mateo-berri b580c13415 feat(prometheus): cap series per metric for every labeled metric ... Add prometheus_metrics_max_series_per_metric: per metric and per worker process, the first N label sets keep a series of their own. Counters and histograms record every later label set on one series whose labels are all "other", so totals stay exact, and gauges skip it. The cap holds with multiple workers because it never needs to remove a series. Add prometheus_metrics_ttl_seconds: a series idle for that long is removed and its slot is freed. The prometheus client cannot remove a series in multi-process mode, so the TTL is ignored there with a startup warning. Both settings are off by default. The end_user caps are unchanged.		2026-10-03 12:19:45 -07:00
..
enterprise_callbacks	fix(otel): name postgres service spans by operation and table (#44240)	2026-10-03 09:20:28 -07:00
integrations	feat(prometheus): cap series per metric for every labeled metric	2026-10-03 12:19:45 -07:00
proxy	fix(vector_stores): return managed file ids from vector store file list (#43800)	2026-10-02 21:28:50 -07:00
__init__.py	test: add __init__.py to migrated tests/unit packages	2026-09-20 11:53:49 +00:00
conftest.py	ci: move caching, proxy-extras, gateway and enterprise tests into tests/unit and run them from litellm-tests (#42902)	2026-09-24 15:49:59 -07:00