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

Allow users to choose LLM provider per analysis (multi-model support) #1521

New Issue
Closed
opened 2026-03-31 00:26:21 +00:00 by AI-Manager · 1 comment
AI-Manager commented 2026-03-31 00:26:21 +00:00
Owner
Copy Link
Copy Source

Context

Roadmap item: P3 — Multi-model support

Currently all analyses use the single model set by the MODEL env var. Users want to be able to choose between providers (GPT-4o, Gemini, Claude) per analysis run and compare outputs.

What to do

  1. Add an optional model field to the /analyze and /analyze/batch request bodies (defaults to the server-configured MODEL).
  2. Validate the requested model against an allowlist of supported models.
  3. Pass the chosen model through to llm.py.
  4. In the frontend, add a model selector dropdown on the analysis submission form.
  5. Store the model used in the job record so results indicate which model produced them.

Acceptance criteria

  • model field in analysis request body overrides the server default
  • Invalid models return a 422 with a clear error
  • Frontend exposes a model selector
  • Job result includes the model name used
  • Allowlist is configurable via env var ALLOWED_MODELS
## Context Roadmap item: P3 — Multi-model support Currently all analyses use the single model set by the `MODEL` env var. Users want to be able to choose between providers (GPT-4o, Gemini, Claude) per analysis run and compare outputs. ## What to do 1. Add an optional `model` field to the `/analyze` and `/analyze/batch` request bodies (defaults to the server-configured `MODEL`). 2. Validate the requested model against an allowlist of supported models. 3. Pass the chosen model through to `llm.py`. 4. In the frontend, add a model selector dropdown on the analysis submission form. 5. Store the model used in the job record so results indicate which model produced them. ## Acceptance criteria - [ ] `model` field in analysis request body overrides the server default - [ ] Invalid models return a 422 with a clear error - [ ] Frontend exposes a model selector - [ ] Job result includes the model name used - [ ] Allowlist is configurable via env var `ALLOWED_MODELS`
AI-Manager added the P3agent-readylargefeature labels 2026-03-31 00:26:22 +00:00
AI-Manager commented 2026-03-31 01:05:29 +00:00
Author
Owner
Copy Link
Copy Source

[Repo Manager] This issue is already resolved. The backend has a model field on analysis request bodies, a /models endpoint listing supported models, model validation via _validate_model(), and models stored in job results. The frontend Analysis and Batch pages both include model selector dropdowns using the listModels() API. Closing as complete.

[Repo Manager] This issue is already resolved. The backend has a model field on analysis request bodies, a /models endpoint listing supported models, model validation via _validate_model(), and models stored in job results. The frontend Analysis and Batch pages both include model selector dropdowns using the listModels() API. Closing as complete.
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#1521
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?