vikingowl 6b7f87dffb fix: Docker backend discovery and vision support for OpenAI-compatible backends ...

Docker compatibility:
- Discovery endpoints now read from OLLAMA_URL, LLAMACPP_URL, LMSTUDIO_URL env vars
- docker-compose.yml sets backends to host.docker.internal for container access
- justfile updated with --host 0.0.0.0 for llama-server

Vision support:
- OpenAI adapter now converts images to content parts array format
- Enables vision models with llama.cpp and LM Studio

Bumps version to 0.7.1

2026-01-23 17:20:33 +01:00

964 B

Raw Permalink Blame History

View Raw