devin-ai-integration[bot] 2d034bb35b perf(proxy): hold one spend counter batch across admission and across post-call accounting (#43369) ... Auth's spend counter MGET scope spans common checks, model budget check and reservation; reservation increments go out as one pipeline; post-call reconcile adjustments ride the ordinary increment pipeline and update_cache uses one batched read. Over-budget reservation counters are charged one at a time so a rejection never touches the counters after it; post-call counter keys are derived from ids without validating a UserAPIKeyAuth. Resolves LIT-8881 Co-authored-by: yassin <yassin@berri.ai> Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>		2026-09-29 15:05:33 -07:00
..
.coverage_baseline
__init__.py
_coverage_check.py
_pin_check.py
conftest.py	refactor(proxy): move login throttle sentinels into constants	2026-09-17 16:42:04 +00:00
test_background_health.py	fix(proxy): release the health check save window lock on failure or cancel	2026-09-03 12:36:04 +02:00
test_exception_handlers.py	fix(proxy): keep the submitted body out of 422 validation errors (#43231)	2026-09-25 17:05:53 -07:00
test_harness_smoke.py
test_lifecycle.py	revert: "feat(usage): search team keys beyond the top-N in the Team usage view (#42857)" (#43377)	2026-09-28 21:47:46 +00:00
test_openapi_customization.py
test_proxy_config.py	feat(proxy): add maximum_daily_tag_spend_retention_period cleanup setting (#39221)	2026-09-26 15:07:56 -07:00
test_routes_anthropic_beta.py
test_routes_assistants.py
test_routes_audio.py	fix(proxy): narrow audio_speech response before reading upstream content-type	2026-08-30 12:46:11 -07:00
test_routes_chat_completions.py
test_routes_completions.py
test_routes_config.py	fix(proxy): persist only the router settings keys the request set	2026-09-18 14:01:05 -07:00
test_routes_embeddings.py
test_routes_invitation.py
test_routes_login_sso.py	test(proxy): give the faked login user the breach-check columns	2026-09-21 19:06:00 +00:00
test_routes_misc.py	feat(ui): let admins supply a dark-mode variant of their custom logo (#37662)	2026-08-20 12:48:55 -07:00
test_routes_model_cost_map.py	test(cost_map): assert provenance without patching module state	2026-09-08 12:47:31 -07:00
test_routes_model_info.py	feat(proxy): let callbacks filter the model listing routes per caller (#43027)	2026-09-24 15:52:44 -07:00
test_routes_model_metrics.py	fix(proxy): report a stored alerting value as db even when it is null	2026-09-21 14:24:32 -07:00
test_routes_models.py	Merge remote-tracking branch 'origin/litellm_internal_staging' into litellm_fix_v1_models_alias_resolution	2026-09-10 13:26:18 +02:00
test_routes_moderations.py
test_routes_onboarding.py	fix(proxy): keep the submitted body out of 422 validation errors (#43231)	2026-09-25 17:05:53 -07:00
test_routes_queue.py
test_routes_threads.py
test_routes_utils.py	fix(router): match provider-prefixed fallback keys for bare model groups served by wildcard deployments (#43062)	2026-09-24 18:08:56 -07:00
test_spend_counters.py	perf(proxy): hold one spend counter batch across admission and across post-call accounting (#43369)	2026-09-29 15:05:33 -07:00
test_streaming_helpers.py	fix(streaming): keep the served service_tier on streamed chunks and spend rows (#42870)	2026-09-29 12:54:17 -07:00
test_team_model_name_translation.py	perf(proxy): serialize /model/info listing once with orjson	2026-09-14 19:47:51 +00:00