microsoft / microsoft/debug-gym
Support to LiteLLM
Open
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 307
- Forks
- 45
- Avg merge
- 1d 7h
- Merged PRs (30d)
- 9
Description
Integrate LiteLLM as an abstraction layer to standardize access to multiple LLM providers within the existing debug_gym.llms module.
Verify feasibility of:
- Support for OpenAI, Azure, Anthropic, HuggingFace, and Copilot
- Reducing boilerplate by unifying message formatting
- Ensuring compatibility with existing
tokenize()andcount_tokens()logic
Contributor guide
No contributing guide indexed for this repository
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reading the existing debug_gym.llms module and its tokenize() and count_tokens() logic, then review LiteLLM's provider support and message-formatting behavior. Assess compatibility with OpenAI, Azure, Anthropic, HuggingFace, and Copilot; the work is done when feasibility, required integration scope, and token-counting compatibility are established.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- ai, backend
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100