refactor: Move Anthropic translation layer to library

[mirrobot-agent]

Summary

This PR refactors the Anthropic endpoint support from PR #45 by moving the translation layer into the rotator_library as a proper, reusable module.

Related to: #45

Changes

New Library Module: rotator_library/anthropic_compat/

• models.py: Pydantic models for Anthropic API (requests, responses, content blocks)
• translator.py: Format translation functions between Anthropic and OpenAI formats
• streaming.py: Framework-agnostic streaming wrapper that converts OpenAI SSE to Anthropic SSE
• __init__.py: Public exports

Updated rotator_library/client.py

Added two new methods to RotatingClient:

• anthropic_messages() - Handle Anthropic Messages API requests
• anthropic_count_tokens() - Handle token counting

Simplified proxy_app/main.py

• Removed ~663 lines of local Anthropic code
• Now imports models and functions from rotator_library.anthropic_compat
• Endpoints work the same way but use library components
• Fixed verify_anthropic_api_key to support open access mode

Benefits

1. Reusability: The Anthropic translation layer can now be used by other applications using rotator_library
2. Maintainability: Clear separation between library code and application code
3. Testability: Library components can be unit tested independently
4. Consistency: Follows the existing library architecture patterns

Files Changed

src/rotator_library/
├── anthropic_compat/
│   ├── __init__.py          (NEW)
│   ├── models.py            (NEW)
│   ├── translator.py        (NEW)
│   └── streaming.py         (NEW)
├── client.py                (MODIFIED)
└── __init__.py              (MODIFIED)

src/proxy_app/
└── main.py                  (MODIFIED)

---

Important

Refactor Anthropic translation layer into a reusable library module for improved code reusability and maintainability.

• New Library Module: rotator_library/anthropic_compat/
  • models.py: Pydantic models for Anthropic API requests and responses.
  • translator.py: Functions for translating between Anthropic and OpenAI formats.
  • streaming.py: Converts OpenAI SSE to Anthropic SSE.
• Client Updates in client.py:
  • Added anthropic_messages() and anthropic_count_tokens() methods to RotatingClient.
• Main Application Simplification in main.py:
  • Removed ~663 lines of Anthropic-specific code.
  • Now uses rotator_library.anthropic_compat for Anthropic functionality.
  • Updated verify_anthropic_api_key() to support open access mode.

^{This description was created by for 9d30ea6. You can customize this summary. It will automatically update as commits are pushed.}

[mirrobot-agent]

Time to examine my own handiwork! Let's see what past-me was thinking when moving 1,300+ lines of Anthropic compatibility code into the library. This should be interesting... 🔍

[mirrobot-agent]

Self-Review Assessment

Well, well, well... time to grade my own homework! 📝

Overall, this is a solid refactoring that moves the Anthropic compatibility layer from proxy_app into rotator_library as a reusable module. The architecture follows the existing library patterns, and the separation of concerns is clear. Past-me did a decent job here... mostly.

Architectural Reflections

The module structure (models.py, translator.py, streaming.py) is clean and intuitive. I particularly like that:

• The streaming wrapper is framework-agnostic (accepts an optional disconnect callback rather than a FastAPI Request)
• The lazy-loading in __init__.py maintains fast import times
• The new RotatingClient methods provide a clean interface for Anthropic requests

Key Fixes I Should Make

1. Code duplication in main.py: I created a nice translate_anthropic_request() function but then... didn't use it in the endpoint? Classic past-me.

2. Type validation in models: The AnthropicThinkingConfig.type field accepts any string. Should use Literal["enabled", "disabled"] for proper validation.

3. Silent JSON failures: When parsing tool call arguments fails, I silently return an empty dict. Adding a debug log would make troubleshooting much easier.

Things That Actually Look Good

• The antigravity_provider.py addition for validating max_tokens > thinkingBudget is a good defensive check
• Error handling in the streaming wrapper properly ensures message_start is sent before any error events
• The token counting endpoint correctly handles both messages and tool definitions

Overall, this PR is ready to merge once the minor improvements above are addressed. Future-me thanks past-me for the decent documentation and clean module structure!

This self-review was generated by an AI assistant.

[mirrobot-agent]

Ah, it seems past-me got a bit ahead of himself! I specifically created translate_anthropic_request() in the library to handle this translation, but then proceeded to duplicate the logic here manually.

The thinking budget mapping logic (lines 1067-1089) is nearly identical to what I put in translator.py (lines 283-304). This could lead to drift if one is updated without the other.

I should either:

1. Use translate_anthropic_request() directly, or
2. Document why the endpoint needs different handling than the library method

[mirrobot-agent]

Past-me was feeling a bit lazy here. The type field should be constrained to valid values ("enabled" or "disabled"). Using a plain str allows invalid values to slip through validation.

Consider using:

from typing import Literal
# ...
type: Literal["enabled", "disabled"]

This gives proper IDE autocomplete and catches typos at validation time.

[mirrobot-agent]

My past-self used a silent fallback here - while pragmatic, it could mask issues where tool arguments are malformed. When tools mysteriously receive empty inputs, this will be hard to debug.

A quick logging statement would help future-me:

except json.JSONDecodeError as e:
    logging.debug(f"Failed to parse tool arguments: {e}")
    input_data = {}