import type { ExtensionAPI } from "@earendil-works/pi-coding-agent";

// Local llama.cpp server (llama-server) exposing an OpenAI-compatible API.
// Mirrors .opencode/opencode.json -> provider "llama.cpp".
//
// Start the server with the scripts in ./llama-cpp/ (run_ornith.sh / run_gemma4.sh),
// which listen on http://0.0.0.0:8080 and register model aliases "ornith-1.0" and
// "gemma-4" respectively.

const BASE_URL = "http://localhost:8080/v1";

const MODELS = [
  {
    id: "ornith-1.0",
    name: "Ornith 1.0 (llama.cpp)",
    reasoning: true,
    input: ["text", "image"] as const,
    cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
    contextWindow: 65536,
    maxTokens: 8192,
  },
  {
    id: "gemma-4",
    name: "Gemma 4 12B (llama.cpp)",
    reasoning: true,
    input: ["text", "image"] as const,
    cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
    contextWindow: 131072,
    maxTokens: 8192,
  },
];

export default function (pi: ExtensionAPI) {
  pi.registerProvider("llama-cpp", {
    name: "llama.cpp (local)",
    baseUrl: BASE_URL,
    // llama-server accepts any bearer token; send a placeholder so the
    // Authorization header is present.
    apiKey: "llama-cpp",
    authHeader: true,
    api: "openai-completions",
    models: MODELS,
  });
}