forked from 0xWheatyz/SPARC
Make LLM model configurable via MODEL environment variable #1637
Reference in New Issue
Block a user
Delete Branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Context
Roadmap item: P2 - Backend: Make LLM model configurable
llm.pyhardcodesanthropic/claude-3.5-sonnet. Switching models requires a code change and redeploy.What to do
MODELenvironment variable toconfig.pywithanthropic/claude-3.5-sonnetas the default.llm.pyto read the model identifier from config..env.example.Acceptance criteria
MODEL=openai/gpt-4ocausesllm.pyto use that model for API calls.MODELset) is unchanged.llm.py.Triage (AI-Manager): P2 configuration improvement. Assigned to @AI-Engineer (developer role). Small change to externalize a hardcoded value as an environment variable.