Yassin Kortam a44bb47563 fix(prometheus): fold auth/pre-call time into litellm_request_total_latency_metric (#37958) ... litellm_request_total_latency_metric's start_time is set inside common_processing_pre_call_logic, which only runs after user_api_key_auth has already succeeded, so the metric silently excluded authentication and pre-call setup time despite being documented as total request latency. The sibling litellm_request_queue_time_seconds metric had the same problem: its arrival_time was captured after auth too, despite its own comment claiming to track when the request arrived at the proxy. request.state.litellm_received_at is now stamped unconditionally at the very first line of user_api_key_auth (previously only when OTEL was configured), giving a timestamp that precedes all auth work. Both metrics now derive from it: queue_time_seconds genuinely spans arrival through the start of pre-call processing, and the total-latency metric adds that queue time on top of its existing start/end window so it becomes true end-to-end latency. queue_time_seconds ends exactly at start_time rather than a separately captured timestamp, so its window and the total-latency window share a boundary instead of overlapping and double-counting a few lines of setup work on every request.		2026-08-22 14:25:55 -07:00
..
test_admin_viewer_handler_access.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_auth_checks.py	fix(auth): stop the team fallback from widening model access (#37962)	2026-08-22 14:25:29 -07:00
test_auth_exception_handler.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_auth_hot_path_network_requests.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_auth_utils.py	test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769)	2026-08-20 20:24:49 -07:00
test_banned_params_extra_body.py
test_cli_auth.py
test_custom_auth_end_user_budget.py	fix(proxy): registry caches stop per-request tag and end-user Postgres reads in auth (#36801)	2026-08-17 18:52:13 +00:00
test_handle_jwt.py	test: require a match= on broad pytest.raises, and drop duplicate parametrize cases (#37769)	2026-08-20 20:24:49 -07:00
test_info_routes.py
test_litellm_license.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_login_utils.py	test: unwind environment writes in tests/test_litellm with monkeypatch (#37806)	2026-08-21 20:28:37 -07:00
test_mcp_ip_filtering.py
test_model_checks.py	test: enforce F811 so a duplicate definition cannot silently replace the first	2026-08-21 12:06:19 -07:00
test_model_checks_fallbacks.py
test_multi_budget_windows.py
test_network.py
test_oauth2_proxy_hook.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_object_permission_loading.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_onboarding.py
test_organization_budget_enforcement.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_password_hashing.py
test_resolvers_exceptions.py
test_resolvers_models.py
test_resolvers_seam.py
test_resolvers_store.py
test_route_checks.py	test: drop the cwd-relative sys.path.insert calls from the test suite (#37802)	2026-08-22 09:25:58 -07:00
test_router_override_fallback_auth.py
test_team_member_budget.py
test_unmapped_model_budget_enforcement.py
test_user_api_key_auth.py	fix(prometheus): fold auth/pre-call time into litellm_request_total_latency_metric (#37958)	2026-08-22 14:25:55 -07:00