mirror of
https://github.com/hanzoai/insights.git
synced 2026-11-03 00:52:32 +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.
77 lines
2.6 KiB
Python
77 lines
2.6 KiB
Python
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock
|
|
|
|
import pytest
|
|
|
|
from llm_gateway.config import get_settings
|
|
from llm_gateway.metrics.prometheus import (
|
|
PRODUCT_COST_LIMIT_USD,
|
|
PRODUCT_COST_WINDOW_SECONDS,
|
|
PRODUCT_COST_WINDOW_USD,
|
|
)
|
|
from llm_gateway.rate_limiting.cost_gauge_publisher import _publish_once
|
|
from llm_gateway.rate_limiting.cost_throttles import CostStatus, ProductCostThrottle
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_publish_once_sets_gauges_for_each_product() -> None:
|
|
get_settings.cache_clear()
|
|
throttle = ProductCostThrottle(redis=None)
|
|
throttle.get_status_for_product = AsyncMock( # type: ignore[method-assign]
|
|
side_effect=lambda product: CostStatus(
|
|
used_usd=100.0,
|
|
limit_usd=1000.0,
|
|
remaining_usd=900.0,
|
|
resets_in_seconds=3600,
|
|
exceeded=False,
|
|
)
|
|
)
|
|
|
|
await _publish_once(throttle)
|
|
|
|
for product in get_settings().product_cost_limits:
|
|
assert PRODUCT_COST_WINDOW_USD.labels(product=product)._value.get() == 100.0
|
|
assert PRODUCT_COST_LIMIT_USD.labels(product=product)._value.get() == 1000.0
|
|
assert PRODUCT_COST_WINDOW_SECONDS.labels(product=product)._value.get() == 3600
|
|
get_settings.cache_clear()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_publish_once_skips_failing_product_and_continues() -> None:
|
|
get_settings.cache_clear()
|
|
throttle = ProductCostThrottle(redis=None)
|
|
products = list(get_settings().product_cost_limits.keys())
|
|
assert len(products) >= 2, "test needs at least two configured products"
|
|
failing_product, healthy_product = products[0], products[1]
|
|
|
|
async def fake_status(product: str) -> CostStatus | None:
|
|
if product == failing_product:
|
|
raise RuntimeError("redis boom")
|
|
return CostStatus(
|
|
used_usd=7.0,
|
|
limit_usd=1000.0,
|
|
remaining_usd=993.0,
|
|
resets_in_seconds=60,
|
|
exceeded=False,
|
|
)
|
|
|
|
throttle.get_status_for_product = AsyncMock(side_effect=fake_status) # type: ignore[method-assign]
|
|
|
|
PRODUCT_COST_WINDOW_USD.labels(product=healthy_product).set(0.0)
|
|
|
|
await _publish_once(throttle)
|
|
|
|
assert PRODUCT_COST_WINDOW_USD.labels(product=healthy_product)._value.get() == 7.0
|
|
get_settings.cache_clear()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_publish_once_skips_product_with_no_config() -> None:
|
|
get_settings.cache_clear()
|
|
throttle = ProductCostThrottle(redis=None)
|
|
throttle.get_status_for_product = AsyncMock(return_value=None) # type: ignore[method-assign]
|
|
|
|
await _publish_once(throttle)
|
|
get_settings.cache_clear()
|