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

feat: add model picker UI and wire model param through backend #353

Merged
AI-Manager merged 2 commits from feature/351-frontend-model-picker into main 2026-03-27 16:45:08 +00:00
Conversation 0 Commits 2 Files Changed 5
+136 -42
AI-Manager commented 2026-03-27 16:13:20 +00:00
Owner
Copy Link
Copy Source

Summary

  • Add LLM model selector dropdown to Analysis and Batch pages
  • Thread model parameter through the full backend pipeline: API endpoints -> analyzer -> LLM
  • Add listModels() API client method to fetch available models from GET /models
  • Single company endpoint now accepts ?model= query parameter
  • Batch and async batch endpoints now pass request.model to the analyzer

Closes #351

Files Changed

  • SPARC/analyzer.py -- Added model parameter to analyze_company, _analyze_company_safe, analyze_companies, analyze_single_patent
  • SPARC/api.py -- Added model query param to single company endpoint; pass request.model in batch endpoints
  • frontend/src/api/client.ts -- Added model param to analyzeCompany, analyzeBatch, analyzeBatchAsync; added listModels() and model types
  • frontend/src/pages/Analysis.tsx -- Added model selector dropdown with data from /models API
  • frontend/src/pages/Batch.tsx -- Added model selector dropdown alongside workers slider

Test Plan

  • Verify model dropdown loads the curated list from GET /models
  • Submit an analysis with a non-default model and confirm the model is used
  • Submit a batch analysis with a selected model
  • Verify default behavior (no model selected) still works
  • Run npx tsc --noEmit to confirm no TypeScript errors
## Summary - Add LLM model selector dropdown to Analysis and Batch pages - Thread `model` parameter through the full backend pipeline: API endpoints -> analyzer -> LLM - Add `listModels()` API client method to fetch available models from `GET /models` - Single company endpoint now accepts `?model=` query parameter - Batch and async batch endpoints now pass `request.model` to the analyzer Closes #351 ## Files Changed - `SPARC/analyzer.py` -- Added `model` parameter to `analyze_company`, `_analyze_company_safe`, `analyze_companies`, `analyze_single_patent` - `SPARC/api.py` -- Added `model` query param to single company endpoint; pass `request.model` in batch endpoints - `frontend/src/api/client.ts` -- Added `model` param to `analyzeCompany`, `analyzeBatch`, `analyzeBatchAsync`; added `listModels()` and model types - `frontend/src/pages/Analysis.tsx` -- Added model selector dropdown with data from `/models` API - `frontend/src/pages/Batch.tsx` -- Added model selector dropdown alongside workers slider ## Test Plan - Verify model dropdown loads the curated list from `GET /models` - Submit an analysis with a non-default model and confirm the model is used - Submit a batch analysis with a selected model - Verify default behavior (no model selected) still works - Run `npx tsc --noEmit` to confirm no TypeScript errors
AI-Manager added 1 commit 2026-03-27 16:13:21 +00:00
feat: add model picker to Analysis and Batch pages with full backend wiring 223d5f7e5d 
Thread the optional model parameter through the entire analysis pipeline:
- analyzer.py: analyze_company, _analyze_company_safe, analyze_companies,
  and analyze_single_patent now accept and forward model override
- api.py: single company endpoint accepts model query param; batch and
  async batch endpoints pass request.model through to the analyzer
- client.ts: analyzeCompany, analyzeBatch, analyzeBatchAsync accept model;
  add listModels() to fetch available models from GET /models
- Analysis.tsx: add model selector dropdown that loads from /models API
- Batch.tsx: add model selector alongside the workers slider

Users can now pick a specific LLM (GPT-4o, Claude 3.5, Gemini, etc.)
per analysis request, or leave it on the server default.

Closes leeworks-agents/SPARC#351

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
AI-Manager added 1 commit 2026-03-27 16:44:54 +00:00
merge: resolve Batch.tsx conflict between model picker and job history 6aa71eb17e 
Combine both useQuery hooks (modelsQuery for model selector, jobsQuery for
job history) and pass selectedModel to analyzeBatch while also triggering
jobsQuery.refetch() on successful submission.
AI-Manager merged commit c72a44aa56 into main 2026-03-27 16:45:08 +00:00
Sign in to join this conversation.
Reviewers
No Reviewers
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
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#353
Delete Branch "feature/351-frontend-model-picker"

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?