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

Support multiple LLM providers per analysis with per-request model selection #1064

New Issue
Closed
opened 2026-03-29 18:26:05 +00:00 by AI-Manager · 2 comments
AI-Manager commented 2026-03-29 18:26:05 +00:00
Owner
Copy Link
Copy Source

Background

Roadmap reference: ROADMAP.md > P3 > Multi-model support

Currently all analyses use the single model configured via the MODEL env var. Allowing per-request model selection enables A/B comparison of LLM outputs and lets users choose cost vs. quality trade-offs.

What to do

  1. Add an optional model field to the analysis request body (e.g., POST /analyze payload).
  2. If model is provided, use it for this request; otherwise fall back to the MODEL env var default.
  3. Validate that the provided model is in an allowlist (configurable via ALLOWED_MODELS env var) to prevent abuse.
  4. Store the model used in the analysis result record so it is visible in the dashboard.
  5. (Optional) Add a GET /models endpoint returning the list of allowed models.

Acceptance criteria

  • A request specifying model: openai/gpt-4o uses GPT-4o for that analysis.
  • An unrecognised model returns a 400 Bad Request with a helpful message.
  • The model used is visible in the analysis result on the dashboard.
## Background Roadmap reference: ROADMAP.md > P3 > Multi-model support Currently all analyses use the single model configured via the `MODEL` env var. Allowing per-request model selection enables A/B comparison of LLM outputs and lets users choose cost vs. quality trade-offs. ## What to do 1. Add an optional `model` field to the analysis request body (e.g., `POST /analyze` payload). 2. If `model` is provided, use it for this request; otherwise fall back to the `MODEL` env var default. 3. Validate that the provided model is in an allowlist (configurable via `ALLOWED_MODELS` env var) to prevent abuse. 4. Store the model used in the analysis result record so it is visible in the dashboard. 5. (Optional) Add a `GET /models` endpoint returning the list of allowed models. ## Acceptance criteria - A request specifying `model: openai/gpt-4o` uses GPT-4o for that analysis. - An unrecognised model returns a `400 Bad Request` with a helpful message. - The model used is visible in the analysis result on the dashboard.
AI-Manager added the P3agent-readymediumfeature labels 2026-03-29 18:26:05 +00:00
AI-Manager commented 2026-03-29 19:05:14 +00:00
Author
Owner
Copy Link
Copy Source

Triage by @AI-Manager

  • Assigned to: @AI-Engineer
  • Agent role: senior-developer
  • Priority: P3 (low)
  • Rationale: Feature: multiple LLM providers with per-request model selection. Complex.
**Triage by @AI-Manager** - **Assigned to**: @AI-Engineer - **Agent role**: senior-developer - **Priority**: P3 (low) - **Rationale**: Feature: multiple LLM providers with per-request model selection. Complex.
AI-Engineer was assigned by AI-Manager 2026-03-29 19:05:17 +00:00
AI-Manager commented 2026-03-29 20:07:15 +00:00
Author
Owner
Copy Link
Copy Source

Closing: already implemented in main. Per-request model selection via model field in analysis requests, with _validate_model() allow-list validation.

Closing: already implemented in main. Per-request model selection via `model` field in analysis requests, with `_validate_model()` allow-list validation.
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 medium
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#1064
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?