45 lines
1.8 KiB
JavaScript
45 lines
1.8 KiB
JavaScript
// Shared LLM model runtime + selection for every model-backed feature (URL prefill, roast
|
|
// evaluation). One ModelRuntime per process; which model actually runs is decided here:
|
|
// the admin-chosen setting (app_settings.llm_model, passed in as `preferred`) wins, then the
|
|
// LLM_MODEL / PREFILL_MODEL env overrides, then the first available configured model.
|
|
|
|
import { ModelRuntime } from "@earendil-works/pi-coding-agent";
|
|
|
|
let modelRuntimePromise = null;
|
|
export async function getModelRuntime() {
|
|
if (!modelRuntimePromise) modelRuntimePromise = ModelRuntime.create();
|
|
return modelRuntimePromise;
|
|
}
|
|
|
|
export const modelKey = (model) => `${model.provider}:${model.id}`;
|
|
|
|
/** Every configured model, as stable "provider:id" keys for the admin picker. */
|
|
export async function listAvailableModels() {
|
|
const runtime = await getModelRuntime();
|
|
return (await runtime.getAvailable()).map((model) => ({
|
|
key: modelKey(model),
|
|
name: model.name ?? model.id,
|
|
provider: model.provider,
|
|
}));
|
|
}
|
|
|
|
/** @param {string|null} preferred "provider:id" from the admin setting, or empty for auto. */
|
|
export async function pickModel(preferred = null) {
|
|
const runtime = await getModelRuntime();
|
|
for (const candidate of [preferred, process.env.LLM_MODEL, process.env.PREFILL_MODEL]) {
|
|
if (!candidate) continue;
|
|
const sep = candidate.indexOf(":");
|
|
if (sep === -1) continue;
|
|
const model = runtime.getModel(candidate.slice(0, sep), candidate.slice(sep + 1));
|
|
if (model) return model;
|
|
}
|
|
return (await runtime.getAvailable())[0];
|
|
}
|
|
|
|
/** Consistent error for "the server has no usable model" across features. */
|
|
export function noModelError() {
|
|
const err = new Error("Bean Bro is not configured on the server. An admin can choose a provider in Admin → Bean Bro.");
|
|
err.code = "no_model";
|
|
return err;
|
|
}
|