litellm/litellm/router_utils
Shivam Rawat 836bf0807b fix(router): keep team wildcard routers fresh and prioritize them over global patterns
team_pattern_routers retained deleted/replaced deployments, so team users could
keep resolving stale credentials; now set_model_list resets the registry and
deployment removal prunes it. Also consult the team wildcard router before the
global pattern_router in get_deployment_credentials_with_provider so a global
pattern like "openai/*" no longer shadows the team's own entry

Co-authored-by: Cursor <cursoragent@cursor.com>
2026-07-17 18:19:02 -07:00
..
pre_call_checks fix(router): take the lowest minimum across a model group, not the highest 2026-07-16 19:53:10 -07:00
router_callbacks build(deps-dev): bump black to 26.3.1 and apply formatting (#28525) 2026-05-21 17:24:18 -07:00
add_retry_fallback_headers.py feat(router): add separate ITPM/OTPM deployment rate limits (#31952) 2026-07-05 21:58:35 +05:30
batch_utils.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
client_initalization_utils.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
clientside_credential_handler.py fix(proxy): extend banned-params + admin-clear lists for NVIDIA Riva (VERIA-493) (#31742) 2026-06-30 15:30:08 -07:00
common_utils.py fix(proxy): route master key to team-scoped models (#32926) 2026-07-14 10:11:56 -07:00
cooldown_cache.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
cooldown_callbacks.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
cooldown_handlers.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
fallback_event_handlers.py fix(router): mask provider credentials embedded in fallback error messages (#32083) 2026-07-03 18:48:06 -07:00
get_retry_from_policy.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
handle_error.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
health_state_cache.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
pattern_match_deployments.py fix(router): keep team wildcard routers fresh and prioritize them over global patterns 2026-07-17 18:19:02 -07:00
prompt_caching_cache.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00
response_headers.py LiteLLM Minor Fixes & Improvements (11/26/2024) (#6913) 2024-11-28 00:01:38 +05:30
search_api_router.py style: unify ruff format width on 120 (#31518) 2026-06-27 12:39:29 -07:00