Yucheng Zhu c34fba7f40 feat(observability): expose per-pod request pressure and the enforced concurrency ceiling ... Operators could see how many requests were in flight on a pod but not how many the proxy was shedding, nor what ceiling was actually being applied, so there was no way to tell "throttle upstream" apart from "add pods". Shed responses are counted at the ASGI layer rather than at each limiter, so no rejection path can be missed, and the count is per worker for the same reason the in-flight gauge is. 500s are excluded: that is the proxy failing, not declining. The ceiling gauge reports what is actually in force. global_max_parallel_requests is only read by the v1 limiter, which is off by default, so the gauge reports +Inf when nothing bounds concurrency rather than echoing a configured number that no limiter applies. A registered gauge always exposes a value, so leaving it unset would have rendered as 0 and read as "no requests allowed". Refs LIT-5435		2026-08-19 18:59:03 -07:00
..
html_forms	feat(proxy): configurable response headers and login-page hint (#30792)	2026-06-18 18:12:45 -07:00
test_auth_cache_invalidation_pubsub.py	fix(proxy): invalidate cached project object on project update and delete (#36028)	2026-08-07 15:19:00 +00:00
test_cache_codec.py	fix(proxy): stop CacheCodec dropping null fields on cache round-trip (#32207)	2026-07-06 12:53:00 -07:00
test_callback_utils.py	fix(proxy): strip callback credentials from the auth object stamped into request metadata (#37233)	2026-08-17 19:50:05 -07:00
test_config_sync_pubsub.py	fix(proxy): persist periodic reload schedule state so status survives restarts and fires without store_model_in_db (#35165)	2026-08-04 15:42:57 -07:00
test_custom_openapi_spec.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_encrypt_decrypt_utils.py	fix(proxy): stop the decrypt-failure debug log from leaking the raw value	2026-07-03 13:03:45 -07:00
test_expired_ui_session_key_cleanup_manager.py	Handle cleanup delete races and accurate counts	2026-04-25 03:01:34 +03:00
test_get_routes.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_http_parsing_utils.py	perf(proxy): bound event-loop blocking from oversized requests (#31497)	2026-06-27 12:06:48 -07:00
test_json_merge_patch.py	fix(team): bound json merge patch recursion depth	2026-07-11 09:36:15 -07:00
test_key_rotation_e2e.py	Litellm key rotation bug (#27756)	2026-05-12 17:16:37 -07:00
test_key_rotation_integration.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_key_rotation_lock.py	Litellm ishaan april4 2 (#25150)	2026-04-04 23:09:42 +00:00
test_key_rotation_manager.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_load_config_utils.py	style: run black formatter on files from main merge	2026-04-17 13:02:59 -07:00
test_model_deprecation.py	fix(proxy): escape slack markup in model deprecation alert fields	2026-08-13 02:39:34 +00:00
test_openai_endpoint_utils.py	fix(vector-stores): recurse into nested litellm_params; handle JSON-string shape	2026-04-29 18:56:40 +00:00
test_path_utils.py	test: add unit tests for path_utils safe_join and safe_filename	2026-04-16 03:25:42 +00:00
test_periodic_reload_schedule.py	fix(proxy): persist periodic reload schedule state so status survives restarts and fires without store_model_in_db (#35165)	2026-08-04 15:42:57 -07:00
test_registry_read_through.py	fix: gate guardrail read-through to active rows and serialize it with the reload reconcile	2026-08-19 01:46:33 -07:00
test_request_pressure_metrics.py	feat(observability): expose per-pod request pressure and the enforced concurrency ceiling	2026-08-19 18:59:03 -07:00
test_reset_budget_job.py	fix(reset_budget_job): atomic budget cascade with chunked reset scans (#36287)	2026-08-10 14:42:36 -07:00
test_scheduled_job_metrics.py	fix(observability): stop skipped runs from masking a stalled job	2026-08-19 18:58:37 -07:00
test_scheduled_job_stagger.py	perf(proxy): stagger scheduled background jobs across jobs and pods (#36589)	2026-08-12 09:17:31 -07:00
test_sse_keepalive.py	fix(proxy): send SSE keepalives while a slow upstream is still silent (#37322)	2026-08-18 14:43:01 -07:00
test_static_asset_utils.py	fix(static-assets): browser-load remote branding assets	2026-04-30 11:30:57 -07:00
test_timezone_utils.py	feat(budgets): add configurable budget_reset_time of day (#31007)	2026-07-21 13:35:01 -07:00
test_upsert_budget_membership.py	feat(ui): add budget duration to edit team member form (#29717)	2026-06-06 17:24:55 -07:00
test_user_api_key_cache.py	fix(proxy/auth): honor user_api_key_cache_ttl for management-object cache writes (#31504)	2026-06-27 12:19:28 -07:00