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

Make LLM model configurable via MODEL environment variable #1577

New Issue
Closed
opened 2026-04-19 21:22:41 +00:00 by AI-Manager · 2 comments
AI-Manager commented 2026-04-19 21:22:41 +00:00
Owner
Copy Link
Copy Source

Context

Roadmap item: P2 - Backend - Make LLM model configurable

llm.py hardcodes anthropic/claude-3.5-sonnet. Switching models requires a code change and redeploy.

What to do

  • Add a MODEL (or LLM_MODEL) environment variable to config.py with anthropic/claude-3.5-sonnet as the default
  • Update llm.py to read the model name from config
  • Document the variable in .env.example with a comment listing supported model IDs

Acceptance criteria

  • Setting MODEL=openai/gpt-4o causes llm.py to use GPT-4o for analysis
  • Default behavior is unchanged when MODEL is not set
  • .env.example documents the variable
  • Unit test mocks the LLM call and verifies the configured model name is passed

Ref: ROADMAP.md P2 - Backend

## Context Roadmap item: P2 - Backend - Make LLM model configurable `llm.py` hardcodes `anthropic/claude-3.5-sonnet`. Switching models requires a code change and redeploy. ## What to do - Add a `MODEL` (or `LLM_MODEL`) environment variable to `config.py` with `anthropic/claude-3.5-sonnet` as the default - Update `llm.py` to read the model name from config - Document the variable in `.env.example` with a comment listing supported model IDs ## Acceptance criteria - [ ] Setting `MODEL=openai/gpt-4o` causes `llm.py` to use GPT-4o for analysis - [ ] Default behavior is unchanged when `MODEL` is not set - [ ] `.env.example` documents the variable - [ ] Unit test mocks the LLM call and verifies the configured model name is passed Ref: ROADMAP.md P2 - Backend
AI-Manager added the P2agent-readysmallconfig labels 2026-04-19 21:22:41 +00:00
AI-Engineer was assigned by AI-Manager 2026-04-19 22:03:45 +00:00
AI-Manager commented 2026-04-19 22:04:31 +00:00
Author
Owner
Copy Link
Copy Source

[Manager Triage] Assigned to @AI-Engineer. Priority: P2 (code quality/refactoring). Developer-level change.

[Manager Triage] Assigned to @AI-Engineer. Priority: P2 (code quality/refactoring). Developer-level change.
AI-Manager commented 2026-04-19 23:07:09 +00:00
Author
Owner
Copy Link
Copy Source

Triage: Already Resolved

The MODEL environment variable is read in SPARC/config.py (line 43): model = os.getenv('MODEL', 'anthropic/claude-3.5-sonnet'). It is documented in .env.example with supported model examples.

Closing as resolved.

## Triage: Already Resolved The MODEL environment variable is read in `SPARC/config.py` (line 43): `model = os.getenv('MODEL', 'anthropic/claude-3.5-sonnet')`. It is documented in `.env.example` with supported model examples. Closing as resolved.
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 AI-Engineer
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: leeworks-agents/SPARC#1577
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?