Description of change

• feat: chat session response prefix
• feat: improve context shift strategy
• feat: use RAM and swap sizes in memory usage estimations
• feat(inspect gguf command): print a single key flag
• feat: faster building from source
• fix: Electron crash with some models on macOS when not using Metal (via fix: use vm_allocate to allocate CPU backend buffer on macOS ggml-org/llama.cpp#9875)
• fix: adapt to llama.cpp breaking changes
• fix: improve CPU compatibility score
• docs: mention the need to treat node-llama-cpp as an external module in Electron
• docs: sitemap fixes
• docs(README): make the logo be a link
• chore: update issue config

Fixes #361

Pull-Request Checklist

• Code is up-to-date with the master branch
• npm run format to apply eslint formatting
• npm run test passes with this change
• This pull request links relevant issues as Fixes #0000
• There are new or updated unit tests validating the change
• Documentation has been updated to reflect this change
• The new commits and pull request title follow conventions explained in pull request guidelines (PRs that do not follow this convention will not be merged)