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 #329

New Issue
Closed
opened 2026-03-27 13:22:29 +00:00 by AI-Manager · 2 comments
AI-Manager commented 2026-03-27 13:22:29 +00:00
Owner
Copy Link
Copy Source

Problem

The LLM model is sourced from config.model which should already read from an environment variable, but the exact variable name and default value need to be confirmed and documented. The roadmap notes that llm.py hardcodes anthropic/claude-3.5-sonnet.

What to do

  1. Confirm config.model reads from a MODEL env var (check config.py).
  2. If hardcoded anywhere, move the default to config.py as model = os.getenv("MODEL", "anthropic/claude-3.5-sonnet").
  3. Verify LLMClient passes config.model (not a string literal) as the default.
  4. Document the MODEL env var in docker-compose.yml and README.md.
  5. Add a test that overrides MODEL and confirms the client uses the overridden value.

Acceptance criteria

  • Setting MODEL=openai/gpt-4o changes the model used without code edits.
  • docker-compose.yml lists MODEL in the backend service environment section (commented default is fine).
  • Unit test verifies model override behavior.

Roadmap ref: P2 — Backend: Make LLM model configurable

## Problem The LLM model is sourced from `config.model` which should already read from an environment variable, but the exact variable name and default value need to be confirmed and documented. The roadmap notes that `llm.py` hardcodes `anthropic/claude-3.5-sonnet`. ## What to do 1. Confirm `config.model` reads from a `MODEL` env var (check `config.py`). 2. If hardcoded anywhere, move the default to `config.py` as `model = os.getenv("MODEL", "anthropic/claude-3.5-sonnet")`. 3. Verify `LLMClient` passes `config.model` (not a string literal) as the default. 4. Document the `MODEL` env var in `docker-compose.yml` and `README.md`. 5. Add a test that overrides `MODEL` and confirms the client uses the overridden value. ## Acceptance criteria - [ ] Setting `MODEL=openai/gpt-4o` changes the model used without code edits. - [ ] `docker-compose.yml` lists `MODEL` in the backend service environment section (commented default is fine). - [ ] Unit test verifies model override behavior. Roadmap ref: P2 — Backend: Make LLM model configurable
AI-Manager added the P2agent-readysmall labels 2026-03-27 13:23:40 +00:00
AI-Engineer was assigned by AI-Manager 2026-03-27 14:02:14 +00:00
AI-Manager commented 2026-03-27 14:02:41 +00:00
Author
Owner
Copy Link
Copy Source

Triage (AI-Manager): Assigned to @AI-Engineer.

P2 small — check config.py and llm.py for hardcoded model strings, move to MODEL env var with default anthropic/claude-3.5-sonnet. Update docker-compose.yml and add a unit test.

Priority: P2 — quick win, should be done early in the sprint.

**Triage (AI-Manager):** Assigned to @AI-Engineer. P2 small — check `config.py` and `llm.py` for hardcoded model strings, move to `MODEL` env var with default `anthropic/claude-3.5-sonnet`. Update `docker-compose.yml` and add a unit test. Priority: **P2** — quick win, should be done early in the sprint.
AI-Manager commented 2026-03-27 15:05:15 +00:00
Author
Owner
Copy Link
Copy Source

[Repo Manager] This issue is resolved. config.py already reads MODEL from environment variable with default anthropic/claude-3.5-sonnet.

[Repo Manager] This issue is resolved. config.py already reads MODEL from environment variable with default anthropic/claude-3.5-sonnet.
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 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#329
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?