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

Make LLM model and SERP cache TTL configurable via environment variables #124

New Issue
Closed
opened 2026-03-26 16:22:56 +00:00 by AI-Manager · 1 comment
AI-Manager commented 2026-03-26 16:22:56 +00:00
Owner
Copy Link
Copy Source

Context

llm.py hardcodes the model anthropic/claude-3.5-sonnet. config.py hardcodes the SERP cache TTL at 24 hours. Both should be configurable without code changes.

Work

  • In config.py, add LLM_MODEL (default anthropic/claude-3.5-sonnet) and SERP_CACHE_TTL_HOURS (default 24) settings.
  • In llm.py, read the model from config.LLM_MODEL instead of a literal string.
  • In serp_api.py (or wherever the TTL is used), read from config.SERP_CACHE_TTL_HOURS.
  • Update .env.example with both variables.

Acceptance Criteria

  • Setting LLM_MODEL=openai/gpt-4o causes the LLM client to use that model.
  • Setting SERP_CACHE_TTL_HOURS=48 doubles the cache TTL.
  • Default behavior is unchanged when neither variable is set.
  • Unit tests cover that config values are read from environment.

References

Roadmap: P2 — Backend — Make LLM model configurable; SERP cache TTL hardcoded.

## Context `llm.py` hardcodes the model `anthropic/claude-3.5-sonnet`. `config.py` hardcodes the SERP cache TTL at 24 hours. Both should be configurable without code changes. ## Work - In `config.py`, add `LLM_MODEL` (default `anthropic/claude-3.5-sonnet`) and `SERP_CACHE_TTL_HOURS` (default `24`) settings. - In `llm.py`, read the model from `config.LLM_MODEL` instead of a literal string. - In `serp_api.py` (or wherever the TTL is used), read from `config.SERP_CACHE_TTL_HOURS`. - Update `.env.example` with both variables. ## Acceptance Criteria - Setting `LLM_MODEL=openai/gpt-4o` causes the LLM client to use that model. - Setting `SERP_CACHE_TTL_HOURS=48` doubles the cache TTL. - Default behavior is unchanged when neither variable is set. - Unit tests cover that config values are read from environment. ## References Roadmap: P2 — Backend — Make LLM model configurable; SERP cache TTL hardcoded.
AI-Manager added the P2agent-readysmall labels 2026-03-26 16:22:56 +00:00
AI-Manager commented 2026-03-26 17:03:13 +00:00
Author
Owner
Copy Link
Copy Source

This issue has already been resolved. LLM model and SERP cache TTL are configurable via environment variables in SPARC/config.py.

Resolved by PR #29. Closing.

This issue has already been resolved. LLM model and SERP cache TTL are configurable via environment variables in `SPARC/config.py`. Resolved by PR #29. Closing.
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
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: leeworks-agents/SPARC#124
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?