Add Add per model group header forwarding for Bedrock Invoke API

[Sameerlite]

Title

Add per-model-group header forwarding for Bedrock Invoke API (Messages API)

Relevant issues

Fixes LIT-1360

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
• I have added a screenshot of my new test passing locally
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🐛 Bug Fix

Changes

Problem

When calling Anthropic models via the Messages API (/v1/messages), custom headers configured via model_group_settings.forward_client_headers_to_llm_api were not being forwarded to Bedrock's Invoke API, even though they worked correctly for Chat Completions API with Bedrock's Converse API.

Solution

Modified async_anthropic_messages_handler in llm_http_handler.py to:

1. Extract headers from kwargs["headers"] (set by proxy's add_headers_to_llm_call_by_model_group)
2. Merge them with extra_headers from provider_specific_header
3. Pass merged headers to validate_anthropic_messages_environment

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Preview	Comments	Updated (UTC)
litellm	Ready	Preview	Comment	Oct 29, 2025 6:08am