feat: Added LiteLLM SDK provider support

[satvikbatra]

No description provided.

[Copilot]

Pull Request Overview

This PR adds LiteLLM SDK provider support to JAF, enabling direct integration with 100+ AI providers without requiring a separate LiteLLM server. The implementation provides a new make_litellm_sdk_provider function that supports OpenAI, Anthropic, Google (Gemini/Vertex AI), and many other providers through the LiteLLM SDK.

• Adds direct LiteLLM SDK integration as an alternative to the existing server-based provider
• Includes comprehensive test suite for validating multiple AI provider integrations
• Updates documentation to explain both SDK and server-based provider options

Reviewed Changes

Copilot reviewed 6 out of 6 changed files in this pull request and generated no comments.

Show a summary per file

File	Description
jaf/providers/model.py	Implements the new LiteLLMSDKProvider class with completion and streaming support
jaf/providers/init.py	Exports the new make_litellm_sdk_provider function
tests/test_manual.py	Comprehensive manual test suite for OpenAI, Gemini, and Vertex AI providers
pyproject.toml	Adds litellm>=1.76.3 dependency
docs/model-providers.md	Updates documentation with SDK provider examples and configuration
.env.default	Adds environment variable templates for API keys

Comments suppressed due to low confidence (2)

jaf/providers/model.py:1

• The model name 'gemini-2.5-pro' does not exist. Google's Gemini models are currently 'gemini-pro', 'gemini-1.5-pro', 'gemini-1.5-flash', etc. Please use a valid model name.

"""

jaf/providers/model.py:1

• The model name 'vertex_ai/gemini-2.5-pro' does not exist. Google's Gemini models are currently 'gemini-pro', 'gemini-1.5-pro', 'gemini-1.5-flash', etc. Please use a valid model name like 'vertex_ai/gemini-1.5-pro'.

"""

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}