Skip to content

Conversation

@hfmsio
Copy link

@hfmsio hfmsio commented Dec 21, 2025

Summary

Adds Anthropic as 4th provider for Claude model completions.

  • Uses tool_use for structured output (Anthropic's equivalent to response_format)
  • Auth via x-api-key + anthropic-version headers
  • System prompts separated from messages
  • No embeddings support (Anthropic API limitation)

Files

  • 6 new files (handler, adapter, tests, docs)
  • 10 modified files (registration, integration)

Test Coverage

  • 16 unit tests (all passing)
  • 4 integration tests
  • OpenAI regression tested - no impact

Supported Functions

Function Status
llm_complete
llm_filter
llm_first/last
llm_reduce
llm_rerank
llm_embedding ✗ (Anthropic limitation)

anasdorbani and others added 2 commits September 19, 2025 11:11
Adds Anthropic as 4th provider for Claude model completions.
Uses tool_use for structured output, x-api-key auth, and
separates system prompts from messages. No embeddings support
(Anthropic API limitation). Includes 16 unit tests, 4 integration
tests, and documentation.
@anasdorbani
Copy link
Member

Hi @hfmsio, thanks for your effort and sorry for the late review 😅. I’ll suggest a few changes so we can merge the PR soon.

@anasdorbani anasdorbani changed the base branch from main to dev January 2, 2026 14:52
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants