compatibility (optional parameter)
Changes:
- Added parseCustomHeaders() function in helpers.ts
- Updated InferenceRequest interface with optional customHeaders field
- Modified simpleInference() and mcpInference() to pass headers to OpenAI client
- Added 18 comprehensive test cases
- Updated documentation with examples and use cases
All 80 tests passing. Zero breaking changes.
In a tool loop, you can't set response_format because the model needs to
be able to think in plain English. But you still need the final response
to be in the desired format, so we add response_format only on the last
iteration.
