Installation

Install from the Marketplace

Open the Extensions view in VS Code (Ctrl+Shift+X / Cmd+Shift+X), search for LlamaNexus for VSCode, and click Install.

Or install it from the command line:

code --install-extension makershop.llamanexus-for-vs-code

Or install it directly from the Marketplace listing in your browser.

First run

Open the LlamaNexus: Open Chat command (Ctrl+Alt+L / Cmd+Alt+L), or click the LlamaNexus icon in the Activity Bar. Each session stays disabled until you pick a discovered server, or set llamanexus.baseUrl in Settings - see Server discovery.

Notes

• Streaming relies on LlamaNexus forwarding llama-server's SSE stream unmodified through /openai/v1/chat/completions, which is what the current proxy implementation does (including tools/tool_choice/stream_options fields - they pass through untouched).
• If your proxy's chat/completions endpoint expects a model field but you leave llamanexus.model empty, the request omits model entirely; make sure LlamaNexus/llama-server has a model already loaded in that case.
• Context size reporting is authoritative when your proxy's /openai/v1/models response includes context_length sourced from router.preset.ini. It falls back to llamanexus.contextSize for models with no preset entry, or if the request fails.
• Token-usage numbers in the context bar come from the server's own reported usage when available; if the server doesn't report it for a given response, the extension estimates it client-side from character counts instead, and the bar shows a ~ prefix to indicate that.