fegger
081084816b
- Adds abstract aclose() and shared load_prompt() helper to BaseVLMClient. - OllamaClient now logs latency, tokens, and prompt hash per call. - Retries cover HTTP 429 and 5xx in addition to network/timeout errors. - Cache key now includes response_format and max_tokens. - Warns when JSON schema generation falls back to plain 'json' format. - Adds FakeVLMClient.aclose() and cache unit tests.
45 lines
1.8 KiB
Python
45 lines
1.8 KiB
Python
"""Tests for the LLM response cache."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import pytest
|
|
|
|
from odoo_ocr.config import Settings
|
|
from odoo_ocr.utils import cache
|
|
|
|
|
|
@pytest.fixture
|
|
def cache_settings(tmp_path) -> Settings:
|
|
return Settings(cache={"enabled": True, "dir": tmp_path / "llm_cache"})
|
|
|
|
|
|
def test_cache_roundtrip(cache_settings: Settings) -> None:
|
|
response = {"content": "hello", "model": "m", "prompt_tokens": 1}
|
|
cache.set_cached("sys", "user", [b"img"], "model", 0.1, 4096, response, cache_settings)
|
|
assert cache.get_cached("sys", "user", [b"img"], "model", 0.1, 4096, cache_settings) == response
|
|
|
|
|
|
def test_cache_miss(cache_settings: Settings) -> None:
|
|
assert cache.get_cached("a", "b", [], "m", 0.1, 4096, cache_settings) is None
|
|
|
|
|
|
def test_cache_disabled(tmp_path) -> None:
|
|
settings = Settings(cache={"enabled": False, "dir": tmp_path / "llm_cache"})
|
|
cache.set_cached("sys", "user", [], "m", 0.1, 4096, {"content": "x"}, settings)
|
|
assert cache.get_cached("sys", "user", [], "m", 0.1, 4096, settings) is None
|
|
assert not (tmp_path / "llm_cache").exists()
|
|
|
|
|
|
def test_cache_key_includes_temperature_format_and_max_tokens(cache_settings: Settings) -> None:
|
|
response = {"content": "x"}
|
|
cache.set_cached("sys", "user", [], "m", 0.1, 4096, response, cache_settings, format_key="text")
|
|
# Different temperature must not hit the same entry.
|
|
assert cache.get_cached("sys", "user", [], "m", 0.2, 4096, cache_settings) is None
|
|
# Different response_format must not hit the same entry.
|
|
assert (
|
|
cache.get_cached("sys", "user", [], "m", 0.1, 4096, cache_settings, format_key="ExtractedInvoice")
|
|
is None
|
|
)
|
|
# Different max_tokens must not hit the same entry.
|
|
assert cache.get_cached("sys", "user", [], "m", 0.1, 2048, cache_settings) is None
|