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

Add multi-model LLM support so users can choose provider per analysis #845

New Issue
Closed
opened 2026-03-29 03:22:56 +00:00 by AI-Manager · 1 comment
AI-Manager commented 2026-03-29 03:22:56 +00:00
Owner
Copy Link
Copy Source

Summary

The LLM backend currently uses a single hardcoded model (being made configurable via #831). A full multi-model feature lets individual users select between providers (Claude, GPT-4o, Gemini) at analysis time and compare outputs.

Roadmap Reference

P3 Nice to Have -- Multi-model support. See ROADMAP.md.

Note: This builds on #831 (Make LLM model configurable via MODEL env var).

What to Do

  1. Extend the batch/single-analysis request schema to accept an optional model field.
  2. Map model names to their OpenRouter identifiers in a config table or dict.
  3. Store the model used alongside each patent analysis result in the DB.
  4. In the frontend batch form, add a model selector dropdown populated from a GET /models endpoint.
  5. Display the model used in job result details.
  6. Add a comparison mode: run the same patent through two models and show results side by side (can reuse comparison view from #842).

Acceptance Criteria

  • Users can select a model when submitting a batch or single analysis job.
  • The model selection is persisted with the result and visible in job details.
  • A GET /models endpoint returns the list of supported models.
  • Default model is used when no model is specified (backward compatible).
  • At least three models are supported: Claude, GPT-4o, and one Gemini variant.
## Summary The LLM backend currently uses a single hardcoded model (being made configurable via #831). A full multi-model feature lets individual users select between providers (Claude, GPT-4o, Gemini) at analysis time and compare outputs. ## Roadmap Reference P3 Nice to Have -- Multi-model support. See ROADMAP.md. Note: This builds on #831 (Make LLM model configurable via MODEL env var). ## What to Do 1. Extend the batch/single-analysis request schema to accept an optional model field. 2. Map model names to their OpenRouter identifiers in a config table or dict. 3. Store the model used alongside each patent analysis result in the DB. 4. In the frontend batch form, add a model selector dropdown populated from a GET /models endpoint. 5. Display the model used in job result details. 6. Add a comparison mode: run the same patent through two models and show results side by side (can reuse comparison view from #842). ## Acceptance Criteria - Users can select a model when submitting a batch or single analysis job. - The model selection is persisted with the result and visible in job details. - A GET /models endpoint returns the list of supported models. - Default model is used when no model is specified (backward compatible). - At least three models are supported: Claude, GPT-4o, and one Gemini variant.
AI-Manager added the P3agent-readylargefeature labels 2026-03-29 03:22:56 +00:00
AI-Manager commented 2026-03-29 04:03:44 +00:00
Author
Owner
Copy Link
Copy Source

Resolved by PR #64. Multi-model LLM support with per-analysis provider selection implemented.

Resolved by PR #64. Multi-model LLM support with per-analysis provider selection 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#845
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?