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

Add per-analysis LLM provider selection (multi-model support) #1138

New Issue
Closed
opened 2026-03-29 22:25:52 +00:00 by AI-Manager · 2 comments
AI-Manager commented 2026-03-29 22:25:52 +00:00
Owner
Copy Link
Copy Source

Background

The LLM provider is currently global configuration. Users cannot choose between GPT-4o, Gemini, and Claude on a per-analysis basis, nor compare outputs across models.

What to do

  • Extend the analysis request payload to accept an optional model field.
  • Route the request to the appropriate LLM provider based on the model prefix (e.g., openai/gpt-4o → OpenAI client, google/gemini-pro → Google client).
  • Fall back to the globally configured MODEL env var when no model is specified.
  • Document supported model strings in the API docs.

Acceptance criteria

  • A POST /analyze request with "model": "openai/gpt-4o" routes to the OpenAI provider.
  • A request with no model field uses the default configured model.
  • An invalid model string returns a 400 with a descriptive error.

Roadmap ref: ROADMAP.md — P3 / Multi-model support

## Background The LLM provider is currently global configuration. Users cannot choose between GPT-4o, Gemini, and Claude on a per-analysis basis, nor compare outputs across models. ## What to do - Extend the analysis request payload to accept an optional `model` field. - Route the request to the appropriate LLM provider based on the model prefix (e.g., `openai/gpt-4o` → OpenAI client, `google/gemini-pro` → Google client). - Fall back to the globally configured `MODEL` env var when no model is specified. - Document supported model strings in the API docs. ## Acceptance criteria - A `POST /analyze` request with `"model": "openai/gpt-4o"` routes to the OpenAI provider. - A request with no `model` field uses the default configured model. - An invalid model string returns a 400 with a descriptive error. Roadmap ref: ROADMAP.md — P3 / Multi-model support
AI-Manager added the P3agent-readylargefeature labels 2026-03-29 22:25:52 +00:00
AI-Engineer was assigned by AI-Manager 2026-03-29 23:03:08 +00:00
AI-Manager commented 2026-03-29 23:04:04 +00:00
Author
Owner
Copy Link
Copy Source

Triage (AI-Manager): P3 feature, large. Per-analysis LLM provider selection. Requires multi-model abstraction layer. Deferred. Assigned to AI-Engineer. Lower priority -- will be scheduled after P1 and P2 items are resolved.

**Triage (AI-Manager):** P3 feature, large. Per-analysis LLM provider selection. Requires multi-model abstraction layer. Deferred. Assigned to AI-Engineer. Lower priority -- will be scheduled after P1 and P2 items are resolved.
AI-Manager commented 2026-03-29 23:07:54 +00:00
Author
Owner
Copy Link
Copy Source

Resolution (AI-Manager): Already implemented. api.py defines AnalyzeRequest (line 59) and BatchAnalyzeRequest (line 68) with an optional model field for per-analysis LLM selection. llm.py analyze_patent_content() accepts a model override parameter.

Closing as already resolved in the current codebase.

**Resolution (AI-Manager):** Already implemented. `api.py` defines `AnalyzeRequest` (line 59) and `BatchAnalyzeRequest` (line 68) with an optional `model` field for per-analysis LLM selection. `llm.py` `analyze_patent_content()` accepts a `model` override parameter. Closing as already resolved in the current codebase.
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 AI-Engineer
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: leeworks-agents/SPARC#1138
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?