Banana Complete

No-bullshit VS Code extension for LLM inline completions via llama.cpp FIM (/infill) endpoints.

Usage

Run a llama.cpp server with /infill support (e.g. ./server -m model.gguf --ctx-size 8192 --host 0.0.0.0 --port 8080)
Configure the extension in VS Code settings (see Configuration)
Place cursor anywhere in a file
Press Cmd+' to trigger an inline completion suggestion

Setting	Default	Description
`banana.baseUrl`	`http://localhost:8080`	Base URL of the llama.cpp server
`banana.n_predict`	`128`	Maximum number of tokens to predict
`banana.t_max_predict_ms`	`500`	Maximum time in milliseconds for prediction
`banana.stop`	`null`	Custom stop tokens (null = omit the field, let model decide when to stop)
`banana.headers`	`{}`	Custom HTTP headers to send with each request. Keys and values must be strings.
`banana.temperature`	`0.6`	Temperature for token sampling (0 = greedy, higher = more random/creative)

Banana Complete automatically injects additional context into each request via the input_extra field:

File info: Project name, language, file path, and cursor position
References: Top completions from VS Code's built-in completion provider
AGENTS.md: If an AGENTS.md file exists in your workspace root, its contents are included as additional context

npm install
npm run compile

npm run package

Icon made by juicy_fish from www.flaticon.com