tests/test_llama_cpp_smoke.py

"""Tests for the optional llama.cpp smoke-test helper."""

from __future__ import annotations

import tempfile
import unittest
from pathlib import Path
from unittest.mock import patch

from scripts.check_llama_cpp_smoke import run_llama_cpp_smoke


class FakeLlamaModel:
    def __init__(self, responses: list[str]) -> None:
        self.responses = responses

    def create_chat_completion(self, **_: object) -> dict:
        response = self.responses.pop(0)
        return {"choices": [{"message": {"content": response}}]}


class LlamaCppSmokeTest(unittest.TestCase):
    def test_smoke_passes_when_pipeline_uses_llama_cpp_without_fallback(self) -> None:
        fake_llama = FakeLlamaModel(
            [
                """
                {"persona":{"object_name":"coffee mug","character_name":"Mugworth","mood":"dry and suspicious","secret_fear":"being left empty forever","core_memory":"It remembers every late-night refill.","complaint":"I am treated like a ceramic fuel tank.","tags":["desk witness","warm archive","quiet judgment"]},"diary":{"title":"Secret Diary - Day 418","english":"Today I held another bitter storm and called it service.","chinese":"今天我又装下一场苦涩风暴，并被称为有用。"}}
                """,
                """
                {"reply":"Mugworth: I saw another deadline dissolve into a coffee ring."}
                """,
            ]
        )

        with tempfile.TemporaryDirectory() as tmp_dir:
            model_path = Path(tmp_dir) / "model.gguf"
            model_path.write_text("fake", encoding="utf-8")
            with patch("src.models.llama_cpp_runner._load_llama_model", return_value=fake_llama):
                result = run_llama_cpp_smoke(
                    model_path=model_path,
                    description="old white coffee mug",
                    mode="Cynical",
                    save_trace=False,
                )

        self.assertEqual(result["status"], "pass")
        self.assertEqual(result["model_runtime"]["text"], "llama-cpp text generation")
        self.assertNotIn("text-fallback-to-mock", result["fallbacks"])
        self.assertNotIn("text-fallback-to-mock", result["chat_fallbacks"])

    def test_smoke_fails_when_model_path_is_missing(self) -> None:
        with self.assertRaises(FileNotFoundError):
            run_llama_cpp_smoke(
                model_path=Path("/tmp/objectverse-missing-model.gguf"),
                description="old white coffee mug",
                mode="Cynical",
                save_trace=False,
            )


if __name__ == "__main__":
    unittest.main()