Files
konstruct/packages
Adolfo Delorenzo 669c0b52b3 feat(02-05): multimodal LLM interpretation with image_url content blocks
- Add supports_vision(model_name) to builder.py — detects vision-capable models
  (claude-3*, gpt-4o*, gpt-4-vision*, gemini-pro-vision*, gemini-1.5*, gemini-2*)
  with provider prefix stripping support
- Add generate_presigned_url(storage_key, expiry=3600) to builder.py — generates
  1-hour MinIO presigned URLs via boto3 S3 client
- Add build_messages_with_media() to builder.py — extends build_messages_with_memory()
  with media injection: IMAGE -> image_url blocks for vision models / text fallback for
  non-vision models, DOCUMENT -> text reference with presigned URL
- image_url blocks use 'detail: auto' per OpenAI/LiteLLM multipart format
- Add 27 unit tests in test_multimodal_messages.py (TDD)
2026-03-23 15:09:18 -06:00
..