* feat(llama-cpp): add in-process text inference * test(llama-cpp): narrow setup provider fixture * fix(llama-cpp): trim public surface and refresh docs map * fix(llama-cpp): import Context type in inference test
* fix(memory): move local llama.cpp runtime to provider plugin * chore: ignore llama cpp dynamic dependency * test: remove invalid local provider alias fixture * chore: refresh llama cpp shrinkwrap * chore: drop stale memory embedding defaults facade