### Check for existing issues

- [x] I have searched the existing issues and checked that my issue is not a duplicate.

**Version:** `docker.litellm.ai/berriai/litellm-database:main-stable` (June 2026)

### What happened?

`POST /config/reload` returns HTTP 404. The endpoint does not appear to exist in this build.

### Steps to reproduce

1. Start the proxy with a valid `litellm_config.yaml`. 2. `POST /config/reload` with master key auth. 3. Response is HTTP 404.

### Expected behaviour

The endpoint should reload the YAML config and resync in-memory state. Without it, the only way to pick up config changes or flush stale model state is a full container restart.

This is a bigger problem in the context of #27852 (multi-worker cache invalidation). Even if you want to manually recover from stale worker state, there is no API path to do it short of bouncing the container.

### What part of LiteLLM is this about?

Proxy