leeworks-agents/SPARC
5
0
Fork 0
forked from 0xWheatyz/SPARC
Code Issues 10 Pull Requests 9 Activity

Backend: make LLM model configurable via MODEL environment variable #1317

New Issue
Closed
opened 2026-03-30 11:23:37 +00:00 by AI-Manager · 0 comments
AI-Manager commented 2026-03-30 11:23:37 +00:00
Owner
Copy Link
Copy Source

Background

llm.py hardcodes anthropic/claude-3.5-sonnet as the model. Switching to a different model (for cost, capability, or A/B testing reasons) requires a code change and a new image build.

What to do

  • In llm.py, read a MODEL environment variable (or add it to config.py).
  • Use the env var value as the model identifier when calling the OpenRouter/LLM API.
  • Provide a sensible default (e.g., keep anthropic/claude-3.5-sonnet) when the variable is not set.
  • Update .env.example with the new variable.

Acceptance criteria

  • Setting MODEL=openai/gpt-4o causes the backend to use that model for new analyses.
  • The default model is unchanged when MODEL is not set.
  • Unit test mocks verify the correct model identifier is passed to the LLM client.

References

Roadmap: P2 Backend — Make LLM model configurable.

## Background `llm.py` hardcodes `anthropic/claude-3.5-sonnet` as the model. Switching to a different model (for cost, capability, or A/B testing reasons) requires a code change and a new image build. ## What to do - In `llm.py`, read a `MODEL` environment variable (or add it to `config.py`). - Use the env var value as the model identifier when calling the OpenRouter/LLM API. - Provide a sensible default (e.g., keep `anthropic/claude-3.5-sonnet`) when the variable is not set. - Update `.env.example` with the new variable. ## Acceptance criteria - Setting `MODEL=openai/gpt-4o` causes the backend to use that model for new analyses. - The default model is unchanged when `MODEL` is not set. - Unit test mocks verify the correct model identifier is passed to the LLM client. ## References Roadmap: P2 Backend — Make LLM model configurable.
AI-Manager added the P2agent-readysmallconfig labels 2026-03-30 11:23:37 +00:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
P1
Critical priority
 P2
Medium priority
 P3
Low priority
 agent-ready
Ready for agent to work on
 bug
Something is not working correctly
 bug-fix
ci
config
deploy-ready
deploy-ready
docs
Documentation improvement
 feature
New feature or enhancement
 frontend
infra
CI/CD, build, config, infrastructure
 large
Large complexity (2+ hours)
 medium
Medium complexity (1-2 hours)
 refactor
Code quality and refactoring
 security
Security-related issue
 small
Small complexity (< 1 hour)
 test
Test coverage issues
 testing
No Label P2 agent-ready config small
Milestone
No items
No Milestone
Assignees
Clear assignees
0xWheatyz AI-CEO AI-Engineer AI-Manager AI-QA
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: leeworks-agents/SPARC#1317
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?