MeshBot/src/llm/llm.service.spec.ts

import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest';
import type { ChatMessage } from './llm.service.js';
import { LlmService } from './llm.service.js';

const BASE = 'http://192.168.1.70:1111/v1';

function json(body: unknown): Response {
  return { ok: true, status: 200, json: async () => body } as Response;
}

/** Fresh service with a clean env (explicit base/model/timeout). */
function makeService(): LlmService {
  process.env.LLM_API_BASE = BASE;
  process.env.LLM_MODEL = 'qwen3.8-27b';
  process.env.LLM_TIMEOUT_MS = '60000';
  return new LlmService();
}

describe('LlmService', () => {
  let fetchMock: ReturnType<typeof vi.fn>;

  beforeEach(() => {
    fetchMock = vi.fn();
    vi.stubGlobal('fetch', fetchMock);
  });

  afterEach(() => {
    vi.unstubAllGlobals();
    for (const k of ['LLM_API_BASE', 'LLM_MODEL', 'LLM_TIMEOUT_MS'])
      delete process.env[k];
  });

  it('listModels returns the data[].id strings from GET /models', async () => {
    const svc = makeService();
    fetchMock.mockResolvedValueOnce(
      json({
        data: [
          { id: 'qwen3.8-27b' },
          { id: 'text-embedding-nomic-embed-text-v1.5' },
        ],
      }),
    );

    await expect(svc.listModels()).resolves.toEqual([
      'qwen3.8-27b',
      'text-embedding-nomic-embed-text-v1.5',
    ]);
    expect(fetchMock).toHaveBeenCalledTimes(1);
    expect(fetchMock.mock.calls[0][0]).toBe(`${BASE}/models`);
  });

  it('chat posts model+messages and returns choices[0].message.content', async () => {
    const svc = makeService();
    fetchMock.mockResolvedValueOnce(
      json({ choices: [{ message: { content: 'hello back' } }] }),
    );

    const messages: ChatMessage[] = [
      { role: 'system', content: 'be brief' },
      { role: 'user', content: 'hi' },
    ];
    await expect(
      svc.chat(messages, { maxTokens: 50, temperature: 0.2 }),
    ).resolves.toBe('hello back');

    const [url, init] = fetchMock.mock.calls[0];
    expect(url).toBe(`${BASE}/chat/completions`);
    expect(init.method).toBe('POST');
    expect(JSON.parse(init.body)).toEqual({
      model: 'qwen3.8-27b',
      messages,
      maxTokens: 50,
      temperature: 0.2,
    });
  });

  it('chat throws on non-2xx with the HTTP status in the message', async () => {
    const svc = makeService();
    fetchMock.mockResolvedValueOnce({
      ok: false,
      status: 503,
      text: async () => 'upstream down',
    } as Response);

    await expect(svc.chat([{ role: 'user', content: 'hi' }])).rejects.toThrow(
      /HTTP 503.*upstream down/,
    );
  });

  it('summarize calls chat with the system prompt plus the user text', async () => {
    const svc = makeService();
    fetchMock.mockResolvedValueOnce(
      json({ choices: [{ message: { content: 'the summary' } }] }),
    );

    await expect(svc.summarize('a long text')).resolves.toBe('the summary');

    const [, init] = fetchMock.mock.calls[0];
    expect(JSON.parse(init.body).messages).toEqual([
      { role: 'system', content: 'Summarize the following text concisely.' },
      { role: 'user', content: 'a long text' },
    ]);
  });
});