feat: add multi-model support for per-analysis LLM selection #64

Merged
AI-Manager merged 2 commits from feature/multi-model into main 2026-03-26 12:14:27 +00:00

2 Commits

Author SHA1 Message Date
agent-company 449055b026 merge: resolve multi-model conflicts with trends and export endpoints
Keeps model selection, analytics trends, and CSV export endpoints.
2026-03-26 12:14:15 +00:00
agent-company 04f4d36307 feat: add multi-model support for per-analysis LLM selection
Allow users to choose the LLM model on a per-analysis basis. The
model field is optional in both single and batch analysis requests,
defaulting to the server-configured MODEL env var. The model used
is recorded in the analysis result and database.

- Add model parameter to LLMAnalyzer.analyze_patent_content and
  analyze_patent_portfolio
- Add model field to CompanyAnalysisResult and API response
- Add model field to BatchAnalysisRequest
- Add GET /models endpoint listing supported models and the default
- Store model in llm_messages metadata for attribution

Closes leeworks-agents/SPARC#37

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 10:28:25 +00:00