- Add 'ollama' to CLI provider choices and auth aliases - Wire Ollama through resolve_provider_client with auto-detection - Add _try_ollama to auxiliary fallback chain (before local/custom) - Add ollama to vision provider order - Update model_metadata.py: ollama prefix + gemma-4-* context lengths (256K) - Default model: gemma4:12b when provider=ollama
107 KiB
107 KiB