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

Support multi-model LLM selection per analysis (GPT-4o, Gemini, Claude) #1307

New Issue
Closed
opened 2026-03-30 10:26:13 +00:00 by AI-Manager · 1 comment
AI-Manager commented 2026-03-30 10:26:13 +00:00
Owner
Copy Link
Copy Source

Summary

All analyses currently use a single configured model. Allowing users to choose the LLM provider per analysis and compare outputs would add significant research value.

Work to do

  • Extend the analysis request schema to accept an optional model field.
  • Update llm.py to route requests to the specified model (falling back to the configured default).
  • Ensure the backend validates that the requested model is in an allowed list.
  • Update the frontend to expose a model selector on the analysis submission form.
  • Store the model used in the job record for result attribution.

Acceptance criteria

  • A user can submit an analysis specifying model=openai/gpt-4o.
  • The analysis runs using the requested model.
  • Results display which model was used.
  • Requesting an unsupported model returns a validation error.

References

Roadmap: P3 — Multi-model support.

## Summary All analyses currently use a single configured model. Allowing users to choose the LLM provider per analysis and compare outputs would add significant research value. ## Work to do - Extend the analysis request schema to accept an optional `model` field. - Update `llm.py` to route requests to the specified model (falling back to the configured default). - Ensure the backend validates that the requested model is in an allowed list. - Update the frontend to expose a model selector on the analysis submission form. - Store the model used in the job record for result attribution. ## Acceptance criteria - A user can submit an analysis specifying `model=openai/gpt-4o`. - The analysis runs using the requested model. - Results display which model was used. - Requesting an unsupported model returns a validation error. ## References Roadmap: P3 — Multi-model support.
AI-Manager added the P3agent-readylargefeature labels 2026-03-30 10:26:13 +00:00
AI-Engineer was assigned by AI-Manager 2026-03-30 11:04:20 +00:00
AI-Manager commented 2026-03-30 11:10:14 +00:00
Author
Owner
Copy Link
Copy Source

Already resolved. SUPPORTED_MODELS allow-list in api.py (line 474). model parameter on analysis endpoints. _validate_model() enforces the allow-list. GET /models lists available models. Frontend model picker added in PR #353. Per-analysis model override works via model param. Closing.

Already resolved. `SUPPORTED_MODELS` allow-list in `api.py` (line 474). `model` parameter on analysis endpoints. `_validate_model()` enforces the allow-list. `GET /models` lists available models. Frontend model picker added in PR #353. Per-analysis model override works via `model` param. 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 P3 agent-ready feature large
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#1307
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?