shivam 165ea273de fix(proxy): refresh models_by_provider on cost map reload so wildcard expansion picks up new models ... add_known_models mutates the per-provider sets, but models_by_provider was a frozen snapshot built once at import via | set unions, so newly added models never reached get_valid_models / get_known_models_from_wildcard. Rebuild models_by_provider from the live sets at the end of add_known_models. Also add a missing add_known_models branch for the bare vertex_ai provider so those models bucket into vertex_ai_models and expand under vertex_ai/*, and make the reload endpoint report a no-op (instead of success) when LITELLM_LOCAL_MODEL_COST_MAP forces the bundled backup map. Resolves LIT-4947 Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>		2026-07-29 21:52:13 +00:00
..
litellm-dashboard	fix(proxy): refresh models_by_provider on cost map reload so wildcard expansion picks up new models	2026-07-29 21:52:13 +00:00
Dockerfile	feat: add componentized proxy deployment with gateway, backend, ui, and migrations (#27557)	2026-05-16 09:25:17 -07:00
nginx.conf	fix(ui): serve /ui/assets from the nginx image instead of SPA fallback (#34066)	2026-07-21 09:22:02 -07:00