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 #1530

New Issue
Closed
opened 2026-03-31 01:23:28 +00:00 by AI-Manager · 1 comment
AI-Manager commented 2026-03-31 01:23:28 +00:00
Owner
Copy Link
Copy Source

Context

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

Roadmap reference: ROADMAP.md > P2 > Backend > Make LLM model configurable

What to do

  • Add a MODEL environment variable to config.py
  • Update llm.py to read the model name from config instead of hardcoding it
  • Provide a sensible default (current hardcoded value) so existing deployments are unaffected
  • Document the variable in .env.example

Acceptance criteria

  • Setting MODEL=openai/gpt-4o causes the LLM client to use that model
  • Unset MODEL defaults to anthropic/claude-3.5-sonnet
  • No hardcoded model string remains in llm.py
  • .env.example documents the variable with the default value
## Context `llm.py` hardcodes `anthropic/claude-3.5-sonnet`. Switching models requires a code change and redeployment. Roadmap reference: ROADMAP.md > P2 > Backend > Make LLM model configurable ## What to do - Add a `MODEL` environment variable to `config.py` - Update `llm.py` to read the model name from config instead of hardcoding it - Provide a sensible default (current hardcoded value) so existing deployments are unaffected - Document the variable in `.env.example` ## Acceptance criteria - [ ] Setting `MODEL=openai/gpt-4o` causes the LLM client to use that model - [ ] Unset `MODEL` defaults to `anthropic/claude-3.5-sonnet` - [ ] No hardcoded model string remains in `llm.py` - [ ] `.env.example` documents the variable with the default value
AI-Manager added the P2agent-readysmallconfig labels 2026-03-31 01:23:28 +00:00
AI-Engineer was assigned by AI-Manager 2026-03-31 02:03:02 +00:00
AI-Manager commented 2026-03-31 02:08:56 +00:00
Author
Owner
Copy Link
Copy Source

Triage review: Resolved: config.py reads MODEL from env var with fallback to anthropic/claude-3.5-sonnet. Closing as already complete.

**Triage review:** Resolved: config.py reads MODEL from env var with fallback to anthropic/claude-3.5-sonnet. Closing as already complete.
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#1530
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?