ryan-crabbe-berri a5f47a271a fix(proxy): re-queue budget window spend increments when the commit fails ... Budget enforcement trusts a current LiteLLM_BudgetWindowSpend row without reconciling it against LiteLLM_SpendLogs, so an increment dropped after a failed commit let the entity spend past its window limit after the next counter reseed. Failed increments now go back on the in-memory queue, or back to the Redis buffer, and retry on the next scheduler tick like every other spend category.		2026-08-29 13:55:36 -07:00
..
test_base_update_queue.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_daily_spend_update_queue.py	feat(spend): report prompt caching savings as total and gateway-attributed (#38134)	2026-08-28 00:19:06 -07:00
test_pod_lock_manager.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_redis_update_buffer.py	fix(proxy): re-queue budget window spend increments when the commit fails	2026-08-29 13:55:36 -07:00
test_spend_logs_partition_manager.py	test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769)	2026-08-20 20:24:49 -07:00
test_spend_update_queue.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_tool_discovery_queue.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_window_spend_update_queue.py	test(proxy): satisfy the test-quality gate for the window spend writer tests	2026-08-29 13:29:59 -07:00