mirror of
https://github.com/headroomlabs-ai/headroom.git
synced 2026-08-27 14:17:10 -04:00
07d89a751d
## Description Adds an explicit, idempotent async cleanup lifecycle for the LiteLLM callback's shared cloud HTTP client. Fixes #2894 ## Type of Change - [x] Bug fix (non-breaking change that fixes an issue) - [ ] New feature (non-breaking change that adds functionality) - [ ] Breaking change (fix or feature that would cause existing functionality to change) - [ ] Documentation update - [ ] Performance improvement - [ ] Code refactoring (no functional changes) ## Changes Made - Added `HeadroomCallback.aclose()` to close the lazily-created `httpx.AsyncClient` and clear its reference. - Made cleanup safe when cloud mode was never used and when shutdown cleanup is invoked more than once. - Added regression coverage for initialized-client cleanup, reference clearing, and repeated/no-op cleanup. ## Testing - [x] Unit tests pass (`pytest`) - [x] Linting passes (`ruff check .`) - [x] Type checking passes (`mypy headroom`) - [x] New tests added for new functionality - [x] Manual testing performed ### Test Output ```text python -m pytest -q tests/test_integrations/test_litellm_callback.py 5 passed ruff check . All checks passed! ruff format --check . 1382 files already formatted python -m mypy headroom Success: no issues found in 515 source files python -m pytest -q Collection blocked in this Windows environment by 174 errors, primarily missing compiled headroom._core; one unrelated test also lacks respx. ``` ## Real Behavior Proof - Environment: Windows, Python 3.12, loopback HTTP server, real `httpx.AsyncClient`. - Exact command / steps: Started a local HTTP server, configured `HeadroomCallback(api_key="hdr_test", api_url="http://127.0.0.1:<port>")`, ran `_cloud_compress()` against it, saved the created client, awaited `callback.aclose()`, then awaited `callback.aclose()` again. - Observed result: The real cloud request succeeded; the client was open during the request, reported closed after `aclose()`, the callback reference became `None`, and repeated cleanup was harmless. - Who maintains it: Headroom Labs maintains this active upstream repository and its LiteLLM integration. - Install surface: No dependencies or install behavior changed. Cloud mode continues to use the existing optional `httpx` dependency; no native code or runtime network access is introduced by this fix. - Not tested: The complete test suite could not run past collection because the local Windows environment lacks the compiled `headroom._core` extension. ## Review Readiness - [x] I have performed a self-review - [x] This PR is ready for human review ## Checklist - [x] My code follows the project's style guidelines - [x] I have performed a self-review of my code - [x] I have commented my code, particularly in hard-to-understand areas - [ ] Documentation changes are not required; `aclose()` is documented in its public docstring and the host owns shutdown sequencing - [x] My changes generate no new warnings - [x] I have added tests that prove my fix is effective or that my feature works - [ ] New and existing unit tests pass locally with my changes (full suite blocked by missing native extension; targeted tests pass) - [x] I did not edit `CHANGELOG.md` - it is generated by release-please from my Conventional Commit PR title. ## Screenshots (if applicable) Not applicable. ## Additional Notes The callback exposes `aclose()` for the host application's async shutdown lifecycle, matching the existing ASGI integration pattern.
82 lines
2.5 KiB
Python
82 lines
2.5 KiB
Python
"""Tests for headroom.integrations.litellm_callback."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import importlib
|
|
import inspect
|
|
from pathlib import Path
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
|
|
import pytest
|
|
|
|
|
|
def _import_callback() -> type:
|
|
# Import the module directly to avoid triggering headroom/integrations/__init__.py
|
|
# which pulls in langchain and the native .so extension.
|
|
module_path = (
|
|
Path(__file__).resolve().parents[2] / "headroom" / "integrations" / "litellm_callback.py"
|
|
)
|
|
spec = importlib.util.spec_from_file_location(
|
|
"headroom.integrations.litellm_callback",
|
|
module_path,
|
|
)
|
|
assert spec is not None and spec.loader is not None
|
|
mod = importlib.util.module_from_spec(spec)
|
|
spec.loader.exec_module(mod) # type: ignore[union-attr]
|
|
return mod.HeadroomCallback # type: ignore[attr-defined]
|
|
|
|
|
|
HeadroomCallback = _import_callback()
|
|
|
|
|
|
class TestHeadroomCallbackPostCallSuccessHook:
|
|
"""async_post_call_success_hook must exist and return response unchanged."""
|
|
|
|
def test_method_exists(self) -> None:
|
|
cb = HeadroomCallback()
|
|
assert hasattr(cb, "async_post_call_success_hook"), (
|
|
"HeadroomCallback must define async_post_call_success_hook "
|
|
"for LiteLLM proxy compatibility"
|
|
)
|
|
|
|
def test_method_is_coroutine(self) -> None:
|
|
cb = HeadroomCallback()
|
|
assert inspect.iscoroutinefunction(cb.async_post_call_success_hook)
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_returns_response_unchanged(self) -> None:
|
|
cb = HeadroomCallback()
|
|
sentinel = object()
|
|
result = await cb.async_post_call_success_hook(
|
|
data={},
|
|
user_api_key_dict=None,
|
|
response=sentinel,
|
|
)
|
|
assert result is sentinel
|
|
|
|
|
|
class TestHeadroomCallbackClientLifecycle:
|
|
"""Cloud client cleanup must be explicit and safe to repeat."""
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_aclose_closes_and_clears_initialized_client(self) -> None:
|
|
cb = HeadroomCallback(api_key="hdr_test")
|
|
client = MagicMock()
|
|
client.aclose = AsyncMock()
|
|
cb._client = client
|
|
|
|
await cb.aclose()
|
|
|
|
client.aclose.assert_awaited_once_with()
|
|
assert cb._client is None
|
|
|
|
await cb.aclose()
|
|
client.aclose.assert_awaited_once_with()
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_aclose_without_initialized_client_is_a_noop(self) -> None:
|
|
cb = HeadroomCallback(api_key="hdr_test")
|
|
|
|
await cb.aclose()
|
|
|
|
assert cb._client is None
|