mirror of
https://github.com/hanzoai/insights.git
synced 2026-10-30 16:15:31 +00:00
zeekay
1b367e2b62
The tree was a debranded snapshot of upstream taken around 2026-02-20, and upstream has moved about five months since. This replaces it with upstream master, mechanically re-derived: bin/debrand does the rename, and the pipeline and squashed migrations are restored from the shipped tree. Not a merge. The previous import replaced the tree wholesale in a single commit, so there is no shared content history to merge against. Reproducing the rename on the new tree is what actually converges. What survives: .hanzo/workflows, the Dockerfiles and bin/docker* entrypoints, compose files, LLM.md, and insights/migrations. The squashed initial migration is load-bearing — the live database records it by name, so upstream's ~918 individual migrations cannot come back. Nine products are dropped as unreferenced. Twenty-one more that we do not run are kept anyway because the core app still imports them; unpicking those is a refactor and does not belong in a rebase. This base does not build yet, and the reasons are not in the rename: upstream now wants Python 3.13.13 against our 3.12.12 and Django 5.2 against our 4.2, and the dependency manifests still name upstream packages that we republish under our own names. Those are decisions, not renames.
43 lines
2.0 KiB
Python
43 lines
2.0 KiB
Python
from unittest.mock import MagicMock, patch
|
|
|
|
import pytest
|
|
|
|
from llm_gateway import flags
|
|
|
|
|
|
@pytest.fixture(autouse=True)
|
|
def clear_flag_caches() -> None:
|
|
flags._flag_cache.clear()
|
|
flags._flag_unavailable_cache.clear()
|
|
|
|
|
|
@pytest.mark.parametrize("enabled", [True, False])
|
|
async def test_evaluate_flag_caches_definitive_answers(enabled: bool) -> None:
|
|
# Both definitive answers must cache — False (flag disabled) is the normal rollout state, and
|
|
# caching only True would re-hit /flags on every GLM request while the ramp is off.
|
|
client = MagicMock()
|
|
client.feature_enabled.return_value = enabled
|
|
with patch("llm_gateway.flags._get_client", return_value=client):
|
|
assert await flags.evaluate_flag("some-flag", "user-a") is enabled
|
|
assert await flags.evaluate_flag("some-flag", "user-a") is enabled
|
|
# One roundtrip per (flag, user) within the TTL — flag checks sit on the GLM hot path.
|
|
assert client.feature_enabled.call_count == 1
|
|
# sync_mode would otherwise block each uncached evaluation on a $feature_flag_called upload.
|
|
assert client.feature_enabled.call_args.kwargs["send_feature_flag_events"] is False
|
|
|
|
|
|
@pytest.mark.parametrize("failure_mode", ["sdk_error", "sdk_none"])
|
|
async def test_evaluate_flag_backs_off_globally_when_unavailable(failure_mode: str) -> None:
|
|
# An outage (exception) and an SDK None result (flag missing / evaluation unavailable) hit the
|
|
# backoff independently; neither must stack one blocking roundtrip per new user — after the
|
|
# first miss everyone gets the fallback answer until the backoff expires.
|
|
client = MagicMock()
|
|
if failure_mode == "sdk_error":
|
|
client.feature_enabled.side_effect = RuntimeError("insights down")
|
|
else:
|
|
client.feature_enabled.return_value = None
|
|
with patch("llm_gateway.flags._get_client", return_value=client):
|
|
assert await flags.evaluate_flag("some-flag", "user-a") is None
|
|
assert await flags.evaluate_flag("some-flag", "user-b") is None
|
|
assert client.feature_enabled.call_count == 1
|