ginnoir
c8db5475d3
Wire mic through Whisper-compatible transcriptions on LLM_BASE_URL. Photos upload to MinIO and reach the vision model as base64 image_url parts.
28 lines
932 B
TypeScript
28 lines
932 B
TypeScript
import assert from "node:assert/strict";
|
|
import { describe, it } from "node:test";
|
|
import { buildVisionContentParts, textFromMessageContent } from "../../src/lib/llm/content";
|
|
|
|
describe("llm content helpers", () => {
|
|
it("reads plain string content", () => {
|
|
assert.equal(textFromMessageContent("hello"), "hello");
|
|
});
|
|
|
|
it("joins text parts from multimodal content", () => {
|
|
assert.equal(
|
|
textFromMessageContent([
|
|
{ type: "text", text: "first" },
|
|
{ type: "image_url", image_url: { url: "data:image/png;base64,abc" } },
|
|
{ type: "text", text: "second" },
|
|
]),
|
|
"first\nsecond",
|
|
);
|
|
});
|
|
|
|
it("builds vision parts with fallback prompt when text is empty", () => {
|
|
const parts = buildVisionContentParts("", ["data:image/jpeg;base64,abc"]);
|
|
assert.equal(parts.length, 2);
|
|
assert.equal(parts[0]?.type, "text");
|
|
assert.equal(parts[1]?.type, "image_url");
|
|
});
|
|
});
|