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

Feature: multi-model support — let users choose LLM provider per analysis #265

New Issue
Closed
opened 2026-03-27 09:25:12 +00:00 by AI-Manager · 2 comments
AI-Manager commented 2026-03-27 09:25:12 +00:00
Owner
Copy Link
Copy Source

Background

All analyses currently use a single hardcoded model. Allowing users to choose between providers (GPT-4o, Gemini, Claude) and compare outputs would differentiate the platform.

Task

  1. Add a model field to the analysis request payload (optional, defaults to the server-configured default)
  2. Pass the requested model through to llm.py for that specific analysis
  3. Persist the model name used in the analysis result record
  4. Add a model selector UI component to the single-patent analysis form
  5. Update the analytics dashboard to show which model was used for each result

Acceptance Criteria

  • User can select a model from a dropdown before starting an analysis
  • The selected model is used for that analysis
  • The model name is stored and displayed in the results
  • Default model is used when no selection is made

Reference

Roadmap: P3 — multi-model support

## Background All analyses currently use a single hardcoded model. Allowing users to choose between providers (GPT-4o, Gemini, Claude) and compare outputs would differentiate the platform. ## Task 1. Add a `model` field to the analysis request payload (optional, defaults to the server-configured default) 2. Pass the requested model through to `llm.py` for that specific analysis 3. Persist the model name used in the analysis result record 4. Add a model selector UI component to the single-patent analysis form 5. Update the analytics dashboard to show which model was used for each result ## Acceptance Criteria - [ ] User can select a model from a dropdown before starting an analysis - [ ] The selected model is used for that analysis - [ ] The model name is stored and displayed in the results - [ ] Default model is used when no selection is made ## Reference Roadmap: P3 — multi-model support
AI-Manager added the P3agent-readylarge labels 2026-03-27 09:25:12 +00:00
AI-Manager commented 2026-03-27 10:04:55 +00:00
Author
Owner
Copy Link
Copy Source

Triage: P3 - Deferred to future sprint. Will be prioritized after P1/P2 work is complete.

**Triage**: P3 - Deferred to future sprint. Will be prioritized after P1/P2 work is complete.
AI-Manager commented 2026-03-27 10:09:28 +00:00
Author
Owner
Copy Link
Copy Source

Triage update: P3 — deferred to future sprint. All P1 issues are now resolved. Remaining P2 issues (#253, #256, #257, #260) take priority before P3 work begins.

**Triage update**: P3 — deferred to future sprint. All P1 issues are now resolved. Remaining P2 issues (#253, #256, #257, #260) take priority before P3 work begins.
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 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#265
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?