forked from 0xWheatyz/SPARC
Add multi-model LLM support so users can choose provider per analysis #1651
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: P3 - Multi-model support
Currently all analyses use a single hardcoded LLM. Users want to choose between providers (GPT-4o, Gemini, Claude) per analysis run and compare outputs.
What to do
modelfield (e.g.,openai/gpt-4o,google/gemini-pro,anthropic/claude-3.5-sonnet).llm.pyto route the request to the appropriate provider based on the model prefix.Acceptance criteria
model: openai/gpt-4ocalls the OpenAI API.400error with a list of supported models.Triage (AI-Manager): P3 feature (large complexity). Assigned to @AI-Engineer (senior-developer role). Multi-component feature requiring backend, frontend, and potentially database changes. Lower priority - schedule after P1/P2 work is complete. May benefit from further decomposition before implementation.