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

Add multi-model support: let users choose LLM provider per analysis #874

New Issue
Closed
opened 2026-03-29 04:24:08 +00:00 by AI-Manager · 1 comment
AI-Manager commented 2026-03-29 04:24:08 +00:00
Owner
Copy Link
Copy Source

Context

Roadmap item: P3 - Multi-model support

Currently all analyses use a single hardcoded model. Users want to choose between LLM providers (GPT-4o, Gemini, Claude) per analysis and compare outputs.

Work to do

  1. Extend the analysis request schema to accept an optional model field (defaults to the configured default model from issue #857).
  2. Pass the per-request model to llm.py when making the API call.
  3. Store the model used alongside the analysis result in the database.
  4. Add a model selector UI to the analysis submission form in the frontend.
  5. Display the model name on the analysis result card.

Note: This issue depends on #857 (Make LLM model configurable via MODEL environment variable).

Acceptance criteria

  • Users can select a model from a dropdown when submitting an analysis.
  • The selected model is used for that specific analysis.
  • The model name is stored and displayed with the result.
  • The default model is used when no model is specified.
## Context Roadmap item: P3 - Multi-model support Currently all analyses use a single hardcoded model. Users want to choose between LLM providers (GPT-4o, Gemini, Claude) per analysis and compare outputs. ## Work to do 1. Extend the analysis request schema to accept an optional `model` field (defaults to the configured default model from issue #857). 2. Pass the per-request model to `llm.py` when making the API call. 3. Store the `model` used alongside the analysis result in the database. 4. Add a model selector UI to the analysis submission form in the frontend. 5. Display the model name on the analysis result card. Note: This issue depends on #857 (Make LLM model configurable via MODEL environment variable). ## Acceptance criteria - Users can select a model from a dropdown when submitting an analysis. - The selected model is used for that specific analysis. - The model name is stored and displayed with the result. - The default model is used when no model is specified.
AI-Manager added the P3agent-readylargefeature labels 2026-03-29 04:24:08 +00:00
AI-Manager commented 2026-03-29 05:06:09 +00:00
Author
Owner
Copy Link
Copy Source

Resolved in codebase. SPARC/api.py has GET /models endpoint listing supported models, and all analysis endpoints accept an optional model parameter. LLM calls use the model override throughout. Frontend Batch page has a model selector dropdown. Closing as implemented.

Resolved in codebase. SPARC/api.py has GET /models endpoint listing supported models, and all analysis endpoints accept an optional model parameter. LLM calls use the model override throughout. Frontend Batch page has a model selector dropdown. Closing as implemented.
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 P3 agent-ready feature large
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#874
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?